Counterfactual Multi-task Learning for Delayed Conversion Modeling in E-commerce Sales Pre-Promotion

TL;DR

This paper introduces a novel counterfactual multi-task learning model for improved delayed conversion prediction in e-commerce pre-promotion periods, addressing distribution shifts and data sparsity.

Contribution

It proposes a multi-task architecture with a personalized gating module and causal modeling to better predict delayed conversions using pre-promotion data.

Findings

CM-DCM outperforms baseline models in pre-promotion CVR prediction.

Online A/B tests show significant revenue and GMV improvements.

The approach effectively models transition from add-to-cart to delayed conversion.

Abstract

Sales promotions, as short-term incentives to stimulate product purchases, play a pivotal role in modern e-commerce marketing strategies. During promotional events, user behavior patterns exhibit distinct characteristics compared to regular periods. In the pre-promotion phase, users typically engage in product search and browsing without immediate purchases, adding items to carts in anticipation of promotional discounts. This behavior leads to delayed conversions, resulting in significantly lower conversion rates (CVR) before the promotion day. Although existing research has made progress in CVR prediction for promotion days using historical data, it largely overlooks the critical pre-promotion period. And delayed feedback modeling has been extensively studied, current approaches fail to account for the unique distribution shifts in conversion behavior before promotional events, where delayed conversions predominantly occur on the promotion day rather than over continuous time windows. To address these limitations, we propose the Counterfactual Multi-task Delayed Conversion Model (CM-DCM), which leverages historical pre-promotion data to enhance CVR prediction for both delayed and direct conversions. Our model incorporates three key innovations: (i) A multi-task architecture that jointly models direct and delayed conversions using historical pre-promotion data; (ii) A personalized user behavior gating module to mitigate data sparsity issues during brief pre-promotion periods; (iii) A counterfactual causal approach to model the transition probability from add-to-cart (ATC) to delayed conversion. Extensive experiments demonstrate that CM-DCM outperforms baselines in pre-promotion scenarios. Online A/B tests during major promotional events showed significant improvements in advertising revenue, delayed conversion GMV, and overall GMV, validating the effectiveness of our approach.