Reducing sample selection bias in a machine learning-based recommender system

US12211073B2 · kind B2 · utility

Assignee

• Rakuten Group, Inc. · JP

Inventors

• Yang Shi · Lo Wu, CN
• Guannan Liang · Willington Hill, US
• Youngjoo Chung · Setagaya, JP

Key dates

• Filing date: Apr 5, 2022
• Grant date: Jan 28, 2025
• Expiry date: May 6, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q30/0255
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops. The improvement is achieved by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset. Each shop-specific model is created by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss. The model includes small and large-shop weight parameters that are applied to user-item interaction scores and that are learned during …