US Patent 12062080 Reducing sample selection bias in a machine learning-based recommender system

The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops 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 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.