Logic based model improves human choice predictions with clear rules
Logic-Logit: A Logic-Based Approach to Choice Modeling
Machine Learning
Summary
Understanding how people make choices can be tricky, especially when computer models are complex and hard to explain. The authors created a new kind of model called Logic-Logit that uses simple, understandable rules to mimic how people decide among options. These rules mimic the way people often think in quick, yes-or-no steps to narrow down choices before picking one. Their method makes the models easier to interpret and also more accurate when tested on both made-up and real-world data. This helps in areas where it is important to know not just what decision is made, but also why.
What this means in practice
- •For market analysts: Create clearer demand forecasts by modeling customer choices with understandable rules that capture real decision processes.
- •For healthcare decision teams: Improve patient choice models to explain and predict treatment selections using transparent logic-based rules from clinical data.
Authors
Shuhan Zhang, Wendi Ren, Shuang Li
Abstract
In this study, we propose a novel rule-based interpretable choice model, Logic-Logit, designed to effectively learn and explain human choices. Choice models have been widely applied across various domains---such as commercial demand forecasting, recommendation systems, and consumer behavior analysis---typically categorized as parametric, nonparametric, or deep network-based. While recent innovations have favored neural network approaches for their computational power, these flexible models often involve large parameter sets and lack interpretability, limiting their effectiveness in contexts where transparency is essential. Previous empirical evidence shows that individuals usually use heuristic decision rules to form their consideration sets, from which they then choose. These rules are often represented as disjunctions of conjunctions (i.e., OR-of-ANDs). These rules-driven, consider-then-choose decision processes enable people to quickly screen numerous alternatives while reducing cognitive and search costs. Motivated by this insight, our approach leverages logic rules to elucidate human choices, providing a fresh perspective on preference modeling. We introduce a unique combination of column generation techniques and the Frank-Wolfe algorithm to facilitate efficient rule extraction for preference modeling---a process recognized as NP-hard. Our empirical evaluation, conducted on both synthetic datasets and real-world data from commercial and healthcare domains, demonstrates that Logic-Logit significantly outperforms baseline models in terms of interpretability and accuracy.