Personalized Product Search Ranking: A Multi-Task Learning Approach with Tabular and Non-Tabular Data

2025-08-13

AI Summary

This paper addresses two key challenges in personalized product search: the difficulty of fusing heterogeneous data (tabular and non-tabular) and the heavy reliance on manual relevance annotation. To this end, we propose a multi-task learning ranking framework. Methodologically: (i) We leverage TinyBERT to generate semantic embeddings and integrate them with user click behavior and positional signals to construct a scalable, annotation-free relevance labeling mechanism—combining click-through rate, click position bias, and semantic similarity; (ii) We design an enhanced embedding interaction module that jointly integrates TinyBERT, FT-Transformer, and multi-task learning to unify the modeling of heterogeneous features. Experiments demonstrate significant improvements in ranking metrics—including NDCG—across multiple benchmarks. Ablation studies confirm the critical contribution of each component to overall performance.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Applications of semantic technologies for improving search, browsing, recommendation, personalization

Abstract

In this paper, we present a novel model architecture for optimizing personalized product search ranking using a multi-task learning (MTL) framework. Our approach uniquely integrates tabular and non-tabular data, leveraging a pre-trained TinyBERT model for semantic embeddings and a novel sampling technique to capture diverse customer behaviors. We evaluate our model against several baselines, including XGBoost, TabNet, FT-Transformer, DCN-V2, and MMoE, focusing on their ability to handle mixed data types and optimize personalized ranking. Additionally, we propose a scalable relevance labeling mechanism based on click-through rates, click positions, and semantic similarity, offering an alternative to traditional human-annotated labels. Experimental results show that combining non-tabular data with advanced embedding techniques in multi-task learning paradigm significantly enhances model performance. Ablation studies further underscore the benefits of incorporating relevance labels, fine-tuning TinyBERT layers, and TinyBERT query-product embedding interactions. These results demonstrate the effectiveness of our approach in achieving improved personalized product search ranking.

Problem

• Optimizing personalized product search ranking using multi-task learning
• Integrating tabular and non-tabular data for improved search results
• Developing scalable relevance labeling without human annotation

Innovation

• Multi-task learning with tabular and non-tabular data
• TinyBERT embeddings with novel sampling technique
• Scalable relevance labeling using click-through rates