Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising

2025-06-04

AI Summary

In e-commerce search advertising, long-tail queries suffer from low matching scores with bid keywords and product titles, resulting in insufficient recall of relevant ads and degraded user experience and platform revenue. To address this, we propose a multi-objective aligned bid keyword generation model. For the first time, we introduce a discriminator-driven joint optimization framework into bidword generation, simultaneously modeling query relevance, semantic authenticity, and commercial value (GMV-oriented), thereby overcoming limitations of conventional single-objective or pipeline-based approaches. The model integrates an adversarial discriminator, a conditional generator, and a preference alignment module, trained via offline multi-task learning and refined with online reinforcement feedback. Experiments demonstrate significant improvements: +3.2% offline AUC, +2.8% online CTR, and +1.9% GMV. The model has been deployed at scale, delivering substantial business impact.

Technology Category

• Search and Optimization: Learning to Search
• Natural Language Processing: Generation
• Machine Learning: Learning Preferences or Rankings

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising

Abstract

Retrieval systems primarily address the challenge of matching user queries with the most relevant advertisements, playing a crucial role in e-commerce search advertising. The diversity of user needs and expressions often produces massive long-tail queries that cannot be matched with merchant bidwords or product titles, which results in some advertisements not being recalled, ultimately harming user experience and search efficiency. Existing query rewriting research focuses on various methods such as query log mining, query-bidword vector matching, or generation-based rewriting. However, these methods often fail to simultaneously optimize the relevance and authenticity of the user's original query and rewrite and maximize the revenue potential of recalled ads. In this paper, we propose a Multi-objective aligned Bidword Generation Model (MoBGM), which is composed of a discriminator, generator, and preference alignment module, to address these challenges. To simultaneously improve the relevance and authenticity of the query and rewrite and maximize the platform revenue, we design a discriminator to optimize these key objectives. Using the feedback signal of the discriminator, we train a multi-objective aligned bidword generator that aims to maximize the combined effect of the three objectives. Extensive offline and online experiments show that our proposed algorithm significantly outperforms the state of the art. After deployment, the algorithm has created huge commercial value for the platform, further verifying its feasibility and robustness.

Problem

• Matching diverse user queries with relevant ads
• Improving relevance and authenticity of query rewrites
• Maximizing platform revenue from recalled advertisements

Innovation

• Multi-objective aligned bidword generation model
• Discriminator optimizes relevance and authenticity
• Generator maximizes platform revenue potential