Uplift modeling with continuous treatments: A predict-then-optimize approach

2024-12-12

arXiv.org

AI Summary

This paper addresses causal decision-making under continuous interventions (e.g., drug dosage, credit limits) by proposing the first uplift modeling framework tailored to continuous treatments. Methodologically, it adopts a two-stage paradigm: first estimating the conditional average dose response (CADR) via causal machine learning, then solving an integer linear programming (ILP) model with customizable objective functions and fairness constraints to optimize dose allocation under resource constraints. Key contributions include: (i) the first extension of uplift modeling to continuous interventions; (ii) support for instance-dependent cost-benefit modeling and multi-dimensional fairness constraints; and (iii) an open-source toolkit enabling CADR model comparison and business-objective alignment. The framework is empirically validated across real-world healthcare, credit scoring, and human resource management applications, demonstrating both strategic effectiveness and controllable trade-offs between fairness and utility.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

The goal of uplift modeling is to recommend actions that optimize specific outcomes by determining which entities should receive treatment. One common approach involves two steps: first, an inference step that estimates conditional average treatment effects (CATEs), and second, an optimization step that ranks entities based on their CATE values and assigns treatment to the top k within a given budget. While uplift modeling typically focuses on binary treatments, many real-world applications are characterized by continuous-valued treatments, i.e., a treatment dose. This paper presents a predict-then-optimize framework to allow for continuous treatments in uplift modeling. First, in the inference step, conditional average dose responses (CADRs) are estimated from data using causal machine learning techniques. Second, in the optimization step, we frame the assignment task of continuous treatments as a dose-allocation problem and solve it using integer linear programming (ILP). This approach allows decision-makers to efficiently and effectively allocate treatment doses while balancing resource availability, with the possibility of adding extra constraints like fairness considerations or adapting the objective function to take into account instance-dependent costs and benefits to maximize utility. The experiments compare several CADR estimators and illustrate the trade-offs between policy value and fairness, as well as the impact of an adapted objective function. This showcases the framework's advantages and flexibility across diverse applications in healthcare, lending, and human resource management. All code is available on github.com/SimonDeVos/UMCT.

Problem

• Extends uplift modeling to handle continuous treatment doses
• Estimates conditional average dose responses using causal ML
• Optimizes dose allocation via integer linear programming

Innovation

• Estimates CADRs using causal machine learning
• Solves dose-allocation via integer linear programming
• Balances policy value, fairness, and costs