Feature interaction
A feature interaction is a joint effect in which a model’s output or behavior depends on a combination of input features rather than on each feature independently.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
A feature interaction is a predictive effect produced jointly by two or more input features rather than by each feature independently.
- How it is used
- Captures joint feature effects when tabular predictions cannot be explained adequately by independent linear contributions.
- How deep it goes
- Defines multiplicative interactions, compares manual and polynomial generation, and discusses tree handling and regularization trade-offs without mathematical derivation.
- Examples
- Uses Airbnb bedrooms and minimum nights, advertising websites and formats, polynomial expansion, XGBFIR rankings, and conjoint partial dependence plots.
- What you can do after
- Apply it via scikit-learn PolynomialFeatures or manually engineered products, while evaluating regularization and model-specific trade-offs.
Ensemble Methods for Machine Learning
A pairwise feature interaction is a joint effect in which a model's output depends on a combination of two features rather than either feature independently.
- How it is used
- Explains joint feature effects within interpretable generalized additive ensemble models.
- How deep it goes
- Defines pairwise components, explains selective inclusion, and connects them to cyclic EBM training and local explanations.
- Examples
- Uses diabetes variables age, glucose, and BMI, plus bank-marketing pairs such as month × day_of_week.
- What you can do after
- Operate/configure an EBM to select, visualize, and interpret important pairwise contributions.
Read how Ensemble Methods for Machine Learning explains feature interaction →
Machine Learning System Design
A dependency or combined effect between features that influences their computation or a model's behavior.
- How it is used
- Guides feature design by combining signals and managing dependencies across training, inference, and real-time serving.
- How deep it goes
- Defines feature interactions, gives ratio and comparison examples, and notes linear separability; stops short of algorithmic construction details.
- Examples
- Uses average distance per ride, category and period sales comparisons, and a DeepETA feature-engineering pipeline.
- What you can do after
- Build it from scratch by combining existing signals, then evaluate computational dependencies, serving availability, and maintenance risks.
Read how Machine Learning System Design explains feature interaction →
Outlier Detection in Python
A feature interaction is a dependency in which the effect of one feature on a model output varies according to the value of another feature.
- How it is used
- Explains why global feature importances can miss dependencies affecting outlier scores.
- How deep it goes
- Defines the dependency and gives engineered-feature and proxy-model remedies, but does not develop interaction-detection procedures.
- Examples
- Uses abalone height and length, a height-to-length ratio, SHAP explanations, and PyOD importance rankings.
- What you can do after
- Evaluate outlier explanations by testing engineered features or comparing SHAP with approximate importance estimates.
Read how Outlier Detection in Python explains feature interaction →
Related concepts
- Explainable Boosted Machineused by · An Explainable Boosted Machine is an interpretable additive model trained with boosted shallow trees to learn individual feature effects and selected interactions.
- parallelismconfigures · Parallelism is the concurrent execution of multiple computational operations, often across multiple processing resources.
- tree-based methodaddressed by · A tree-based method is a predictive or decision-making technique that represents its rules or decision structure using one or more trees.
- linear regressionuses · Linear regression is a statistical modeling method that estimates a continuous response as a linear combination of predictor variables and fitted coefficients.
- linearly separableaddresses · Linearly separable describes labeled data whose classes can be divided by a single linear decision boundary in feature space.
- gradient boostinguses · Gradient boosting is an ensemble-learning technique that sequentially adds predictive models, typically weak learners, to reduce a loss by fitting its gradient.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.