One Embedding To Do Them All

TL;DR

This paper presents a unified framework for creating product embeddings by combining text, clickstream, and image data, improving performance across multiple e-commerce tasks.

Contribution

It introduces a novel approach to integrate diverse data sources into a single product embedding, enhancing versatility and effectiveness in e-commerce applications.

Findings

Unified embeddings perform well across multiple tasks

Combining data sources improves attribute coverage

Embeddings enhance product similarity and return prediction

Abstract

Online shopping caters to the needs of millions of users daily. Search, recommendations, personalization have become essential building blocks for serving customer needs. Efficacy of such systems is dependent on a thorough understanding of products and their representation. Multiple information sources and data types provide a complete picture of the product on the platform. While each of these tasks shares some common characteristics, typically product embeddings are trained and used in isolation. In this paper, we propose a framework to combine multiple data sources and learn unified embeddings for products on our e-commerce platform. Our product embeddings are built from three types of data sources - catalog text data, a user's clickstream session data and product images. We use various techniques like denoising auto-encoders for text, Bayesian personalized ranking (BPR) for clickstream data, Siamese neural network architecture for image data and combined ensemble over the above methods for unified embeddings. Further, we compare and analyze the performance of these embeddings across three unrelated real-world e-commerce tasks specifically checking product attribute coverage, finding similar products and predicting returns. We show that unified product embeddings perform uniformly well across all these tasks.