8.3 Modeling Techniques for Interpretability Requirements

Key Takeaways

  • Intrinsically interpretable models such as linear and logistic regression expose weights directly, while tree ensembles and DNNs need post-hoc explanation methods.
  • Agent Platform feature attribution methods are sampled Shapley for non-differentiable models, integrated gradients for differentiable models, and XRAI for image regions.
  • BigQuery ML explains boosted tree and random forest models with Tree SHAP or approximate feature contribution, and DNNs with integrated gradients.
  • Feature attributions are measured relative to a baseline, so the choice of baseline changes how attributions should be read.
  • Vertex Explainable AI was deprecated on March 16, 2026, and Google points to open-source SHAP and LIME as alternatives.
Last updated: September 2026

The exam guide lists modeling techniques given interpretability requirements as part of building models. Interpretability can be a legal requirement (explaining a credit denial), a trust requirement (clinicians must see why), or a debugging aid. This section is about choosing the technique. Implementing and monitoring explanations in production is covered in Section 18.4.

Two Paths to Interpretability

PathExamplesProsCons
Intrinsically interpretable ("glass-box") modelsLinear or logistic regression, shallow decision trees, rule lists, ARIMA_PLUS decompositionExplanations are exact and stable. Easy to auditCan lose accuracy on complex non-linear data
Post-hoc explanations of complex modelsShapley-based feature attributions for tree ensembles and DNNs, saliency for images, example-based explanationsKeep high accuracyApproximations that depend on method and baseline. Harder to validate

Decision rule: if a regulator or policy requires a precise, stable reason for each decision and the accuracy gap is small, prefer a glass-box model. If complex models are much more accurate and approximate explanations are acceptable, use a complex model plus post-hoc attributions, and validate that the explanations make sense.

Local vs. Global Explanations

  • Local explanations show how each feature contributed to one prediction ("income and debt ratio lowered this applicant's score"). They're needed for individual adverse-action reasons.
  • Global explanations show a feature's overall influence across the dataset. They're used for model validation and governance reviews.

Explanation Methods on Google Cloud

Agent Platform feature attributions

All three methods are based on Shapley values, which credit each feature for its share of the outcome.

MethodBest forNotes
Sampled ShapleyNon-differentiable models such as tree ensembles, and meta-ensembles of trees and neural networks (AutoML tabular)Sampling approximation of exact Shapley values. Works with any custom-trained model in any container
Integrated gradientsDifferentiable models (neural networks), especially with large feature spaces. Low-contrast images such as X-raysIntegrates gradients along a path from a baseline to the input
XRAIImage classification with natural imagesBuilds on integrated gradients, then oversegments the image and ranks regions by attribution

Example-based explanations return the most similar training examples, found by nearest-neighbor search on embeddings. They help debug mislabeled or underrepresented data and flag inputs far from anything seen in training. They support TensorFlow models that produce embeddings, not tree models.

BigQuery ML explanations

ModelMethodFunctions
Linear and logistic regressionShapley values (weight × standardized feature), plus standard errors and p-valuesML.EXPLAIN_PREDICT, ML.GLOBAL_EXPLAIN, ML.ADVANCED_WEIGHTS
Boosted trees, random forestTree SHAP (exact for trees), approximate feature contribution, Gini-based importanceML.EXPLAIN_PREDICT, ML.GLOBAL_EXPLAIN, ML.FEATURE_IMPORTANCE
DNN, Wide & DeepIntegrated gradientsML.EXPLAIN_PREDICT, ML.GLOBAL_EXPLAIN
AutoML TablesSampled ShapleyML.GLOBAL_EXPLAIN
ARIMA_PLUSTime series decompositionML.EXPLAIN_FORECAST

Baselines matter

Attributions measure contribution relative to a baseline, such as the median input for tabular data or an all-black image. Change the baseline and the attributions change. Pick a baseline that fits the question, like "compared with a typical applicant."

Lifecycle Note: Explainable AI Deprecation

Vertex Explainable AI was deprecated on March 16, 2026 and is scheduled to shut down on March 16, 2027. No new features are being added, and Google recommends open-source libraries such as SHAP and LIME as alternatives. For long-lived designs:

  • Prefer glass-box models where they meet accuracy needs.
  • Use BigQuery ML explanation functions for BigQuery ML models.
  • Package SHAP (Shapley-based, including TreeSHAP for trees) or LIME (local surrogate models) in training, batch, or serving code for custom models.

Techniques That Improve Interpretability Without Losing Much Accuracy

  • Feature selection: fewer, meaningful features make any explanation clearer (Chapter 2).
  • Domain-meaningful feature engineering: "debt-to-income ratio" explains better than 40 raw balance columns.
  • Constraints: limit tree depth, or use monotonic relationships where the domain requires them ("higher income never lowers the score").
  • Two-stage designs: a glass-box model for the regulated decision, and a complex model only for non-regulated ranking.
  • Model documentation: record intended use, training data, evaluation slices, and limitations.

Matching Requirements to Techniques

RequirementSuitable approach
Exact per-decision reason codes for a regulatorLinear or logistic regression, or shallow trees
Global validation that the model uses sensible driversGlobal attributions (ML.GLOBAL_EXPLAIN, SHAP summaries) on any model
Explain which image region drove a diagnosisIntegrated gradients or XRAI saliency on the vision model
Explain an unexpected prediction by showing similar past casesExample-based explanations or nearest-neighbor retrieval on embeddings
Explain a forecast to plannersARIMA_PLUS decomposition with ML.EXPLAIN_FORECAST

Interpretability for Generative AI

LLMs don't provide faithful feature attributions, and a model's self-written "reasoning" isn't a guaranteed account of how it produced an answer. For gen AI, interpretability usually means:

  • Grounding with citations, so users can check sources (Chapter 4).
  • Structured outputs that separate the decision from the supporting evidence.
  • Evaluation of grounding and instruction following (Chapter 7).
  • Keeping regulated decisions in interpretable models, with the LLM summarizing or drafting only.

Worked Scenario

A lender must give each rejected applicant the top reasons for denial, and model-risk reviewers must approve the model yearly.

  • A logistic regression with well-engineered features reaches AUC 0.81. A boosted tree reaches 0.83.
  • Adverse-action reasons must be exact and consistent, and the 0.02 AUC gain doesn't offset the review burden. The team picks logistic regression, with reason codes from each feature's contribution (weight × value).
  • A separate boosted tree with Tree SHAP explanations ranks marketing offers, where approximate explanations are acceptable.
Test Your Knowledge

A bank's model-risk policy requires exact, stable reasons for every credit denial. A logistic regression model reaches AUC 0.80, and a deep neural network reaches AUC 0.81. Which choice best satisfies the requirement?

A
B
C
D
Test Your Knowledge

A team needs local feature attributions for a custom XGBoost model served in a custom container on Agent Platform. Which built-in attribution method matches this non-differentiable model?

A
B
C
D
Test Your Knowledge

Which statement about feature attributions is correct?

A
B
C
D