DeepHalo: A Neural Choice Model with Controllable Context Effects

TL;DR

DeepHalo is a neural model that captures and interprets complex context effects in human decision-making, improving prediction accuracy and transparency in preference modeling.

Contribution

It introduces a flexible neural framework that explicitly controls interaction order and enhances interpretability of context effects in choice models.

Findings

Strong predictive performance on synthetic and real-world data

Provides transparent insights into decision drivers

Enables systematic analysis of interaction effects by order

Abstract

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself -- a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.