Cross Market Recommendation (CMR) is a method of recommending in a resource-scarce market by using modelagnostic meta-learning. Generally, more interactions give more clues to identify the user preferences, so CF performs better with outlier users (who have more item interactions) than normal users. However, constructing each adapt batch set (support set) and evaluation batch set (query set) for meta-learning in CMR causes the model to underfit in outlier users. We aim at this phenomenon and propose a new hybrid strategy to solve this problem. By simply combining MAML and CF to target general users and outliers, respectively. We also validate our method with the benchmark dataset and the proposed model shows better performance compared to the original model.
VII. ACKNOWLEDGEMENT This research was supported by the MIST(Ministry of Science, ICT), Korea, under the National Program for Excellence in SW), supervised by the IITP (Institute of Information & communications Technology Planning & Evaluation) in 2023 (2022-0-01077).
