Graph-Based Methods for Discrete Choice

TL;DR

This paper explores how graph learning techniques can enhance discrete choice models by incorporating social network data, improving prediction accuracy and providing new insights into social influence on individual choices.

Contribution

The paper introduces three novel methods for integrating graph learning into discrete choice modeling, addressing limitations of traditional approaches and demonstrating their effectiveness on real-world datasets.

Findings

Social network structure improves choice prediction accuracy.

App installations are socially influenced, but app usage is habit-driven.

Graph-based methods outperform traditional models on synthetic data.

Abstract

Choices made by individuals have widespread impacts--for instance, people choose between political candidates to vote for, between social media posts to share, and between brands to purchase--moreover, data on these choices are increasingly abundant. Discrete choice models are a key tool for learning individual preferences from such data. Additionally, social factors like conformity and contagion influence individual choice. Traditional methods for incorporating these factors into choice models do not account for the entire social network and require hand-crafted features. To overcome these limitations, we use graph learning to study choice in networked contexts. We identify three ways in which graph learning techniques can be used for discrete choice: learning chooser representations, regularizing choice model parameters, and directly constructing predictions from a network. We design methods in each category and test them on real-world choice datasets, including county-level 2016 US election results and Android app installation and usage data. We show that incorporating social network structure can improve the predictions of the standard econometric choice model, the multinomial logit. We provide evidence that app installations are influenced by social context, but we find no such effect on app usage among the same participants, which instead is habit-driven. In the election data, we highlight the additional insights a discrete choice framework provides over classification or regression, the typical approaches. On synthetic data, we demonstrate the sample complexity benefit of using social information in choice models.