The Value of "Who" and "What" When Predicting Choice Under Risk
We investigate the predictive value-add of auxiliary covariates in a choice under risk setting. We start with a data set representative of the Dutch population, and simulate different levels of data availability by selectively removing demographic covariates, subject identifiers, or both. We use expected utility theory (EUT) as a benchmark model and evaluate its out-of-sample prediction performance against machine learning (ML) models. We show that identifying information is more valuable than demographic data, although both show significant improvement over choice data alone. EUT is competitive with ML models, in particular outperforming them on subjects whose choices are consistent with (monotonic) utility maximization. There is little heterogeneity across demographic groups. Overall, our results demonstrate the predictive power of simple identifying information while emphasizing the continued relevance of EUT amid advances in ML and AI.
Predicting and Understanding Individual-Level Choice Under Risk (with Shachar Kariv and Erkut Y. Ozbay)
(previously titled "What Can the Demand Analyst Learn from Machine Learning?")
Non-isolation and Social Preference (with Paul Cheung)
Revise and Resubmit at Games and Economic Behavior
Predicting and Understanding Individual-Level Choice Under Uncertainty (with Shachar Kariv and Erkut Y. Ozbay)
(previously titled "The Predicitivity of Theories of Choice Under Uncertainty")
Consistency and Heterogeneity in Consideration and Choice (with Emel Filiz-Ozbay and Erkut Y. Ozbay)
Model Complexity and Restrictiveness (with Sara Neff)
Scaling Up: Individual-Level Transfer Performance of Models (with Shachar Kariv and Erkut Y. Ozbay)
Multi-symbol Forbidden Configurations (with Baian Liu and Attila Sali)
Discrete Applied Mathematics, April 2020, Volume 276, pp 24-36.