Eva Ascarza

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 BEAT (Bias-Eliminating Adapted Trees) to address these issues. This approach allows decision makers to target individuals based on differences in their predicted behavior—hence capturing value from personalization—while ensuring a balanced allocation of resources across individuals, guaranteeing both group and individual fairness. Essentially, the method only extracts heterogeneity in the data that is unrelated to protected attributes. To do so, we build on the General Random Forest (GRF) framework (S. Athey et al., Ann. Stat. 47, 1148–1178 (2019)) and develop a targeting allocation that is “balanced” with respect to protected attributes.  We validate BEAT using simulations and an online experiment with N=3,146 participants. This approach 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.

The success of customer relationship management (CRM) programs ultimately depends on the firm’s ability to identify and leverage differences across customers—a difficult task when firms attempt to manage new customers, for whom only the first purchase has been observed. The lack of repeated observations for these customers poses a structural challenge for firms to infer unobserved differences across them. This is what the authors call the “cold start” problem of customer relationship management, whereby companies have difficulties leveraging existing data when they attempt to make inferences about customers at the beginning of their relationship. The authors propose a solution to the cold start problem by developing a probabilistic machine learning modeling framework that leverages the information collected at the moment of acquisition. The main aspect of the model is that it flexibly captures latent dimensions that govern the behaviors observed at acquisition as well as future propensities to buy and to respond to marketing actions using deep exponential families. The model can be integrated with a variety of demand specifications and is flexible enough to capture a wide range of heterogeneity structures. The authors validate their approach in a retail context and empirically demonstrate the model’s ability to identify high-value customers as well as those most sensitive to marketing actions right after their first purchase.

Fewer than 40% of companies that invest in AI see gains from it, usually because of one or more of these errors: (1) They don’t ask the right question, and end up directing AI to solve the wrong problem. (2) They don’t recognize the differences between the value of being right and the costs of being wrong, and assume all prediction mistakes are equivalent. (3) They don’t leverage AI’s ability to make far more frequent and granular decisions, and keep following their old practices. If marketers and data science teams communicate better and take steps to avoid these pitfalls, they’ll get much higher returns on their AI efforts.