Multi-Treatment Multi-Task Uplift Modeling for Enhancing User Growth

TL;DR

This paper introduces a Multi-Treatment Multi-Task uplift model that estimates treatment effects across multiple treatments and tasks, improving user response prediction and business outcomes in online platforms.

Contribution

The paper proposes a novel MTMT uplift network that models multi-treatment and multi-task effects, explicitly capturing base and incremental effects with a new encoding and interaction mechanism.

Findings

MTMT outperforms existing models on public and proprietary datasets.

The model effectively captures base and incremental treatment effects.

Deployment in a gaming platform improved user engagement.

Abstract

As a key component in boosting online user growth, uplift modeling aims to measure individual user responses (e.g., whether to play the game) to various treatments, such as gaming bonuses, thereby enhancing business outcomes. However, previous research typically considers a single-task, single-treatment setting, where only one treatment exists and the overall treatment effect is measured by a single type of user response. In this paper, we propose a Multi-Treatment Multi-Task (MTMT) uplift network to estimate treatment effects in a multi-task scenario. We identify the multi-treatment problem as a causal inference problem with a tiered response, comprising a base effect (from offering a treatment) and an incremental effect (from offering a specific type of treatment), where the base effect can be numerically much larger than the incremental effect. Specifically, MTMT separately encodes user features and treatments. The user feature encoder uses a multi-gate mixture of experts (MMOE) network to encode relevant user features, explicitly learning inter-task relations. The resultant embeddings are used to measure natural responses per task. Furthermore, we introduce a treatment-user feature interaction module to model correlations between each treatment and user feature. Consequently, we separately measure the base and incremental treatment effect for each task based on the produced treatment-aware representations. Experimental results based on an offline public dataset and an online proprietary dataset demonstrate the effectiveness of MTMT in single/multi-treatment and single/multi-task settings. Additionally, MTMT has been deployed in our gaming platform to improve user experience.