This page organizes papers related to artificial intelligence published around the world. This page is summarized using Google Gemini and is operated on a non-profit basis. The copyright of the paper belongs to the author and the relevant institution. When sharing, simply cite the source.
This paper explores the efforts of modern e-commerce platforms to provide timely and contextually relevant recommendations to enhance the customer experience. Specifically, we address the understudied challenge of recommending general merchandise to customers focused on grocery shopping. To this end, we propose a novel approach, the cross-pollination (XP) framework, that leverages multi-source product associations and real-time shopping cart context. This framework consists of two steps: (1) a candidate generation mechanism that uses joint purchase market basket analysis and an LLM-based approach to identify novel inter-item associations; and (2) a transformer-based ranker that leverages real-time sequential shopping cart context and optimizes for engagement signals such as shopping cart additions.
Takeaways, Limitations
•
Takeaways:
◦
Providing practical techniques for cross-category recommendations across grocery and general merchandise.
◦
Increased cart add-to rates on product pages by 36% with LLM-based search.
◦
Increased cart add-to-sales rates by 15% on the cart page using a context-based ranker.
◦
Providing comprehensive insights for e-commerce systems.
•
Limitations:
◦
There is no specific mention of Limitations in the paper (no inference can be made from the presented information).
