# DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search

arXiv: https://arxiv.org/abs/2608.25635 · HTML: https://mlsanity.com/paper/2608.25635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Reinforcement Learning to Rank in E-Commerce Search Engine: Formalization, Analysis, and Application](https://mlsanity.com/paper/1803.00710/) (2018)
- [Cascade Ranking for Operational E-commerce Search](https://mlsanity.com/paper/1706.02093/) (2017)
- [On Application of Learning to Rank for E-Commerce Search](https://mlsanity.com/paper/1903.04263/) (2019)
- [PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement](https://mlsanity.com/paper/2212.02779/) (2022)
- [Value-aware Recommendation based on Reinforced Profit Maximization in E-commerce Systems](https://mlsanity.com/paper/1902.00851/) (2019)
- [AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems](https://mlsanity.com/paper/2310.03984/) (2023)
- [Pantheon: Personalized Multi-objective Ensemble Sort via Iterative Pareto Policy Optimization](https://mlsanity.com/paper/2505.13894/) (2025)
- [Future Impact Decomposition in Request-level Recommendations](https://mlsanity.com/paper/2401.16108/) (2024)
- [UMRE: A Unified Monotonic Transformation for Ranking Ensemble in Recommender Systems](https://mlsanity.com/paper/2508.07613/) (2025)
- [Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems](https://mlsanity.com/paper/2510.07621/) (2025)
- [GRADE: Personalized Multi-Task Fusion via Group-relative Reinforcement Learning with Adaptive Dirichlet Exploration](https://mlsanity.com/paper/2510.07919/) (2025)
- [Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning](https://mlsanity.com/paper/2607.14192/) (2026)

## Abstract (arXiv)

Industrial e-commerce search systems ultimately aim to optimize the user-level long-term objective, such as n-day cumulative purchases or gross merchandise value (GMV) per user. However, such objectives are defined at the user level, whereas search ranking is based on item-level scores within each request. Existing methods typically bridge this granularity gap through manually designed multi-objective fusion, where predictions of multiple item-level objectives, such as clicks, carts, purchases, and transaction value, are combined into a ranking score that serves as a proxy for the ultimate objective. Such hand-crafted fusion schemes rely on a small set of manually tuned weights, limiting fine-grained personalization and leading to suboptimal alignment with the ultimate objective. In this paper, we propose DCEO (Direct Causal Effect Optimization), a data-driven framework for learning item-level proxy scores that are better aligned with the ultimate objective. We first aggregate the item-level proxy scores into a user-level proxy metric and quantify its alignment with the ultimate objective using a relative causal effect. We then develop an actor-critic framework, where the critic estimates the ultimate objective for a given user-level proxy metric, and the actor dynamically generates context-dependent fusion weights over multiple objectives to construct the item-level proxy scores and is trained to directly optimize the relative causal effect. Extensive offline experiments and analyses demonstrate the effectiveness and interpretability of DCEO. In addition, DCEO has been deployed in a large-scale industrial e-commerce search system, outperforming the conventional GMV proxy by 0.36% in GMV in a 41-day online A/B test.