검색 상세

Autoencoder and Collaborative Filtering Based Recommender System Using Natural Noise Removal

오토인코더 및 협엽필터링 기반 자연 노이즈 제거를 통한 추천 시스템

초록 (요약문)

To improve the performance of the collaborative filtering (CF) based recommender systems, users’ rating data should be pre-processed to avoid noise and enhance data reliability. However, anomalies can exist in non-attacked real user data, which is called natural noise, as the ratings of users can be impacted by unpredictable factors such as other users’ ratings and anchoring bias. In this thesis, an autoencoder-based recommendation system was proposed for exploiting the ability of both anomaly detection and CF. The proposed system detects the natural noise in the rating data based on the reconstruction errors after training. By removing the detected natural noise, CF can predict the unrated ratings with noise-free data. Our experiments show that the proposed model showed better performance than the traditional method that does not consider natural noise detection as well as the conventional natural noise detection method called rating classification.

more