Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data

TL;DR

This paper introduces Bi-DFCL, a novel bi-level learning framework that integrates observational and experimental data to improve large-scale marketing decision-making by addressing prediction-decision misalignment and bias-variance tradeoffs.

Contribution

It develops an unbiased estimator for decision quality and a bi-level optimization framework that jointly leverages observational and experimental data for better marketing strategies.

Findings

Significant improvements over state-of-the-art methods.

Effective correction of observational data biases.

Successful deployment at Meituan, a large online platform.

Abstract

Online Internet platforms require sophisticated marketing strategies to optimize user retention and platform revenue -- a classical resource allocation problem. Traditional solutions adopt a two-stage pipeline: machine learning (ML) for predicting individual treatment effects to marketing actions, followed by operations research (OR) optimization for decision-making. This paradigm presents two fundamental technical challenges. First, the prediction-decision misalignment: Conventional ML methods focus solely on prediction accuracy without considering downstream optimization objectives, leading to improved predictive metrics that fail to translate to better decisions. Second, the bias-variance dilemma: Observational data suffers from multiple biases (e.g., selection bias, position bias), while experimental data (e.g., randomized controlled trials), though unbiased, is typically scarce and costly -- resulting in high-variance estimates. We propose Bi-level Decision-Focused Causal Learning (Bi-DFCL) that systematically addresses these challenges. First, we develop an unbiased estimator of OR decision quality using experimental data, which guides ML model training through surrogate loss functions that bridge discrete optimization gradients. Second, we establish a bi-level optimization framework that jointly leverages observational and experimental data, solved via implicit differentiation. This novel formulation enables our unbiased OR estimator to correct learning directions from biased observational data, achieving optimal bias-variance tradeoff. Extensive evaluations on public benchmarks, industrial marketing datasets, and large-scale online A/B tests demonstrate the effectiveness of Bi-DFCL, showing statistically significant improvements over state-of-the-art. Currently, Bi-DFCL has been deployed at Meituan, one of the largest online food delivery platforms in the world.