OMBA: User-Guided Product Representations for Online Market Basket Analysis

TL;DR

OMBA introduces a novel representation learning approach for online market basket analysis that captures temporal dynamics and rare associations, outperforming existing methods on real-world datasets.

Contribution

OMBA is the first to jointly learn product and user representations that preserve temporal dynamics and rare associations in online market basket analysis.

Findings

OMBA outperforms state-of-the-art methods by up to 21%.

It effectively captures temporal changes in product associations.

It emphasizes rarely occurring but strong associations.

Abstract

Market Basket Analysis (MBA) is a popular technique to identify associations between products, which is crucial for business decision making. Previous studies typically adopt conventional frequent itemset mining algorithms to perform MBA. However, they generally fail to uncover rarely occurring associations among the products at their most granular level. Also, they have limited ability to capture temporal dynamics in associations between products. Hence, we propose OMBA, a novel representation learning technique for Online Market Basket Analysis. OMBA jointly learns representations for products and users such that they preserve the temporal dynamics of product-to-product and user-to-product associations. Subsequently, OMBA proposes a scalable yet effective online method to generate products' associations using their representations. Our extensive experiments on three real-world datasets show that OMBA outperforms state-of-the-art methods by as much as 21%, while emphasizing rarely occurring strong associations and effectively capturing temporal changes in associations.