Incremental Profit per Conversion: a Response Transformation for Uplift Modeling in E-Commerce Promotions
This work addresses a specific problem for e-commerce platforms in optimizing promotional campaigns, but it is incremental as it builds on existing uplift modeling approaches.
The paper tackles the challenge of estimating profit for e-commerce promotions with response-dependent costs, where existing uplift models require multiple models or struggle with zero-inflated data, by introducing Incremental Profit per Conversion (IPC) as a novel measure that uses only converted data and a single model, validated through synthetic simulation results.
Promotions play a crucial role in e-commerce platforms, and various cost structures are employed to drive user engagement. This paper focuses on promotions with response-dependent costs, where expenses are incurred only when a purchase is made. Such promotions include discounts and coupons. While existing uplift model approaches aim to address this challenge, these approaches often necessitate training multiple models, like meta-learners, or encounter complications when estimating profit due to zero-inflated values stemming from non-converted individuals with zero cost and profit. To address these challenges, we introduce Incremental Profit per Conversion (IPC), a novel uplift measure of promotional campaigns' efficiency in unit economics. Through a proposed response transformation, we demonstrate that IPC requires only converted data, its propensity, and a single model to be estimated. As a result, IPC resolves the issues mentioned above while mitigating the noise typically associated with the class imbalance in conversion datasets and biases arising from the many-to-one mapping between search and purchase data. Lastly, we validate the efficacy of our approach by presenting results obtained from a synthetic simulation of a discount coupon campaign.