🤖 AI Summary
This paper addresses the limitation of standard stochastic preference (SP) models in capturing context-dependent irrational choice phenomena—such as the compromise and attraction effects. To overcome this, we propose the Generalized Stochastic Preference (GSP) model, which formally incorporates controllable irrationality types into a ranking-based choice framework while subsuming classical SP and Random Utility Models (RUM) as special cases. We further introduce a computationally tractable subclass, the Generalized Multinomial Logit (GMNL), and develop the first Expectation-Maximization (EM) algorithm tailored to irrational choice behavior. Estimability is ensured via an iterative integer linear programming (ILP) solution strategy. Empirical evaluation on real-world datasets demonstrates that both GMNL and GSP achieve statistically significant improvements in out-of-sample prediction accuracy over rational baseline models.
📝 Abstract
We propose a new discrete choice model, called the generalized stochastic preference (GSP) model, that incorporates non-rationality into the stochastic preference (SP) choice model, also known as the rank- based choice model. Our model can explain several choice phenomena that cannot be represented by any SP model such as the compromise and attraction effects, but still subsumes the SP model class. The GSP model is defined as a distribution over consumer types, where each type extends the choice behavior of rational types in the SP model. We build on existing methods for estimating the SP model and propose an iterative estimation algorithm for the GSP model that finds new types by solving a integer linear program in each iteration. We further show that our proposed notion of non-rationality can be incorporated into other choice models, like the random utility maximization (RUM) model class as well as any of its subclasses. As a concrete example, we introduce the non-rational extension of the classical MNL model, which we term the generalized MNL (GMNL) model and present an efficient expectation-maximization (EM) algorithm for estimating the GMNL model. Numerical evaluation on real choice data shows that the GMNL and GSP models can outperform their rational counterparts in out-of-sample prediction accuracy.
