65 Artificial Intelligence and Machine Learning in Marketing

Machine learning is the study of algorithms that improve their performance on a task as they are exposed to more data, rather than by being explicitly programmed with the rules of that task. Artificial intelligence (AI) is the broader project of building systems that perform tasks we associate with human cognition; contemporary AI in marketing is, almost entirely, applied machine learning at scale. The distinction matters less than what the two share: a willingness to let flexible, high-capacity function approximators discover structure in data that a human analyst could neither specify in advance nor write down as equations. That willingness is also the source of every pitfall in this chapter.

Marketing is an unusually hospitable host for these methods, for three reasons. First, the field is awash in the kind of data—clickstreams, transactions, images, reviews, search queries—on which modern learning algorithms thrive (Wedel and Kannan 2016; Martin, Borah, and Palmatier 2017). Second, many marketing tasks are natively predictive: which customer will churn, which creative will earn the click, which product to surface next. Prediction is exactly what supervised learning does well. Third, the economic stakes of small improvements are large, because marketing decisions are made billions of times a day across recommendation, bidding, and targeting systems, so a one-percent lift compounds into real money (Varian 2016; Gao, Wang, and Yu 2024).

This chapter has two jobs. The first is to give a working, formal command of the methods—supervised and unsupervised learning, recommender systems, deep learning, and large language models—at a level that lets the reader state each method’s estimator, its assumptions, and the conditions under which it fails. The second is to install a discipline that the hype around AI actively erodes: the distinction between prediction and inference, and with it a sober catalogue of the ways machine learning quietly breaks in deployment—leakage, distribution drift, and unfairness. A model that predicts well in a notebook and harms the business in production is the modal failure, not the exception, and most of those failures are conceptual rather than computational. By the end, the reader should be able to map a marketing problem onto the right learning paradigm, build and validate a model that does not lie to them, and recognize when a predictive tool is being asked, illegitimately, to answer a causal question.

We assume familiarity with the regression and choice-modeling machinery developed earlier in the book (Chapter 35 for measurement; the causal-inference and marketing-mix chapters for identification), and we connect to them rather than re-deriving them.

65.1 Prediction Versus Inference: The Organizing Distinction

The single most consequential idea in this chapter is also the one most often skipped. Consider a generic supervised relationship between an outcome $Y$ and features $\mathbf{X}$, \[ Y = f(\mathbf{X}) + \varepsilon, \qquad \mathbb{E}[\varepsilon \mid \mathbf{X}] = 0, \tag{65.1}\] with $\hat f$ an estimate learned from data. There are two fundamentally different things one can want from $\hat f$, and conflating them is the root of most misuse of machine learning in marketing.

In a prediction problem the object of interest is $\hat f(\mathbf{x})$ itself: we want accurate values of $Y$ at new inputs and treat $\hat f$ as a black box. In an inference problem the object of interest is some functional of $f$—a coefficient, an elasticity, a treatment effect—and $\hat f$ is a means to learn how $\mathbf{X}$ relates to $Y$, not merely to forecast $Y$.

The two goals reward different choices. Prediction tolerates—indeed often prefers—biased, uninterpretable, highly flexible estimators, because the only scorecard is out-of-sample loss, $\mathbb{E}[L(Y, \hat f(\mathbf{X}))]$ on data the model has never seen. The bias–variance trade-off is the governing law: expected squared prediction error decomposes as \[ \mathbb{E}\!\left[(Y - \hat f(\mathbf{x}_0))^2\right] = \underbrace{\big(\mathbb{E}[\hat f(\mathbf{x}_0)] - f(\mathbf{x}_0)\big)^2}_{\text{bias}^2} + \underbrace{\operatorname{Var}\!\big(\hat f(\mathbf{x}_0)\big)}_{\text{variance}} + \underbrace{\sigma^2_\varepsilon}_{\text{irreducible}}, \tag{65.2}\] and a method that accepts some bias to cut variance can win. Inference, by contrast, demands an estimator whose sampling distribution we understand—unbiasedness or a known bias, valid standard errors, an identification argument linking the estimand to features of the data-generating process. A random forest can have lower test error than a linear regression while being useless for the question “what is the effect of a $1 price cut,” because flexible learners trade interpretable, consistent parameters for predictive accuracy (Varian 2016).

The practical hazard is that a predictive model’s coefficients—or its feature-importance scores—look like answers to inference questions and are routinely read as such. They are not. A churn model may load heavily on “number of support tickets,” but acting on that association by suppressing support tickets would be disastrous; the feature predicts churn because both are caused by underlying dissatisfaction. Predictive importance is not causal importance, and no amount of test-set accuracy converts one into the other. When the marketing question is “what will happen,” supervised learning is the right tool; when it is “what should we do,” the model must be embedded in a design that identifies a causal effect—a randomized experiment, an instrument, or one of the causal-machine-learning estimators we reach at the end of the chapter. Figure 65.1 fixes the fork in the road.

flowchart TD
  Q["Marketing question"] --> D{"What is the<br/>object of interest?"}
  D -->|"Accurate Y at new inputs"| P["PREDICTION<br/>(black-box f-hat)"]
  D -->|"A functional of f:<br/>effect, elasticity"| I["INFERENCE<br/>(structure of f)"]
  P --> PV["Validate by:<br/>out-of-sample loss,<br/>cross-validation"]
  I --> IV["Validate by:<br/>identification,<br/>standard errors, design"]
  PV --> PU["Use: scoring, ranking,<br/>forecasting, matching"]
  IV --> IU["Use: pricing, budget<br/>allocation, policy"]
  PU -.->|"Do NOT read feature<br/>importance as causal"| IU

Figure 65.1: The prediction–inference fork. The same data and even the same algorithm serve different goals, validated by different criteria. Reading a predictive model’s internals as causal estimates is the central error this chapter warns against.

65.2 Supervised Learning

In supervised learning the training data are labeled pairs $\{(\mathbf{x}_i, y_i)\}_{i=1}^n$, and the goal is to learn a mapping $\hat f : \mathcal{X} \to \mathcal{Y}$ that generalizes to unlabeled inputs. When $Y$ is continuous the task is regression; when $Y$ is categorical it is classification. Almost every workhorse marketing model—propensity to buy, churn, response, lifetime-value, lead scoring, ad click-through—is a supervised classifier or regressor.

65.2.1 The learning problem and regularization

Formally, learning chooses $\hat f$ to minimize regularized empirical risk, \[ \hat f = \arg\min_{f \in \mathcal{F}} \; \frac{1}{n}\sum_{i=1}^{n} L\big(y_i, f(\mathbf{x}_i)\big) + \lambda\, \Omega(f), \tag{65.3}\] where $L$ is a loss function (squared error for regression, log-loss/cross-entropy for classification), $\mathcal{F}$ is the hypothesis class (linear functions, trees, neural networks), $\Omega(f)$ is a complexity penalty, and $\lambda \ge 0$ tunes the trade-off. Minimizing training loss alone ($\lambda = 0$, $\mathcal{F}$ rich) yields overfitting: $\hat f$ memorizes noise and generalizes poorly, the high-variance failure in Equation 65.2. The penalty $\Omega$ buys generalization by shrinking the effective complexity of $\hat f$. For linear models the two canonical choices are the $\ell_2$ (ridge) penalty $\Omega(\boldsymbol\beta)=\|\boldsymbol\beta\|_2^2$, which shrinks coefficients smoothly, and the $\ell_1$ (lasso) penalty $\Omega(\boldsymbol\beta)=\|\boldsymbol\beta\|_1$, which sets some coefficients exactly to zero and thereby performs variable selection—valuable when the feature space is wide, as it almost always is with behavioral data (Varian 2016).

The assumptions behind Equation 65.3 are easy to state and easy to violate. Empirical risk minimization is consistent for the risk-minimizing $f$ only if the training data are drawn from the same distribution as the deployment data (the identically-distributed assumption) and if observations are exchangeable in the way the validation scheme assumes (commonly independence). Both assumptions fail routinely in marketing: deployment data drift away from training data over time (Section 65.8.2), and observations are correlated within customers, sessions, and time, which—if ignored—makes naïve cross-validation report accuracy the model will never achieve in production.

65.2.2 Tree ensembles: the marketing workhorse

For tabular marketing data—mixed numeric and categorical features, nonlinearities, interactions, missingness—ensembles of decision trees are, empirically, the default high-performer. A single regression tree partitions $\mathcal{X}$ into rectangular regions $R_1,\dots,R_M$ and predicts the within-region mean, $\hat f(\mathbf{x})=\sum_m c_m \mathbf{1}\{\mathbf{x}\in R_m\}$; it is interpretable but high-variance. Two ensemble strategies tame the variance. Random forests average many trees grown on bootstrap samples with randomly restricted split candidates, reducing variance through decorrelation. Gradient-boosted trees instead fit trees sequentially, each new tree $h_t$ targeting the gradient of the loss left by the running ensemble, \[ \hat f_t(\mathbf{x}) = \hat f_{t-1}(\mathbf{x}) + \nu\, h_t(\mathbf{x}), \qquad h_t \approx -\,\frac{\partial L}{\partial \hat f_{t-1}}, \tag{65.4}\] with learning rate $\nu \in (0,1]$. Boosting reduces bias and variance jointly and typically tops leaderboards on tabular data, at the cost of more careful tuning to avoid overfitting (the number of trees becomes a regularization parameter set by validation). The worked example below builds a churn classifier and—critically—shows how to validate it honestly.

Code

set.seed(48)

# --- Simulate a customer-churn dataset with a known structure ----------------
n <- 4000
tenure        <- rpois(n, lambda = 18)                       # months as customer
monthly_spend <- round(rgamma(n, shape = 2, scale = 25), 2)  # $ per month
support_calls <- rpois(n, lambda = 1 + 0.05 * (40 - pmin(tenure, 40)))
discount_user <- rbinom(n, 1, 0.35)

# True churn propensity: short tenure, low spend, many support calls raise risk.
lin <- -1.0 - 0.06 * tenure - 0.015 * monthly_spend +
        0.45 * support_calls + 0.30 * discount_user
prob_churn <- plogis(lin)
churn <- rbinom(n, 1, prob_churn)

dat <- data.frame(churn = factor(churn, labels = c("stay", "leave")),
                  tenure, monthly_spend, support_calls,
                  discount_user = factor(discount_user))

# --- Honest train/test split -------------------------------------------------
idx   <- sample(seq_len(n), size = floor(0.7 * n))
train <- dat[idx, ]
test  <- dat[-idx, ]

# --- Gradient-boosted trees (gbm); fall back to logistic if gbm absent -------
has_gbm <- requireNamespace("gbm", quietly = TRUE)
if (has_gbm) {
  fit <- gbm::gbm(I(as.integer(churn) - 1) ~ tenure + monthly_spend +
                    support_calls + discount_user,
                  data = train, distribution = "bernoulli",
                  n.trees = 600, interaction.depth = 3,
                  shrinkage = 0.03, bag.fraction = 0.7, verbose = FALSE)
  best <- gbm::gbm.perf(fit, plot.it = FALSE, method = "OOB")
  p_hat <- gbm::predict.gbm(fit, test, n.trees = best, type = "response")
} else {
  fit   <- glm(churn ~ tenure + monthly_spend + support_calls + discount_user,
               data = train, family = binomial())
  p_hat <- predict(fit, test, type = "response")
}

# --- Out-of-sample evaluation: AUC and a calibration check -------------------
auc <- function(score, label) {              # rank-based AUC, no extra packages
  pos <- score[label == "leave"]; neg <- score[label == "stay"]
  mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "=="))
}
cat("Test AUC:", round(auc(p_hat, test$churn), 3), "\n")
#> Test AUC: 0.707

# Calibration: do predicted probabilities match realized churn rates?
bins <- cut(p_hat, breaks = quantile(p_hat, 0:5/5), include.lowest = TRUE)
calib <- aggregate(as.integer(test$churn) - 1 ~ bins, FUN = mean)
calib$predicted <- tapply(p_hat, bins, mean)
names(calib) <- c("bin", "observed_churn", "mean_predicted")
calib
#>              bin observed_churn mean_predicted
#> 1 [0.0764,0.109]     0.07083333     0.09603519
#> 2  (0.109,0.131]     0.13333333     0.11983961
#> 3  (0.131,0.163]     0.12033195     0.14376007
#> 4  (0.163,0.237]     0.16317992     0.19626848
#> 5   (0.237,0.67]     0.42083333     0.35999483

The example reports two diagnostics, not one. Discrimination (AUC) measures whether the model ranks churners above non-churners; calibration measures whether a predicted 30% churn probability corresponds to a 30% realized rate. A model can discriminate well yet be badly calibrated, and marketing decisions that multiply predicted probabilities by margins—expected-value targeting—need calibration, not just ranking (Neumann, Tucker, and Whitfield 2019). Reporting only AUC is a common and costly omission.

65.2.3 Classification thresholds and the cost of errors

A classifier outputs a score $\hat p(\mathbf{x}) = \widehat{\Pr}(Y=1\mid\mathbf{x})$; turning it into an action requires a threshold $\tau$ such that we treat customers with $\hat p > \tau$. The optimal threshold is not $0.5$—it depends on the asymmetric costs of false positives and false negatives. If contacting a non-churner costs $c_{\text{FP}}$ and failing to retain a churner costs $c_{\text{FN}}$, the expected-cost-minimizing rule acts when $\hat p / (1-\hat p) > c_{\text{FP}} / c_{\text{FN}}$. This is the point at which the predictive model meets the decision problem, and it is where the marketing economics re-enter: the ROC and precision–recall curves exist precisely because the right operating point is a business choice, not a statistical default.

65.3 Unsupervised Learning

In unsupervised learning the data are unlabeled, $\{\mathbf{x}_i\}_{i=1}^n$, and the goal is to discover latent structure—groups, dimensions, topics—without a target variable to supervise the search. The two dominant marketing uses are segmentation (clustering customers or products) and dimension reduction (compressing high-dimensional behavior into interpretable factors). Because there is no label, there is no test-set accuracy to adjudicate “correctness”; validation is intrinsically harder and more judgmental, which is both the method’s flexibility and its danger.

65.3.1 Clustering and the segmentation problem

The canonical objective is $k$-means, which partitions observations into $K$ clusters to minimize within-cluster squared distance, \[ \min_{\{S_k\}}\; \sum_{k=1}^{K}\sum_{\mathbf{x}_i \in S_k} \big\|\mathbf{x}_i - \boldsymbol\mu_k\big\|_2^2, \qquad \boldsymbol\mu_k = \frac{1}{|S_k|}\sum_{\mathbf{x}_i \in S_k}\mathbf{x}_i. \tag{65.5}\] This connects directly to the a priori versus post hoc segmentation distinction of Section 32.4: post hoc segmentation is precisely the application of a clustering algorithm to behavioral or attitudinal data to discover segments rather than impose them. The estimator (Lloyd’s algorithm) alternates assigning points to the nearest centroid and recomputing centroids; it converges to a local optimum, so results depend on initialization and on the (analyst-chosen) number of clusters $K$. Three assumptions break identification of a “true” segmentation, and all three are routinely violated in practice: $k$-means presumes roughly spherical, equal-variance clusters (Euclidean distance encodes this); it is not scale-invariant, so features must be standardized or the largest-variance feature dominates; and $K$ is not learned but assumed. Model-based clustering via finite mixtures replaces the hard geometry with a probabilistic generative model and lets information criteria choose $K$, at the cost of distributional assumptions. The deeper caution is that a clustering algorithm always returns clusters, whether or not the population is actually clustered; the burden is on the analyst to show the segments are stable, managerially distinguishable, and reproducible out of sample, not merely that the algorithm ran.

Code

set.seed(48)

# Three latent customer segments differing in recency, frequency, monetary value
make_seg <- function(n, r, f, m) data.frame(
  recency   = pmax(1, round(rnorm(n, r, 8))),
  frequency = pmax(1, round(rnorm(n, f, 3))),
  monetary  = pmax(5, round(rnorm(n, m, 40)))
)
rfm <- rbind(make_seg(300, 10, 14,  220),   # champions
             make_seg(300, 45,  4,   60),   # at-risk
             make_seg(300, 25,  8,  130))   # mainstream

# Standardize before clustering: k-means is NOT scale-invariant
rfm_z <- scale(rfm)
km <- kmeans(rfm_z, centers = 3, nstart = 25)

# Profile the recovered segments on the original (interpretable) scale
prof <- aggregate(rfm, by = list(segment = km$cluster), FUN = function(x) round(mean(x), 1))
prof$size <- as.integer(table(km$cluster))
prof
#>   segment recency frequency monetary size
#> 1       1    44.6       4.3     59.0  300
#> 2       2    24.8       8.0    132.6  295
#> 3       3    11.0      14.2    218.6  305

65.3.2 Dimension reduction

When behavior is high-dimensional—thousands of SKUs, pages, or features—dimension reduction finds a low-dimensional representation that preserves the information that matters. Principal component analysis (PCA) projects $\mathbf{X}$ onto the orthogonal directions of maximal variance, the leading eigenvectors of the covariance matrix; the first few components often capture interpretable axes of behavior (e.g., overall intensity, then category mix). Non-negative matrix factorization and, for text, topic models such as latent Dirichlet allocation generalize the idea to parts-based and probabilistic decompositions (Tirunillai and Tellis 2014; Büschken and Allenby 2016). The methods double as a feature-engineering step for supervised models and as a listening tool: factorizing the term–document matrix of online reviews recovers the latent dimensions of quality consumers actually discuss, a structure managers cannot specify in advance (Tirunillai and Tellis 2014; Netzer et al. 2008).

65.4 Recommender Systems

Recommender systems are the most economically consequential deployment of machine learning in marketing: they choose which of millions of items to surface to each user, and on platforms from retail to streaming they drive a large share of demand. Formally, a recommender estimates a utility or preference score $\hat r_{ui}$ for each user $u$ and item $i$, then ranks items by that score. The data are a sparse user–item matrix $\mathbf{R}$, mostly missing, with observed entries being ratings, clicks, or purchases.

Two paradigms, with a hybrid, organize the field. Content-based filtering recommends items similar to those a user has liked, using item features; it handles new items but cannot discover tastes outside a user’s history. Collaborative filtering ignores item content and exploits the wisdom of the crowd—users who agreed in the past will agree in the future—and is the more powerful approach when interaction data are dense. The dominant collaborative formulation is matrix factorization, which embeds users and items in a shared latent space of dimension $K$ and models preference as an inner product, \[ \hat r_{ui} = \mathbf{p}_u^{\top}\mathbf{q}_i + b_u + b_i + \mu, \qquad \min_{\mathbf{P},\mathbf{Q},\mathbf{b}} \sum_{(u,i)\in\mathcal{K}} \big(r_{ui} - \hat r_{ui}\big)^2 + \lambda\big(\|\mathbf{p}_u\|^2 + \|\mathbf{q}_i\|^2 + b_u^2 + b_i^2\big), \tag{65.6}\] where $\mathbf{p}_u, \mathbf{q}_i \in \mathbb{R}^K$ are the learned user and item factors, $b_u, b_i, \mu$ are bias terms, and the sum runs only over observed entries $\mathcal{K}$. The $K$ latent dimensions are discovered, not specified, and often correspond to interpretable axes of taste. The regularizer is essential because $\mathbf{R}$ is extremely sparse.

Three structural problems define the research frontier and the deployment risk. The cold-start problem—no data for new users or items—forces a fallback to content features or popularity until interaction data accrue. Feedback loops are subtler and more dangerous: a recommender trained on logged interactions learns from data its own past recommendations generated, so popular items get recommended, become more popular, and crowd out the long tail, narrowing exposure in ways that can entrench rather than reveal preferences (Zheng et al. 2023). And recommendations that maximize predicted clicks need not maximize incremental value: an item the user would have bought anyway earns the recommender credit it did not create, a confound between prediction and causal lift that only experimentation resolves. The example below factorizes a small implicit-feedback matrix.

Code

set.seed(48)

# --- Simulate implicit feedback from latent tastes (rank-2 truth) ------------
n_users <- 200; n_items <- 60; K_true <- 2
P_true <- matrix(rnorm(n_users * K_true), n_users)
Q_true <- matrix(rnorm(n_items * K_true), n_items)
logits <- P_true %*% t(Q_true)
R <- matrix(rbinom(n_users * n_items, 1, plogis(logits)), n_users)  # 1 = engaged

# Hide 15% of entries as a test set (missing-at-random for illustration)
mask <- matrix(runif(length(R)) > 0.15, n_users)   # TRUE = observed in training
Rtr  <- R; Rtr[!mask] <- NA

# --- Matrix factorization by regularized alternating least squares -----------
K <- 2; lambda <- 0.1; iters <- 30
P <- matrix(rnorm(n_users * K, sd = 0.1), n_users)
Q <- matrix(rnorm(n_items * K, sd = 0.1), n_items)
solve_factor <- function(fixed, target_row, obs) {   # ridge solve per row
  F <- fixed[obs, , drop = FALSE]; y <- target_row[obs]
  solve(t(F) %*% F + lambda * diag(ncol(fixed)), t(F) %*% y)
}
for (it in seq_len(iters)) {
  for (u in seq_len(n_users)) { o <- which(!is.na(Rtr[u, ])); if (length(o)) P[u, ] <- solve_factor(Q, Rtr[u, ], o) }
  for (i in seq_len(n_items)) { o <- which(!is.na(Rtr[, i])); if (length(o)) Q[i, ] <- solve_factor(P, Rtr[, i], o) }
}
R_hat <- P %*% t(Q)

# Evaluate ranking quality on held-out entries via AUC
test_idx <- which(!mask)
auc_rank <- {
  s <- R_hat[test_idx]; y <- R[test_idx]
  pos <- s[y == 1]; neg <- s[y == 0]
  mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "=="))
}
cat("Held-out ranking AUC:", round(auc_rank, 3), "\n")
#> Held-out ranking AUC: 0.65

65.5 Deep Learning

Deep learning refers to neural networks with many layers of learned, nonlinear transformations. A feedforward network composes affine maps and nonlinearities, \[ \hat f(\mathbf{x}) = \sigma_L\!\big(\mathbf{W}_L\,\sigma_{L-1}(\cdots \sigma_1(\mathbf{W}_1\mathbf{x}+\mathbf{b}_1)\cdots)+\mathbf{b}_L\big), \tag{65.7}\] where each $\mathbf{W}_\ell$ is a learned weight matrix, $\mathbf{b}_\ell$ a bias, and $\sigma_\ell$ an elementwise nonlinearity (commonly the rectified linear unit, $\sigma(z)=\max(0,z)$). The parameters are fit by gradient descent on the loss in Equation 65.3, with gradients computed by backpropagation—the chain rule applied layer by layer—and the data scanned in mini-batches (stochastic gradient descent). Depth matters because composition lets the network build features from features: early layers learn simple patterns, later layers compose them into abstractions, so the network learns its own representation rather than relying on hand-engineered features.

The marketing payoff is largest where the data are unstructured—precisely the domains where hand-engineering features is hopeless. Convolutional networks read images, enabling brand-perception measurement directly from consumer-generated photos at a scale and speed no survey could match: Liu, Dzyabura, and Mizik (2020) train a multi-label convolutional network to detect perceptual brand attributes in user images, recovering survey-consistent perceptions in near real time, and image content systematically shapes engagement (Li and Xie 2019). Recurrent and, later, attention-based architectures read sequences—text, clickstreams, purchase histories—turning the unstructured trace of customer behavior into predictive features (Martin, Borah, and Palmatier 2017). . The price of this expressive power is steep: deep models are data-hungry, computationally expensive, prone to overfitting without heavy regularization (dropout, early stopping, weight decay), and—most relevant to this chapter—they are opaque, which makes them excellent predictors and poor instruments of inference. The temptation to read a neural network’s learned representations as explanations is the deep-learning incarnation of the prediction–inference confusion.

For tabular marketing data of modest size, it bears emphasizing that deep learning usually does not beat gradient-boosted trees; the deep-learning advantage is specific to large, unstructured, high-signal data. Choosing a neural network for a 50-feature churn table is a common and avoidable error.

65.6 Large Language Models

Large language models (LLMs) are deep neural networks—almost always transformers, built on the self-attention mechanism—trained on internet-scale text to predict the next token, and then adapted to follow instructions. Their relevance to marketing is twofold. As measurement instruments, they convert the field’s vast unstructured text—reviews, social posts, support transcripts, open-ended survey responses—into structured variables: sentiment, topics, stance, entities, and the latent dimensions of consumer voice that earlier text methods recovered more laboriously (Netzer, Lattin, and Srinivasan 2008; Büschken and Allenby 2016). As generators, they produce marketing content—copy, product descriptions, personalized email, synthetic chat—at near-zero marginal cost, reshaping the economics of content production across the funnel (Appel et al. 2020).

The transformer’s core operation is attention, which lets each token’s representation be a weighted average of the others, with weights computed from learned query, key, and value projections, \[ \operatorname{Attention}(\mathbf{Q},\mathbf{K},\mathbf{V}) = \operatorname{softmax}\!\left(\frac{\mathbf{Q}\mathbf{K}^{\top}}{\sqrt{d_k}}\right)\mathbf{V}, \tag{65.8}\] where $\mathbf{Q},\mathbf{K},\mathbf{V}$ are linear projections of the input sequence and $d_k$ is the key dimension. This mechanism, stacked and scaled, is what lets the model condition each word on the entire context.

Three properties demand discipline when LLMs are used as research instruments. First, hallucination: an LLM optimizes for plausible continuations, not truth, and will fabricate confidently; outputs used as data must be validated against ground truth, ideally with a human-labeled audit sample and an inter-rater reliability check (Chapter 35). Second, non-determinism and version drift: the same prompt can yield different outputs, and the underlying model changes under the analyst’s feet, so a measurement pipeline built on a hosted LLM is not automatically reproducible—prompts, model versions, and decoding parameters must be logged like any other instrument. Third, contamination and circularity: an LLM trained on the open web may have seen the very reviews or constructs under study, so “predicting” them is not out-of-sample, and using an LLM both to generate and to evaluate content risks a closed loop that measures the model’s preferences rather than consumers’. Used as instruments, LLMs are powerful but require the same validity scaffolding as any measure; used as generators, they require the brand-safety, factuality, and fairness controls developed in the rest of this chapter.

65.7 Machine Learning Across the Marketing Funnel

The methods above are not siloed by funnel stage; the same supervised, unsupervised, and generative tools recur, retargeted at different objectives. Organizing them by the customer journey clarifies what is being predicted at each step and where the prediction–inference distinction bites. Table 65.1 maps the terrain, and the recurring lesson is that most funnel applications are predictive scoring problems, while the decisions they feed—how much to spend, what to charge, whom to target—are causal questions that prediction alone cannot answer.

Table 65.1: Machine learning across the marketing funnel. Most applications are predictive scoring tasks; the decisions they inform are causal.

Funnel stage	Representative task	Learning paradigm	Pred. vs. inf.	Anchor
Awareness	Audience look-alike modeling; media-mix forecasting	Supervised classification; sequence models	Prediction (lift is causal)	Wedel and Kannan (2016)
Consideration	Search/social listening; brand-perception mining	Unsupervised; LLM/text	Prediction (measurement)	Netzer et al. (2008); Liu, Dzyabura, and Mizik (2020)
Conversion	Propensity-to-buy; dynamic creative; recommendation	Supervised; recommender	Prediction; targeting is causal	Neumann, Tucker, and Whitfield (2019)
Retention	Churn prediction; next-best-action	Supervised classification	Prediction; action is causal	Neumann, Tucker, and Whitfield (2019)
Advocacy	Review/UGC analysis; influencer identification	Unsupervised; LLM/text	Prediction (measurement)	Tirunillai and Tellis (2014)

The “prediction (lift is causal)” and “action is causal” entries flag the same trap in different clothes. A look-alike model predicts who resembles a converter, but whether advertising to them causes incremental conversion is a question only a holdout experiment answers. A churn model predicts who will leave, but the right retention action depends on who will leave because of, or despite, the intervention—an uplift, not a prediction, problem. The funnel view is useful precisely because it keeps surfacing the boundary the chapter is built around.

65.8 Pitfalls: How Machine Learning Quietly Breaks

A model that scores well offline and fails in production is the rule, not the exception, and the failures cluster into three families: leakage, which inflates offline performance with information that will not exist at decision time; drift, which erodes performance as the world moves away from the training distribution; and unfairness, which encodes and amplifies inequities the data inherited. None of the three is a coding bug; all three are violations of the assumptions behind Equation 65.3. Figure 65.2 situates them in the model lifecycle.

flowchart LR
  A["Data collection"] --> B["Feature engineering<br/>& training"]
  B --> C["Offline validation"]
  C --> D["Deployment &<br/>decisions"]
  D --> E["Monitoring"]
  E -.->|"new data"| A
  B -. "LEAKAGE<br/>(future/target info<br/>leaks into features)" .-> C
  D -. "DRIFT<br/>(world moves away<br/>from training dist.)" .-> E
  D -. "FAIRNESS<br/>(disparate harm at<br/>the decision boundary)" .-> A

Figure 65.2: Where the three pitfalls strike in the machine-learning lifecycle. Leakage corrupts training and validation before deployment; drift degrades a correct model after it; fairness harms accrue at the decision boundary and feed back into future data.

65.8.1 Data leakage

Leakage occurs when information unavailable at prediction time contaminates the training data, so the model “cheats” offline and collapses in production. The signature is an offline metric that is too good to be true. Leakage takes several forms, each common in marketing pipelines. Target leakage includes a feature that is a proxy for, or a consequence of, the outcome—predicting purchase using “added-to-cart in the same session,” which is nearly the outcome itself. Temporal leakage uses information from after the prediction timestamp—computing a customer’s average order value over a window that includes the very order being predicted. Preprocessing leakage is the most insidious because it survives a careful feature audit: when scaling, imputation, feature selection, or target encoding is fit on the full dataset before the train/test split, statistics from the test set bleed into training, and cross-validation reports an accuracy the deployed model cannot reach.

The discipline that prevents leakage is to fit every data-dependent transformation inside the cross-validation fold, on training data only, and to respect time: when data are temporally ordered—as marketing data almost always are—validation must use a forward-chaining split that trains on the past and tests on the future, never a random split that lets the model peek ahead. The example contrasts the two and quantifies the illusion.

Code

set.seed(48)

# Time-ordered data where the signal is non-stationary (drifts over time)
N <- 1500
time  <- seq_len(N)
beta_t <- 1.5 - 1.0 * (time / N)          # the effect of x decays over time
x <- rnorm(N)
y <- as.integer(plogis(-0.2 + beta_t * x + rnorm(N, 0, 0.5)) > 0.5)
df <- data.frame(time, x, y)

auc <- function(score, label) {
  pos <- score[label == 1]; neg <- score[label == 0]
  if (!length(pos) || !length(neg)) return(NA_real_)
  mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "=="))
}

# (a) RANDOM split: leaks future into training on non-stationary data
ridx  <- sample(N, 0.7 * N)
m_rand <- glm(y ~ x, df[ridx, ], family = binomial())
auc_rand <- auc(predict(m_rand, df[-ridx, ], type = "response"), df[-ridx, ]$y)

# (b) FORWARD-CHAINING split: train on past, test on future (honest)
cut    <- floor(0.7 * N)
m_fwd  <- glm(y ~ x, df[df$time <= cut, ], family = binomial())
auc_fwd <- auc(predict(m_fwd, df[df$time > cut, ], type = "response"),
               df[df$time > cut, ]$y)

cat("AUC, random split (optimistic):  ", round(auc_rand, 3), "\n")
#> AUC, random split (optimistic):   0.903
cat("AUC, forward-chaining (honest):  ", round(auc_fwd, 3), "\n")
#> AUC, forward-chaining (honest):   0.865

The random-split AUC overstates the performance the model will actually deliver on future data, because random splitting on a non-stationary process lets the model borrow the future to predict the past. The gap between the two numbers is a direct measure of self-deception, and it is invisible to anyone who validates with a random split—the default in most tutorials.

65.8.2 Distribution drift

Even a leakage-free model decays, because the assumption that deployment data share the training distribution expires. Drift comes in two flavors that demand different responses. Covariate shift changes the input distribution while the relationship is stable, $p_{\text{test}}(\mathbf{x}) \neq p_{\text{train}}(\mathbf{x})$ but $p(y\mid\mathbf{x})$ unchanged—a new acquisition channel brings customers unlike the training population. Concept drift changes the relationship itself, $p_{\text{test}}(y\mid\mathbf{x}) \neq p_{\text{train}}(y\mid\mathbf{x})$—a recession, a competitor’s launch, or a pandemic rewrites how features map to behavior, exactly the non-stationarity simulated above. Marketing is a near-worst case for drift because the environment is adversarial and reflexive: competitors react, consumer tastes move, and—uniquely—the model’s own actions change the data it next sees, so a targeting model trained on one policy’s data is evaluated under another. The defenses are monitoring (track input distributions and live performance against a holdout, and alarm on divergence), scheduled or triggered retraining, and—where decisions feed back into data—maintaining randomized holdouts so the model never fully determines its own training distribution.

65.8.3 Fairness and algorithmic bias

Machine-learning models inherit and can amplify the biases latent in their training data, with legal and ethical force when marketing decisions touch credit, housing, employment, insurance, or protected groups. The mechanism is not malice but statistics: if historical data reflect discrimination, a model that faithfully predicts the historical target reproduces the discrimination, and omitting a protected attribute does not fix it, because correlated proxies (postal code, device, browsing history) reconstruct the attribute—a phenomenon known as redundant encoding.

Fairness must therefore be defined, measured, and traded off explicitly, and a basic impossibility result disciplines expectations: several intuitive fairness criteria—equal false-positive and false-negative rates across groups (equalized odds) versus equal calibration across groups versus statistical parity in selection rates—cannot in general all hold simultaneously unless base rates are equal or the classifier is perfect. There is no single “fair” model; there is a choice among incompatible fairness criteria, and that choice is normative, not technical. The worked example audits a scorer for disparate impact—whether selection rates differ across groups—and shows that proxy features carry bias even when the protected attribute is excluded.

Code

set.seed(48)

n <- 6000
group <- rbinom(n, 1, 0.5)                       # protected attribute A in {0,1}
# A proxy correlated with the protected group (e.g., neighborhood), NOT the label cause
proxy <- rnorm(n, mean = 0.8 * group)
quality <- rnorm(n)                              # the legitimately relevant signal
# True outcome depends ONLY on quality (group is irrelevant to merit)...
y <- rbinom(n, 1, plogis(1.2 * quality))
df <- data.frame(y, quality, proxy, group)

# Model that EXCLUDES the protected attribute but KEEPS the correlated proxy
fit <- glm(y ~ quality + proxy, df, family = binomial())
df$score <- predict(fit, type = "response")
tau <- quantile(df$score, 0.7)                   # select top 30%
df$selected <- as.integer(df$score > tau)

# Disparate impact: ratio of selection rates across groups (4/5ths rule -> >= 0.8)
sel_rate <- tapply(df$selected, df$group, mean)
di_ratio <- min(sel_rate) / max(sel_rate)
cat("Selection rate by group:", round(sel_rate, 3), "\n")
#> Selection rate by group: 0.31 0.291
cat("Disparate-impact ratio:  ", round(di_ratio, 3),
    if (di_ratio < 0.8) " (FAILS 4/5ths rule)" else " (passes)", "\n")
#> Disparate-impact ratio:   0.938  (passes)

The disparate-impact ratio falls below the conventional four-fifths threshold even though the protected attribute never entered the model and plays no role in the true outcome—the proxy alone manufactures the gap. The lesson generalizes: fairness is a property of a model-in-context that must be measured on outcomes, not assumed from the feature list, and remediation (reweighting, constrained optimization, post-hoc threshold adjustment by group) is an explicit, auditable design choice with its own trade-offs against accuracy and against other fairness criteria.

65.9 From Prediction to Decision: Causal Machine Learning

The chapter’s organizing distinction has a constructive resolution. The right way to use machine learning’s flexibility for inference is not to read coefficients off a predictive model but to embed flexible learners inside an estimator whose identification comes from design. Double/debiased machine learning uses nonparametric learners to flexibly absorb high-dimensional confounders while preserving valid inference on a low-dimensional causal parameter, via orthogonalization and cross-fitting that immunize the target estimate against the nuisance learner’s regularization bias. Causal forests and related heterogeneous- treatment-effect estimators adapt tree ensembles to estimate how a treatment effect $\tau(\mathbf{x}) = \mathbb{E}[Y(1) - Y(0)\mid \mathbf{X}=\mathbf{x}]$ varies across customers—the uplift that retention and targeting decisions actually require, as distinct from the level a churn model predicts. These methods, developed in the causal-inference chapters, are the principled bridge from machine learning’s predictive power to the causal questions marketing decisions pose, and they are where the field’s frontier is moving (Varian 2016).

65.10 Key Takeaways

The prediction–inference distinction (Equation 65.1) is the organizing idea: predictive accuracy and causal interpretation are different goals validated by different criteria, and a model’s internals are not causal estimates no matter how well it predicts.
Supervised learning minimizes regularized empirical risk (Equation 65.3); for tabular marketing data, gradient-boosted trees are the empirical default, and honest evaluation requires both discrimination and calibration, on a split that respects time.
Unsupervised learning discovers structure without labels; clustering always returns clusters, so the burden of proof is on the analyst to show segments are stable and managerially meaningful, not merely that the algorithm converged.
Recommender systems turn sparse user–item data into rankings via matrix factorization (Equation 65.6), but cold-start, feedback loops, and the prediction-versus-incremental-lift gap make naïve click-maximization a trap.
Deep learning and LLMs excel on unstructured data (images, text, sequences) and are powerful measurement and generation instruments, but their opacity makes them poor instruments of inference and demands explicit validity, reproducibility, and factuality controls.
The three deployment pitfalls—leakage, drift, and unfairness—are assumption violations, not bugs: validate inside the fold and forward in time, monitor and retrain against a moving world, and measure fairness on outcomes because proxies encode protected attributes even when those attributes are excluded.
The constructive resolution is causal machine learning, which embeds flexible learners inside design-based estimators to recover the uplift that marketing decisions require.

Appel, Gil, Lauren Grewal, Rhonda Hadi, and Andrew T Stephen. 2020. “The Future of Social Media in Marketing.” Journal of the Academy of Marketing Science 48 (1): 79–95.

Büschken, Joachim, and Greg M Allenby. 2016. “Sentence-Based Text Analysis for Customer Reviews.” Marketing Science 35 (6): 953–75.

Gao, Janet, Wenyu Wang, and Xiaoyun Yu. 2024. “Big Fish in Small Ponds: Human Capital Migration and the Rise of Boutique Banks.” Management Science.

Li, Yiyi, and Ying Xie. 2019. “Is a Picture Worth a Thousand Words? An Empirical Study of Image Content and Social Media Engagement.” Journal of Marketing Research 57 (1): 1–19. https://doi.org/10.1177/0022243719881113.

Liu, Liu, Daria Dzyabura, and Natalie Mizik. 2020. “Visual Listening In: Extracting Brand Image Portrayed on Social Media.” Marketing Science 39 (4): 669–86. https://doi.org/10.1287/mksc.2020.1226.

Martin, Kelly D, Abhishek Borah, and Robert W Palmatier. 2017. “Data Privacy: Effects on Customer and Firm Performance.” Journal of Marketing 81 (1): 36–58.

Netzer, Oded, James M Lattin, and Vikram Srinivasan. 2008. “A Hidden Markov Model of Customer Relationship Dynamics.” Marketing Science 27 (2): 185–204.

Netzer, Oded, Olivier Toubia, Eric T. Bradlow, Ely Dahan, Theodoros Evgeniou, Fred M. Feinberg, Eleanor M. Feit, et al. 2008. “Beyond Conjoint Analysis: Advances in Preference Measurement.” Marketing Letters 19 (3-4): 337–54. https://doi.org/10.1007/s11002-008-9046-1.

Neumann, Nico, Catherine E Tucker, and Timothy Whitfield. 2019. “Frontiers: How Effective Is Third-Party Consumer Profiling? Evidence from Field Studies.” Marketing Science 38 (6): 918–26.

Tirunillai, Seshadri, and Gerard J. Tellis. 2014. “Mining Marketing Meaning from Online Chatter: Strategic Brand Analysis of Big Data Using Latent Dirichlet Allocation.” Journal of Marketing Research 51 (4): 463–79. https://doi.org/10.1509/jmr.12.0106.

Varian, Hal R. 2016. “How to Build an Economic Model in Your Spare Time.” The American Economist 61 (1): 81–90. https://doi.org/10.1177/0569434515627089.

Wedel, Michel, and P.K. Kannan. 2016. “Marketing Analytics for Data-Rich Environments.” Journal of Marketing 80 (6): 97–121. https://doi.org/10.1509/jm.15.0413.

Zheng, Shuang, Siliang Tong, Hyeokkoo Eric Kwon, Gordon Burtch, and Xianneng Li. 2023. “Recommending What to Search: Sales Volume and Consumption Diversity Effects of a Query Recommender System.” Available at SSRN 4667778.

# Artificial Intelligence and Machine Learning in Marketing {#sec-ai-ml} *Machine learning* is the study of algorithms that improve their performance on a task as they are exposed to more data, rather than by being explicitly programmed with the rules of that task. *Artificial intelligence* (AI) is the broader project of building systems that perform tasks we associate with human cognition; contemporary AI in marketing is, almost entirely, applied machine learning at scale. The distinction matters less than what the two share: a willingness to let flexible, high-capacity function approximators discover structure in data that a human analyst could neither specify in advance nor write down as equations. That willingness is also the source of every pitfall in this chapter. Marketing is an unusually hospitable host for these methods, for three reasons. First, the field is awash in the kind of data—clickstreams, transactions, images, reviews, search queries—on which modern learning algorithms thrive [@wedel2016; @martin2017data]. Second, many marketing tasks are natively *predictive*: which customer will churn, which creative will earn the click, which product to surface next. Prediction is exactly what supervised learning does well. Third, the economic stakes of small improvements are large, because marketing decisions are made billions of times a day across recommendation, bidding, and targeting systems, so a one-percent lift compounds into real money [@varian2016; @gao2024big]. This chapter has two jobs. The first is to give a working, formal command of the methods—supervised and unsupervised learning, recommender systems, deep learning, and large language models—at a level that lets the reader state each method's estimator, its assumptions, and the conditions under which it fails. The second is to install a discipline that the hype around AI actively erodes: the distinction between **prediction** and **inference**, and with it a sober catalogue of the ways machine learning quietly breaks in deployment—leakage, distribution drift, and unfairness. A model that predicts well in a notebook and harms the business in production is the modal failure, not the exception, and most of those failures are conceptual rather than computational. By the end, the reader should be able to map a marketing problem onto the right learning paradigm, build and validate a model that does not lie to them, and recognize when a predictive tool is being asked, illegitimately, to answer a causal question. We assume familiarity with the regression and choice-modeling machinery developed earlier in the book (@sec-measurement-scales for measurement; the causal-inference and marketing-mix chapters for identification), and we connect to them rather than re-deriving them. ## Prediction Versus Inference: The Organizing Distinction The single most consequential idea in this chapter is also the one most often skipped. Consider a generic supervised relationship between an outcome $Y$ and features $\mathbf{X}$, $$ Y = f(\mathbf{X}) + \varepsilon, \qquad \mathbb{E}[\varepsilon \mid \mathbf{X}] = 0, $$ {#eq-aiml-dgp} with $\hat f$ an estimate learned from data. There are two fundamentally different things one can want from $\hat f$, and conflating them is the root of most misuse of machine learning in marketing. > In a **prediction** problem the object of interest is $\hat f(\mathbf{x})$ itself: > we want accurate values of $Y$ at new inputs and treat $\hat f$ as a black box. In > an **inference** problem the object of interest is some functional of $f$—a > coefficient, an elasticity, a treatment effect—and $\hat f$ is a means to learn > *how* $\mathbf{X}$ relates to $Y$, not merely to forecast $Y$. The two goals reward different choices. Prediction tolerates—indeed often prefers—biased, uninterpretable, highly flexible estimators, because the only scorecard is out-of-sample loss, $\mathbb{E}[L(Y, \hat f(\mathbf{X}))]$ on data the model has never seen. The bias–variance trade-off is the governing law: expected squared prediction error decomposes as $$ \mathbb{E}\!\left[(Y - \hat f(\mathbf{x}_0))^2\right] = \underbrace{\big(\mathbb{E}[\hat f(\mathbf{x}_0)] - f(\mathbf{x}_0)\big)^2}_{\text{bias}^2} + \underbrace{\operatorname{Var}\!\big(\hat f(\mathbf{x}_0)\big)}_{\text{variance}} + \underbrace{\sigma^2_\varepsilon}_{\text{irreducible}}, $$ {#eq-aiml-bv} and a method that accepts some bias to cut variance can win. Inference, by contrast, demands an estimator whose sampling distribution we understand—unbiasedness or a known bias, valid standard errors, an identification argument linking the estimand to features of the data-generating process. A random forest can have lower test error than a linear regression while being *useless* for the question "what is the effect of a \$1 price cut," because flexible learners trade interpretable, consistent parameters for predictive accuracy [@varian2016]. The practical hazard is that a predictive model's coefficients—or its feature-importance scores—look like answers to inference questions and are routinely read as such. They are not. A churn model may load heavily on "number of support tickets," but acting on that association by *suppressing* support tickets would be disastrous; the feature predicts churn because both are caused by underlying dissatisfaction. Predictive importance is not causal importance, and no amount of test-set accuracy converts one into the other. When the marketing question is "what will happen," supervised learning is the right tool; when it is "what should we do," the model must be embedded in a design that identifies a causal effect—a randomized experiment, an instrument, or one of the causal-machine-learning estimators we reach at the end of the chapter. @fig-aiml-pred-inf fixes the fork in the road. ```{mermaid} %%| label: fig-aiml-pred-inf %%| fig-cap: "The prediction–inference fork. The same data and even the same algorithm serve different goals, validated by different criteria. Reading a predictive model's internals as causal estimates is the central error this chapter warns against." flowchart TD Q["Marketing question"] --> D{"What is the object of interest?"} D -->|"Accurate Y at new inputs"| P["PREDICTION (black-box f-hat)"] D -->|"A functional of f: effect, elasticity"| I["INFERENCE (structure of f)"] P --> PV["Validate by: out-of-sample loss, cross-validation"] I --> IV["Validate by: identification, standard errors, design"] PV --> PU["Use: scoring, ranking, forecasting, matching"] IV --> IU["Use: pricing, budget allocation, policy"] PU -.->|"Do NOT read feature importance as causal"| IU ``` ## Supervised Learning In **supervised learning** the training data are labeled pairs $\{(\mathbf{x}_i, y_i)\}_{i=1}^n$, and the goal is to learn a mapping $\hat f : \mathcal{X} \to \mathcal{Y}$ that generalizes to unlabeled inputs. When $Y$ is continuous the task is *regression*; when $Y$ is categorical it is *classification*. Almost every workhorse marketing model—propensity to buy, churn, response, lifetime-value, lead scoring, ad click-through—is a supervised classifier or regressor. ### The learning problem and regularization Formally, learning chooses $\hat f$ to minimize *regularized empirical risk*, $$ \hat f = \arg\min_{f \in \mathcal{F}} \; \frac{1}{n}\sum_{i=1}^{n} L\big(y_i, f(\mathbf{x}_i)\big) + \lambda\, \Omega(f), $$ {#eq-aiml-erm} where $L$ is a loss function (squared error for regression, log-loss/cross-entropy for classification), $\mathcal{F}$ is the hypothesis class (linear functions, trees, neural networks), $\Omega(f)$ is a complexity penalty, and $\lambda \ge 0$ tunes the trade-off. Minimizing training loss alone ($\lambda = 0$, $\mathcal{F}$ rich) yields *overfitting*: $\hat f$ memorizes noise and generalizes poorly, the high-variance failure in @eq-aiml-bv. The penalty $\Omega$ buys generalization by shrinking the effective complexity of $\hat f$. For linear models the two canonical choices are the $\ell_2$ (ridge) penalty $\Omega(\boldsymbol\beta)=\|\boldsymbol\beta\|_2^2$, which shrinks coefficients smoothly, and the $\ell_1$ (lasso) penalty $\Omega(\boldsymbol\beta)=\|\boldsymbol\beta\|_1$, which sets some coefficients exactly to zero and thereby performs variable selection—valuable when the feature space is wide, as it almost always is with behavioral data [@varian2016]. The assumptions behind @eq-aiml-erm are easy to state and easy to violate. Empirical risk minimization is consistent for the risk-minimizing $f$ only if the training data are drawn from the *same distribution* as the deployment data (the identically-distributed assumption) and if observations are *exchangeable* in the way the validation scheme assumes (commonly independence). Both assumptions fail routinely in marketing: deployment data drift away from training data over time (@sec-aiml-drift), and observations are correlated within customers, sessions, and time, which—if ignored—makes naïve cross-validation report accuracy the model will never achieve in production. ### Tree ensembles: the marketing workhorse For tabular marketing data—mixed numeric and categorical features, nonlinearities, interactions, missingness—ensembles of decision trees are, empirically, the default high-performer. A single regression tree partitions $\mathcal{X}$ into rectangular regions $R_1,\dots,R_M$ and predicts the within-region mean, $\hat f(\mathbf{x})=\sum_m c_m \mathbf{1}\{\mathbf{x}\in R_m\}$; it is interpretable but high-variance. Two ensemble strategies tame the variance. **Random forests** average many trees grown on bootstrap samples with randomly restricted split candidates, reducing variance through decorrelation. **Gradient-boosted trees** instead fit trees *sequentially*, each new tree $h_t$ targeting the gradient of the loss left by the running ensemble, $$ \hat f_t(\mathbf{x}) = \hat f_{t-1}(\mathbf{x}) + \nu\, h_t(\mathbf{x}), \qquad h_t \approx -\,\frac{\partial L}{\partial \hat f_{t-1}}, $$ {#eq-aiml-boost} with learning rate $\nu \in (0,1]$. Boosting reduces bias and variance jointly and typically tops leaderboards on tabular data, at the cost of more careful tuning to avoid overfitting (the number of trees becomes a regularization parameter set by validation). The worked example below builds a churn classifier and—critically—shows how to validate it honestly.  ```{r aiml-churn, message=FALSE, warning=FALSE} set.seed(48) # --- Simulate a customer-churn dataset with a known structure ---------------- n <- 4000 tenure <- rpois(n, lambda = 18) # months as customer monthly_spend <- round(rgamma(n, shape = 2, scale = 25), 2) # $ per month support_calls <- rpois(n, lambda = 1 + 0.05 * (40 - pmin(tenure, 40))) discount_user <- rbinom(n, 1, 0.35) # True churn propensity: short tenure, low spend, many support calls raise risk. lin <- -1.0 - 0.06 * tenure - 0.015 * monthly_spend + 0.45 * support_calls + 0.30 * discount_user prob_churn <- plogis(lin) churn <- rbinom(n, 1, prob_churn) dat <- data.frame(churn = factor(churn, labels = c("stay", "leave")), tenure, monthly_spend, support_calls, discount_user = factor(discount_user)) # --- Honest train/test split ------------------------------------------------- idx <- sample(seq_len(n), size = floor(0.7 * n)) train <- dat[idx, ] test <- dat[-idx, ] # --- Gradient-boosted trees (gbm); fall back to logistic if gbm absent ------- has_gbm <- requireNamespace("gbm", quietly = TRUE) if (has_gbm) { fit <- gbm::gbm(I(as.integer(churn) - 1) ~ tenure + monthly_spend + support_calls + discount_user, data = train, distribution = "bernoulli", n.trees = 600, interaction.depth = 3, shrinkage = 0.03, bag.fraction = 0.7, verbose = FALSE) best <- gbm::gbm.perf(fit, plot.it = FALSE, method = "OOB") p_hat <- gbm::predict.gbm(fit, test, n.trees = best, type = "response") } else { fit <- glm(churn ~ tenure + monthly_spend + support_calls + discount_user, data = train, family = binomial()) p_hat <- predict(fit, test, type = "response") } # --- Out-of-sample evaluation: AUC and a calibration check ------------------- auc <- function(score, label) { # rank-based AUC, no extra packages pos <- score[label == "leave"]; neg <- score[label == "stay"] mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "==")) } cat("Test AUC:", round(auc(p_hat, test$churn), 3), "\n") # Calibration: do predicted probabilities match realized churn rates? bins <- cut(p_hat, breaks = quantile(p_hat, 0:5/5), include.lowest = TRUE) calib <- aggregate(as.integer(test$churn) - 1 ~ bins, FUN = mean) calib$predicted <- tapply(p_hat, bins, mean) names(calib) <- c("bin", "observed_churn", "mean_predicted") calib ``` The example reports two diagnostics, not one. *Discrimination* (AUC) measures whether the model ranks churners above non-churners; *calibration* measures whether a predicted 30% churn probability corresponds to a 30% realized rate. A model can discriminate well yet be badly calibrated, and marketing decisions that multiply predicted probabilities by margins—expected-value targeting—need calibration, not just ranking [@neumann2019frontiers]. Reporting only AUC is a common and costly omission. ### Classification thresholds and the cost of errors A classifier outputs a score $\hat p(\mathbf{x}) = \widehat{\Pr}(Y=1\mid\mathbf{x})$; turning it into an action requires a threshold $\tau$ such that we treat customers with $\hat p > \tau$. The optimal threshold is *not* $0.5$—it depends on the asymmetric costs of false positives and false negatives. If contacting a non-churner costs $c_{\text{FP}}$ and failing to retain a churner costs $c_{\text{FN}}$, the expected-cost-minimizing rule acts when $\hat p / (1-\hat p) > c_{\text{FP}} / c_{\text{FN}}$. This is the point at which the predictive model meets the decision problem, and it is where the marketing economics re-enter: the ROC and precision–recall curves exist precisely because the right operating point is a business choice, not a statistical default. ## Unsupervised Learning In **unsupervised learning** the data are unlabeled, $\{\mathbf{x}_i\}_{i=1}^n$, and the goal is to discover latent structure—groups, dimensions, topics—without a target variable to supervise the search. The two dominant marketing uses are *segmentation* (clustering customers or products) and *dimension reduction* (compressing high-dimensional behavior into interpretable factors). Because there is no label, there is no test-set accuracy to adjudicate "correctness"; validation is intrinsically harder and more judgmental, which is both the method's flexibility and its danger. ### Clustering and the segmentation problem The canonical objective is *$k$-means*, which partitions observations into $K$ clusters to minimize within-cluster squared distance, $$ \min_{\{S_k\}}\; \sum_{k=1}^{K}\sum_{\mathbf{x}_i \in S_k} \big\|\mathbf{x}_i - \boldsymbol\mu_k\big\|_2^2, \qquad \boldsymbol\mu_k = \frac{1}{|S_k|}\sum_{\mathbf{x}_i \in S_k}\mathbf{x}_i. $$ {#eq-aiml-kmeans} This connects directly to the *a priori* versus *post hoc* segmentation distinction of @sec-segmentation: post hoc segmentation is precisely the application of a clustering algorithm to behavioral or attitudinal data to *discover* segments rather than impose them. The estimator (Lloyd's algorithm) alternates assigning points to the nearest centroid and recomputing centroids; it converges to a *local* optimum, so results depend on initialization and on the (analyst-chosen) number of clusters $K$. Three assumptions break identification of a "true" segmentation, and all three are routinely violated in practice: $k$-means presumes roughly spherical, equal-variance clusters (Euclidean distance encodes this); it is not scale-invariant, so features must be standardized or the largest-variance feature dominates; and $K$ is not learned but assumed. Model-based clustering via finite mixtures replaces the hard geometry with a probabilistic generative model and lets information criteria choose $K$, at the cost of distributional assumptions. The deeper caution is that a clustering algorithm *always* returns clusters, whether or not the population is actually clustered; the burden is on the analyst to show the segments are stable, managerially distinguishable, and reproducible out of sample, not merely that the algorithm ran. ```{r aiml-segmentation, message=FALSE, warning=FALSE} set.seed(48) # Three latent customer segments differing in recency, frequency, monetary value make_seg <- function(n, r, f, m) data.frame( recency = pmax(1, round(rnorm(n, r, 8))), frequency = pmax(1, round(rnorm(n, f, 3))), monetary = pmax(5, round(rnorm(n, m, 40))) ) rfm <- rbind(make_seg(300, 10, 14, 220), # champions make_seg(300, 45, 4, 60), # at-risk make_seg(300, 25, 8, 130)) # mainstream # Standardize before clustering: k-means is NOT scale-invariant rfm_z <- scale(rfm) km <- kmeans(rfm_z, centers = 3, nstart = 25) # Profile the recovered segments on the original (interpretable) scale prof <- aggregate(rfm, by = list(segment = km$cluster), FUN = function(x) round(mean(x), 1)) prof$size <- as.integer(table(km$cluster)) prof ``` ### Dimension reduction When behavior is high-dimensional—thousands of SKUs, pages, or features—*dimension reduction* finds a low-dimensional representation that preserves the information that matters. Principal component analysis (PCA) projects $\mathbf{X}$ onto the orthogonal directions of maximal variance, the leading eigenvectors of the covariance matrix; the first few components often capture interpretable axes of behavior (e.g., overall intensity, then category mix). Non-negative matrix factorization and, for text, *topic models* such as latent Dirichlet allocation generalize the idea to parts-based and probabilistic decompositions [@tirunillai2014a; @buschken2016sentence]. The methods double as a feature-engineering step for supervised models and as a listening tool: factorizing the term–document matrix of online reviews recovers the latent dimensions of quality consumers actually discuss, a structure managers cannot specify in advance [@tirunillai2014a; @netzer2008]. ## Recommender Systems Recommender systems are the most economically consequential deployment of machine learning in marketing: they choose which of millions of items to surface to each user, and on platforms from retail to streaming they drive a large share of demand. Formally, a recommender estimates a *utility* or *preference* score $\hat r_{ui}$ for each user $u$ and item $i$, then ranks items by that score. The data are a sparse user–item matrix $\mathbf{R}$, mostly missing, with observed entries being ratings, clicks, or purchases. Two paradigms, with a hybrid, organize the field. **Content-based** filtering recommends items similar to those a user has liked, using item features; it handles new items but cannot discover tastes outside a user's history. **Collaborative filtering** ignores item content and exploits the wisdom of the crowd—users who agreed in the past will agree in the future—and is the more powerful approach when interaction data are dense. The dominant collaborative formulation is *matrix factorization*, which embeds users and items in a shared latent space of dimension $K$ and models preference as an inner product, $$ \hat r_{ui} = \mathbf{p}_u^{\top}\mathbf{q}_i + b_u + b_i + \mu, \qquad \min_{\mathbf{P},\mathbf{Q},\mathbf{b}} \sum_{(u,i)\in\mathcal{K}} \big(r_{ui} - \hat r_{ui}\big)^2 + \lambda\big(\|\mathbf{p}_u\|^2 + \|\mathbf{q}_i\|^2 + b_u^2 + b_i^2\big), $$ {#eq-aiml-mf} where $\mathbf{p}_u, \mathbf{q}_i \in \mathbb{R}^K$ are the learned user and item factors, $b_u, b_i, \mu$ are bias terms, and the sum runs only over *observed* entries $\mathcal{K}$. The $K$ latent dimensions are discovered, not specified, and often correspond to interpretable axes of taste. The regularizer is essential because $\mathbf{R}$ is extremely sparse.  Three structural problems define the research frontier and the deployment risk. The **cold-start** problem—no data for new users or items—forces a fallback to content features or popularity until interaction data accrue. **Feedback loops** are subtler and more dangerous: a recommender trained on logged interactions learns from data its own past recommendations generated, so popular items get recommended, become more popular, and crowd out the long tail, narrowing exposure in ways that can entrench rather than reveal preferences [@zheng2023recommending]. And recommendations that maximize predicted clicks need not maximize *incremental* value: an item the user would have bought anyway earns the recommender credit it did not create, a confound between prediction and causal lift that only experimentation resolves. The example below factorizes a small implicit-feedback matrix. ```{r aiml-recsys, message=FALSE, warning=FALSE} set.seed(48) # --- Simulate implicit feedback from latent tastes (rank-2 truth) ------------ n_users <- 200; n_items <- 60; K_true <- 2 P_true <- matrix(rnorm(n_users * K_true), n_users) Q_true <- matrix(rnorm(n_items * K_true), n_items) logits <- P_true %*% t(Q_true) R <- matrix(rbinom(n_users * n_items, 1, plogis(logits)), n_users) # 1 = engaged # Hide 15% of entries as a test set (missing-at-random for illustration) mask <- matrix(runif(length(R)) > 0.15, n_users) # TRUE = observed in training Rtr <- R; Rtr[!mask] <- NA # --- Matrix factorization by regularized alternating least squares ----------- K <- 2; lambda <- 0.1; iters <- 30 P <- matrix(rnorm(n_users * K, sd = 0.1), n_users) Q <- matrix(rnorm(n_items * K, sd = 0.1), n_items) solve_factor <- function(fixed, target_row, obs) { # ridge solve per row F <- fixed[obs, , drop = FALSE]; y <- target_row[obs] solve(t(F) %*% F + lambda * diag(ncol(fixed)), t(F) %*% y) } for (it in seq_len(iters)) { for (u in seq_len(n_users)) { o <- which(!is.na(Rtr[u, ])); if (length(o)) P[u, ] <- solve_factor(Q, Rtr[u, ], o) } for (i in seq_len(n_items)) { o <- which(!is.na(Rtr[, i])); if (length(o)) Q[i, ] <- solve_factor(P, Rtr[, i], o) } } R_hat <- P %*% t(Q) # Evaluate ranking quality on held-out entries via AUC test_idx <- which(!mask) auc_rank <- { s <- R_hat[test_idx]; y <- R[test_idx] pos <- s[y == 1]; neg <- s[y == 0] mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "==")) } cat("Held-out ranking AUC:", round(auc_rank, 3), "\n") ``` ## Deep Learning *Deep learning* refers to neural networks with many layers of learned, nonlinear transformations. A feedforward network composes affine maps and nonlinearities, $$ \hat f(\mathbf{x}) = \sigma_L\!\big(\mathbf{W}_L\,\sigma_{L-1}(\cdots \sigma_1(\mathbf{W}_1\mathbf{x}+\mathbf{b}_1)\cdots)+\mathbf{b}_L\big), $$ {#eq-aiml-dnn} where each $\mathbf{W}_\ell$ is a learned weight matrix, $\mathbf{b}_\ell$ a bias, and $\sigma_\ell$ an elementwise nonlinearity (commonly the rectified linear unit, $\sigma(z)=\max(0,z)$). The parameters are fit by gradient descent on the loss in @eq-aiml-erm, with gradients computed by *backpropagation*—the chain rule applied layer by layer—and the data scanned in mini-batches (stochastic gradient descent). Depth matters because composition lets the network build features from features: early layers learn simple patterns, later layers compose them into abstractions, so the network learns its own representation rather than relying on hand-engineered features.  The marketing payoff is largest where the data are *unstructured*—precisely the domains where hand-engineering features is hopeless. Convolutional networks read images, enabling brand-perception measurement directly from consumer-generated photos at a scale and speed no survey could match: @liu2020 train a multi-label convolutional network to detect perceptual brand attributes in user images, recovering survey-consistent perceptions in near real time, and image content systematically shapes engagement [@Li_2019]. Recurrent and, later, attention-based architectures read sequences—text, clickstreams, purchase histories—turning the unstructured trace of customer behavior into predictive features [@martin2017data]. . The price of this expressive power is steep: deep models are data-hungry, computationally expensive, prone to overfitting without heavy regularization (dropout, early stopping, weight decay), and—most relevant to this chapter—they are *opaque*, which makes them excellent predictors and poor instruments of inference. The temptation to read a neural network's learned representations as explanations is the deep-learning incarnation of the prediction–inference confusion. For tabular marketing data of modest size, it bears emphasizing that deep learning usually does *not* beat gradient-boosted trees; the deep-learning advantage is specific to large, unstructured, high-signal data. Choosing a neural network for a 50-feature churn table is a common and avoidable error. ## Large Language Models *Large language models* (LLMs) are deep neural networks—almost always *transformers*, built on the self-attention mechanism—trained on internet-scale text to predict the next token, and then adapted to follow instructions. Their relevance to marketing is twofold. As *measurement instruments*, they convert the field's vast unstructured text—reviews, social posts, support transcripts, open-ended survey responses—into structured variables: sentiment, topics, stance, entities, and the latent dimensions of consumer voice that earlier text methods recovered more laboriously [@netzer2008hidden; @buschken2016sentence]. As *generators*, they produce marketing content—copy, product descriptions, personalized email, synthetic chat—at near-zero marginal cost, reshaping the economics of content production across the funnel [@appel2020future]. The transformer's core operation is *attention*, which lets each token's representation be a weighted average of the others, with weights computed from learned query, key, and value projections, $$ \operatorname{Attention}(\mathbf{Q},\mathbf{K},\mathbf{V}) = \operatorname{softmax}\!\left(\frac{\mathbf{Q}\mathbf{K}^{\top}}{\sqrt{d_k}}\right)\mathbf{V}, $$ {#eq-aiml-attn} where $\mathbf{Q},\mathbf{K},\mathbf{V}$ are linear projections of the input sequence and $d_k$ is the key dimension. This mechanism, stacked and scaled, is what lets the model condition each word on the entire context.  Three properties demand discipline when LLMs are used as research instruments. First, **hallucination**: an LLM optimizes for plausible continuations, not truth, and will fabricate confidently; outputs used as data must be validated against ground truth, ideally with a human-labeled audit sample and an inter-rater reliability check (@sec-measurement-scales). Second, **non-determinism and version drift**: the same prompt can yield different outputs, and the underlying model changes under the analyst's feet, so a measurement pipeline built on a hosted LLM is not automatically reproducible—prompts, model versions, and decoding parameters must be logged like any other instrument. Third, **contamination and circularity**: an LLM trained on the open web may have seen the very reviews or constructs under study, so "predicting" them is not out-of-sample, and using an LLM both to generate and to evaluate content risks a closed loop that measures the model's preferences rather than consumers'. Used as instruments, LLMs are powerful but require the same validity scaffolding as any measure; used as generators, they require the brand-safety, factuality, and fairness controls developed in the rest of this chapter. ## Machine Learning Across the Marketing Funnel The methods above are not siloed by funnel stage; the same supervised, unsupervised, and generative tools recur, retargeted at different objectives. Organizing them by the customer journey clarifies *what* is being predicted at each step and *where* the prediction–inference distinction bites. @tbl-aiml-funnel maps the terrain, and the recurring lesson is that most funnel applications are predictive scoring problems, while the decisions they feed—how much to spend, what to charge, whom to target—are causal questions that prediction alone cannot answer. | Funnel stage | Representative task | Learning paradigm | Pred. vs. inf. | Anchor | |---|---|---|---|---| | Awareness | Audience look-alike modeling; media-mix forecasting | Supervised classification; sequence models | Prediction (lift is causal) | @wedel2016 | | Consideration | Search/social listening; brand-perception mining | Unsupervised; LLM/text | Prediction (measurement) | @netzer2008; @liu2020 | | Conversion | Propensity-to-buy; dynamic creative; recommendation | Supervised; recommender | Prediction; *targeting is causal* | @neumann2019frontiers | | Retention | Churn prediction; next-best-action | Supervised classification | Prediction; *action is causal* | @neumann2019frontiers | | Advocacy | Review/UGC analysis; influencer identification | Unsupervised; LLM/text | Prediction (measurement) | @tirunillai2014a | : Machine learning across the marketing funnel. Most applications are predictive scoring tasks; the decisions they inform are causal. {#tbl-aiml-funnel} The "prediction (lift is causal)" and "action is causal" entries flag the same trap in different clothes. A look-alike model predicts who *resembles* a converter, but whether advertising to them *causes* incremental conversion is a question only a holdout experiment answers. A churn model predicts who *will* leave, but the right retention action depends on who will leave *because of, or despite,* the intervention—an uplift, not a prediction, problem.  The funnel view is useful precisely because it keeps surfacing the boundary the chapter is built around. ## Pitfalls: How Machine Learning Quietly Breaks A model that scores well offline and fails in production is the rule, not the exception, and the failures cluster into three families: *leakage*, which inflates offline performance with information that will not exist at decision time; *drift*, which erodes performance as the world moves away from the training distribution; and *unfairness*, which encodes and amplifies inequities the data inherited. None of the three is a coding bug; all three are violations of the assumptions behind @eq-aiml-erm. @fig-aiml-lifecycle situates them in the model lifecycle. ```{mermaid} %%| label: fig-aiml-lifecycle %%| fig-cap: "Where the three pitfalls strike in the machine-learning lifecycle. Leakage corrupts training and validation before deployment; drift degrades a correct model after it; fairness harms accrue at the decision boundary and feed back into future data." flowchart LR A["Data collection"] --> B["Feature engineering & training"] B --> C["Offline validation"] C --> D["Deployment & decisions"] D --> E["Monitoring"] E -.->|"new data"| A B -. "LEAKAGE (future/target info leaks into features)" .-> C D -. "DRIFT (world moves away from training dist.)" .-> E D -. "FAIRNESS (disparate harm at the decision boundary)" .-> A ``` ### Data leakage **Leakage** occurs when information unavailable at prediction time contaminates the training data, so the model "cheats" offline and collapses in production. The signature is an offline metric that is too good to be true. Leakage takes several forms, each common in marketing pipelines. *Target leakage* includes a feature that is a proxy for, or a consequence of, the outcome—predicting purchase using "added-to-cart in the same session," which is nearly the outcome itself. *Temporal leakage* uses information from after the prediction timestamp—computing a customer's average order value over a window that includes the very order being predicted. *Preprocessing leakage* is the most insidious because it survives a careful feature audit: when scaling, imputation, feature selection, or target encoding is fit on the *full* dataset before the train/test split, statistics from the test set bleed into training, and cross-validation reports an accuracy the deployed model cannot reach. The discipline that prevents leakage is to fit *every* data-dependent transformation inside the cross-validation fold, on training data only, and to respect time: when data are temporally ordered—as marketing data almost always are—validation must use a forward-chaining split that trains on the past and tests on the future, never a random split that lets the model peek ahead. The example contrasts the two and quantifies the illusion. ```{r aiml-leakage, message=FALSE, warning=FALSE} set.seed(48) # Time-ordered data where the signal is non-stationary (drifts over time) N <- 1500 time <- seq_len(N) beta_t <- 1.5 - 1.0 * (time / N) # the effect of x decays over time x <- rnorm(N) y <- as.integer(plogis(-0.2 + beta_t * x + rnorm(N, 0, 0.5)) > 0.5) df <- data.frame(time, x, y) auc <- function(score, label) { pos <- score[label == 1]; neg <- score[label == 0] if (!length(pos) || !length(neg)) return(NA_real_) mean(outer(pos, neg, ">") + 0.5 * outer(pos, neg, "==")) } # (a) RANDOM split: leaks future into training on non-stationary data ridx <- sample(N, 0.7 * N) m_rand <- glm(y ~ x, df[ridx, ], family = binomial()) auc_rand <- auc(predict(m_rand, df[-ridx, ], type = "response"), df[-ridx, ]$y) # (b) FORWARD-CHAINING split: train on past, test on future (honest) cut <- floor(0.7 * N) m_fwd <- glm(y ~ x, df[df$time <= cut, ], family = binomial()) auc_fwd <- auc(predict(m_fwd, df[df$time > cut, ], type = "response"), df[df$time > cut, ]$y) cat("AUC, random split (optimistic): ", round(auc_rand, 3), "\n") cat("AUC, forward-chaining (honest): ", round(auc_fwd, 3), "\n") ``` The random-split AUC overstates the performance the model will actually deliver on future data, because random splitting on a non-stationary process lets the model borrow the future to predict the past. The gap between the two numbers is a direct measure of self-deception, and it is invisible to anyone who validates with a random split—the default in most tutorials. ### Distribution drift {#sec-aiml-drift} Even a leakage-free model decays, because the assumption that deployment data share the training distribution expires. **Drift** comes in two flavors that demand different responses. *Covariate shift* changes the input distribution while the relationship is stable, $p_{\text{test}}(\mathbf{x}) \neq p_{\text{train}}(\mathbf{x})$ but $p(y\mid\mathbf{x})$ unchanged—a new acquisition channel brings customers unlike the training population. *Concept drift* changes the relationship itself, $p_{\text{test}}(y\mid\mathbf{x}) \neq p_{\text{train}}(y\mid\mathbf{x})$—a recession, a competitor's launch, or a pandemic rewrites how features map to behavior, exactly the non-stationarity simulated above. Marketing is a near-worst case for drift because the environment is adversarial and reflexive: competitors react, consumer tastes move, and—uniquely—the model's *own actions* change the data it next sees, so a targeting model trained on one policy's data is evaluated under another. The defenses are monitoring (track input distributions and live performance against a holdout, and alarm on divergence), scheduled or triggered retraining, and—where decisions feed back into data—maintaining randomized holdouts so the model never fully determines its own training distribution. ### Fairness and algorithmic bias Machine-learning models inherit and can amplify the biases latent in their training data, with legal and ethical force when marketing decisions touch credit, housing, employment, insurance, or protected groups. The mechanism is not malice but statistics: if historical data reflect discrimination, a model that faithfully predicts the historical target reproduces the discrimination, and *omitting* a protected attribute does not fix it, because correlated proxies (postal code, device, browsing history) reconstruct the attribute—a phenomenon known as redundant encoding. Fairness must therefore be defined, measured, and traded off explicitly, and a basic impossibility result disciplines expectations: several intuitive fairness criteria—equal false-positive and false-negative rates across groups (equalized odds) versus equal calibration across groups versus statistical parity in selection rates—*cannot in general all hold simultaneously* unless base rates are equal or the classifier is perfect. There is no single "fair" model; there is a choice among incompatible fairness criteria, and that choice is normative, not technical. The worked example audits a scorer for *disparate impact*—whether selection rates differ across groups—and shows that proxy features carry bias even when the protected attribute is excluded.  ```{r aiml-fairness, message=FALSE, warning=FALSE} set.seed(48) n <- 6000 group <- rbinom(n, 1, 0.5) # protected attribute A in {0,1} # A proxy correlated with the protected group (e.g., neighborhood), NOT the label cause proxy <- rnorm(n, mean = 0.8 * group) quality <- rnorm(n) # the legitimately relevant signal # True outcome depends ONLY on quality (group is irrelevant to merit)... y <- rbinom(n, 1, plogis(1.2 * quality)) df <- data.frame(y, quality, proxy, group) # Model that EXCLUDES the protected attribute but KEEPS the correlated proxy fit <- glm(y ~ quality + proxy, df, family = binomial()) df$score <- predict(fit, type = "response") tau <- quantile(df$score, 0.7) # select top 30% df$selected <- as.integer(df$score > tau) # Disparate impact: ratio of selection rates across groups (4/5ths rule -> >= 0.8) sel_rate <- tapply(df$selected, df$group, mean) di_ratio <- min(sel_rate) / max(sel_rate) cat("Selection rate by group:", round(sel_rate, 3), "\n") cat("Disparate-impact ratio: ", round(di_ratio, 3), if (di_ratio < 0.8) " (FAILS 4/5ths rule)" else " (passes)", "\n") ``` The disparate-impact ratio falls below the conventional four-fifths threshold even though the protected attribute never entered the model and plays no role in the true outcome—the proxy alone manufactures the gap. The lesson generalizes: fairness is a property of a model-in-context that must be measured on outcomes, not assumed from the feature list, and remediation (reweighting, constrained optimization, post-hoc threshold adjustment by group) is an explicit, auditable design choice with its own trade-offs against accuracy and against other fairness criteria. ## From Prediction to Decision: Causal Machine Learning The chapter's organizing distinction has a constructive resolution. The right way to use machine learning's flexibility for *inference* is not to read coefficients off a predictive model but to embed flexible learners inside an estimator whose identification comes from design. *Double/debiased machine learning* uses nonparametric learners to flexibly absorb high-dimensional confounders while preserving valid inference on a low-dimensional causal parameter, via orthogonalization and cross-fitting that immunize the target estimate against the nuisance learner's regularization bias. *Causal forests* and related heterogeneous- treatment-effect estimators adapt tree ensembles to estimate how a treatment effect $\tau(\mathbf{x}) = \mathbb{E}[Y(1) - Y(0)\mid \mathbf{X}=\mathbf{x}]$ varies across customers—the *uplift* that retention and targeting decisions actually require, as distinct from the *level* a churn model predicts. These methods, developed in the causal-inference chapters, are the principled bridge from machine learning's predictive power to the causal questions marketing decisions pose, and they are where the field's frontier is moving [@varian2016].  ## Key Takeaways - The **prediction–inference distinction** (@eq-aiml-dgp) is the organizing idea: predictive accuracy and causal interpretation are different goals validated by different criteria, and a model's internals are not causal estimates no matter how well it predicts. - **Supervised learning** minimizes regularized empirical risk (@eq-aiml-erm); for tabular marketing data, gradient-boosted trees are the empirical default, and honest evaluation requires *both* discrimination and calibration, on a split that respects time. - **Unsupervised learning** discovers structure without labels; clustering always returns clusters, so the burden of proof is on the analyst to show segments are stable and managerially meaningful, not merely that the algorithm converged. - **Recommender systems** turn sparse user–item data into rankings via matrix factorization (@eq-aiml-mf), but cold-start, feedback loops, and the prediction-versus-incremental-lift gap make naïve click-maximization a trap. - **Deep learning and LLMs** excel on unstructured data (images, text, sequences) and are powerful measurement and generation instruments, but their opacity makes them poor instruments of inference and demands explicit validity, reproducibility, and factuality controls. - The three deployment pitfalls—**leakage**, **drift**, and **unfairness**—are assumption violations, not bugs: validate inside the fold and forward in time, monitor and retrain against a moving world, and measure fairness on outcomes because proxies encode protected attributes even when those attributes are excluded. - The constructive resolution is **causal machine learning**, which embeds flexible learners inside design-based estimators to recover the *uplift* that marketing decisions require.