Predicting Choice with Set-Dependent Aggregation
This addresses the need for improved choice prediction in online platforms, offering a method that overcomes limitations in capturing diverse behaviors and scalability, though it appears incremental by building on existing economic results.
The paper tackles the problem of predicting user choice from alternatives in online platforms by proposing a learning framework that captures set-related invariances, resulting in accurate, versatile, and scalable models with favorable sample complexity guarantees.
Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success. A renewed interest in learning choice models has led to significant progress in modeling power, but most current methods are either limited in the types of choice behavior they capture, cannot be applied to large-scale data, or both. Here we propose a learning framework for predicting choice that is accurate, versatile, theoretically grounded, and scales well. Our key modeling point is that to account for how humans choose, predictive models must capture certain set-related invariances. Building on recent results in economics, we derive a class of models that can express any behavioral choice pattern, enjoy favorable sample complexity guarantees, and can be efficiently trained end-to-end. Experiments on three large choice datasets demonstrate the utility of our approach.