NAM: A Normalization Attention Model for Personalized Product Search In Fliggy

TL;DR

This paper introduces NAM, a normalization attention model for personalized product search that improves accuracy by considering item popularity and user behavior heterogeneity, leading to better search relevance and conversion rates.

Contribution

NAM innovatively combines normalization and attention mechanisms with inverse item frequency to enhance personalization in product search, addressing limitations of previous co-occurrence based methods.

Findings

NAM outperforms state-of-the-art models in experiments.

Online A/B testing shows a 0.8% increase in conversion rate.

The model effectively balances popular and long-tail item recommendations.

Abstract

Personalized product search provides significant benefits to e-commerce platforms by extracting more accurate user preferences from historical behaviors. Previous studies largely focused on the user factors when personalizing the search query, while ignoring the item perspective, which leads to the following two challenges that we summarize in this paper: First, previous approaches relying only on co-occurrence frequency tend to overestimate the conversion rates for popular items and underestimate those for long-tail items, resulting in inaccurate item similarities; Second, user purchasing propensity is highly heterogeneous according to the popularity of the target item: it is less correlated with the user's historical behavior for a popular item and more correlated for a long-tail item. To address these challenges, in this paper we propose NAM, a Normalization Attention Model, which optimizes ''when to personalize'' by utilizing Inverse Item Frequency (IIF) and employing a gating mechanism, as well as optimizes ''how to personalize'' by normalizing the attention mechanism from a global perspective. Through comprehensive experiments, we demonstrate that our proposed NAM model significantly outperforms state-of-the-art baseline models. Furthermore, we conducted an online A/B test at Fliggy, and obtained a significant improvement of 0.8% over the latest production system in conversion rate.