Optimal Comprehensible Targeting

2025-12-02

AI Summary

This paper addresses the challenge of designing **interpretable and profit-optimal personalized marketing strategies** under data privacy regulations—such as the GDPR’s “right to explanation.” To overcome the unreliability of post-hoc explanations for black-box models, we propose **natively interpretable targeting policies**, represented as natural-language sentences, and formally establish their superiority over post-hoc approaches. Methodologically, we integrate machine learning, causal inference, and combinatorial optimization into an end-to-end framework for learning interpretable policies. Evaluated on real-world promotional experiment data from a durable-goods retailer, our approach achieves near-optimal profit while ensuring user transparency and regulatory compliance. We quantify the “explanation cost” as a 7.5% profit reduction relative to black-box baselines (≈$23 per customer), substantially lower than competing interpretable methods. Our core contribution is the first formulation of interpretability as an *intrinsic* property of policy learning—backed by theoretical guarantees and empirical benchmarks.

Technology Category

• Machine Learning: Privacy
• Search and Optimization: Learning to Search
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Developments in machine learning and big data allow firms to fully personalize and target their marketing mix. However, data and privacy regulations, such as those in the European Union (GDPR), incorporate a"right to explanation,"which is fulfilled when targeting policies are comprehensible to customers. This paper provides a framework for firms to navigate right-to-explanation legislation. First, I construct a class of comprehensible targeting policies that is represented by a sentence. Second, I show how to optimize over this class of policies to find the profit-maximizing comprehensible policy. I further demonstrate that it is optimal to estimate the comprehensible policy directly from the data, rather than projecting down the black box policy into a comprehensible policy. Third, I find the optimal black box targeting policy and compare it to the optimal comprehensible policy. I then empirically apply my framework using data from a price promotion field experiment from a durable goods retailer. I quantify the cost of explanation, which I define as the difference in expected profits between the optimal black box and comprehensible targeting policies. Compared to the black box benchmark, the comprehensible targeting policy reduces profits by 7.5% or 23 cents per customer.

Problem

• Develops a framework for firms to comply with explanation rights in data regulations.
• Optimizes comprehensible targeting policies to maximize profits under legal constraints.
• Quantifies the profit trade-off between black box and comprehensible targeting policies.

Innovation

• Constructing comprehensible targeting policies represented by sentences
• Optimizing directly from data for profit-maximizing comprehensible policies
• Quantifying explanation cost as profit difference between black box and comprehensible policies