Learning and Transferring IDs Representation in E-commerce

TL;DR

This paper introduces an embedding framework for representing various IDs in e-commerce, improving upon traditional methods by capturing relationships and enabling transfer across items, domains, and tasks.

Contribution

It proposes a novel embedding-based approach to learn and transfer ID representations, addressing sparsity and relationship modeling issues in e-commerce data.

Findings

Effective in measuring item similarity

Enables transfer to unseen items

Validated on Hema App with positive results

Abstract

Many machine intelligence techniques are developed in E-commerce and one of the most essential components is the representation of IDs, including user ID, item ID, product ID, store ID, brand ID, category ID etc. The classical encoding based methods (like one-hot encoding) are inefficient in that it suffers sparsity problems due to its high dimension, and it cannot reflect the relationships among IDs, either homogeneous or heterogeneous ones. In this paper, we propose an embedding based framework to learn and transfer the representation of IDs. As the implicit feedbacks of users, a tremendous amount of item ID sequences can be easily collected from the interactive sessions. By jointly using these informative sequences and the structural connections among IDs, all types of IDs can be embedded into one low-dimensional semantic space. Subsequently, the learned representations are utilized and transferred in four scenarios: (i) measuring the similarity between items, (ii) transferring from seen items to unseen items, (iii) transferring across different domains, (iv) transferring across different tasks. We deploy and evaluate the proposed approach in Hema App and the results validate its effectiveness.