Model Distillation for Revenue Optimization: Interpretable Personalized Pricing

Abstract

Data-driven pricing strategies are becoming increasingly common, where customers are offered a personalized price based on features that are predictive of their valuation of a product. It is desirable for this pricing policy to be simple and interpretable, so it can be verified, checked for fairness, and easily implemented. However, efforts to incorporate machine learning into a pricing framework often lead to complex pricing policies which are not interpretable, resulting in slow adoption in practice. We present a customized, prescriptive tree-based algorithm that distills knowledge from a complex black-box machine learning algorithm, segments customers with similar valuations and prescribes prices in such a way that maximizes revenue while maintaining interpretability. We quantify the regret of a resulting policy and demonstrate its efficacy in applications with both synthetic and real-world datasets.

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• Recursive Partitioning for Heterogeneous Causal Effects
• Predictive learning via rule ensembles
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• How to Explain Individual Classification Decisions
• Supersparse Linear Integer Models for Optimized Medical Scoring Systems
• Distilling a Neural Network Into a Soft Decision Tree
• Interpreting Blackbox Models via Model Extraction
• Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
• Decision Trees for Decision-Making under the Predict-then-Optimize Framework
• The Price of Interpretability
• Optimization over Continuous and Multi-dimensional Decisions with Observational Data
• The Power and Limits of Predictive Approaches to Observational-Data-Driven Optimization