BEAT Unintended Bias in Personalized Policies
37 Pages Posted: 21 Aug 2021 Last revised: 24 Aug 2021
Date Written: August 19, 2021
An inherent risk of algorithmic personalization is disproportionate targeting of individuals from certain groups (or demographic characteristics such as gender or race), even when the decision maker does not intend to discriminate based on those “protected” attributes. This unintended discrimination is often caused by underlying correlations in the data between protected attributes and other observed characteristics used by the algorithm (or machine learning (ML) tool) to create predictions and target individuals optimally. Because these correlations are hidden in high dimensional data, removing protected attributes from the database does not solve the discrimination problem; instead, removing those attributes often exacerbates the problem by making it undetectable and, in some cases, even increases the bias generated by the algorithm.
We propose the BEAT (Bias-Eliminating Adapted Trees) framework to address these issues. This framework allows decision makers to target individuals based on differences in their predicted behavior—hence capturing value from personalization—while ensuring that the allocation of resources is balanced with respect to the population. Essentially, the method only extracts heterogeneity in the data that is unrelated to those protected attributes. To do so, we build on the General Random Forest (GRF) framework (Wager and Athey 2018; Athey et al. 2019) and develop a targeting allocation that is “balanced” with respect to protected attributes. We validate the BEAT framework using simulations and an online experiment with N=3,146 participants. This framework can be applied to any type of allocation decision that is based on prediction algorithms, such as medical treatments, hiring decisions, product recommendations, or dynamic pricing.
Keywords: Algorithmic bias, personalization, targeting, generalized random forests (GRF), fairness, discrimination
JEL Classification: C53, C54, C55, M31
Suggested Citation: Suggested Citation