An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems

논문 연구/논문 분석

An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems

상솜공방 2023. 9. 30. 17:29

본 논문은 추천 시스템에서 Matrix Factorzation을 이용한 Collaborative Filtering 기술을 한 단계 더 진보시켰다.

해당 논문을 읽으면서 필기한 내용을 정리한다.

논문 링크: https://ieeexplore.ieee.org/abstract/document/6748996

An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems

Matrix-factorization (MF)-based approaches prove to be highly accurate and scalable in addressing collaborative filtering (CF) problems. During the MF process, the non-negativity, which ensures good representativeness of the learnt model, is critically imp

ieeexplore.ieee.org

최종 알고리즘

논문의 아이디어

1. Non-Negative Matrix Factorization을 Single-element-base로 수정

→ Computational cost를 절반 가까이 줄임

2. L2 Regularization을 적용

→ 정확도를 매우 높임