Long or Short or Both? An Exploration on Lookback Time Windows of Behavioral Features in Product Search Ranking

TL;DR

This paper explores how different lookback time windows for behavioral features affect product search ranking in eCommerce, proposing a novel integration method that combines long and short-term signals for improved relevance.

Contribution

It introduces a new approach to integrating behavioral features from multiple time windows, emphasizing the importance of query-level signals in ranking models.

Findings

Effective combination of long and short-term behavioral features improves ranking.

Query-level signals are critical for aggregating behavioral data.

Live traffic experiments demonstrate the approach's practical benefits.

Abstract

Customer shopping behavioral features are core to product search ranking models in eCommerce. In this paper, we investigate the effect of lookback time windows when aggregating these features at the (query, product) level over history. By studying the pros and cons of using long and short time windows, we propose a novel approach to integrating these historical behavioral features of different time windows. In particular, we address the criticality of using query-level vertical signals in ranking models to effectively aggregate all information from different behavioral features. Anecdotal evidence for the proposed approach is also provided using live product search traffic on Walmart.com.