Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

TL;DR

This paper introduces Trans2D, a Transformer-based model with a novel attention mechanism for sequential watchlist recommendation in e-commerce, effectively predicting user attention on items with multiple changing attributes.

Contribution

The paper proposes a new sequential recommendation task for watchlist items and introduces Trans2D, a Transformer model with Attention2D for capturing complex attribute interactions.

Findings

Trans2D outperforms state-of-the-art baselines on eBay data.

The novel Attention2D mechanism effectively models attribute interactions.

The approach improves prediction accuracy for watchlist item relevance.

Abstract

In e-commerce, the watchlist enables users to track items over time and has emerged as a primary feature, playing an important role in users' shopping journey. Watchlist items typically have multiple attributes whose values may change over time (e.g., price, quantity). Since many users accumulate dozens of items on their watchlist, and since shopping intents change over time, recommending the top watchlist items in a given context can be valuable. In this work, we study the watchlist functionality in e-commerce and introduce a novel watchlist recommendation task. Our goal is to prioritize which watchlist items the user should pay attention to next by predicting the next items the user will click. We cast this task as a specialized sequential recommendation task and discuss its characteristics. Our proposed recommendation model, Trans2D, is built on top of the Transformer architecture, where we further suggest a novel extended attention mechanism (Attention2D) that allows to learn complex item-item, attribute-attribute and item-attribute patterns from sequential-data with multiple item attributes. Using a large-scale watchlist dataset from eBay, we evaluate our proposed model, where we demonstrate its superiority compared to multiple state-of-the-art baselines, many of which are adapted for this task.