The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Generalized neural collaborative filtering

일반화 신경망 협업필터링

  • In Jun Hwang (Business School, Sogang University) ;
  • Hee Ju Kim (Business School, Sogang University) ;
  • Yu Jin Kim (Business School, Sogang University) ;
  • Yoon Dong Lee (Business School, Sogang University)
  • 황인준 (서강대학교 경영학부) ;
  • 김희주 (서강대학교 경영학부) ;
  • 김유진 (서강대학교 경영학부) ;
  • 이윤동 (서강대학교 경영학부)
  • Received : 2024.02.15
  • Accepted : 2024.03.09
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we conduct an exploratory analysis of the MovieLens data, which is frequently used in many recommender system researches, to examine the detailed characteristics of the data. Also, we seek alternatives to improve the well-known neural collaborative filtering (NCF) method. NCF improved matrix factorization method by using deep neural networks in recommender systems. We devise, generalized NCF (G-NCF), a variant of NCF and test the performances. The G-NCF we propose shows superior characteristics on average performance across key evaluation metrics, compared to the NCF, but it also has a slightly larger variance in the evaluation metrics. Evaluation metrics such as MAP and nDCG were considered for comparison.

본 연구에서는, 추천시스템 연구에 자주 활용되는 무비렌즈 데이터에 대한 탐색적 분석을 통하여 무비렌즈 데이터의 자세한 특성을 살펴보고, 추천시스템에서 심층신경망을 이용한 협업필터링 (NCF) 방법으로 잘 알려진 신경망행렬분해법을 개선하기 위한 대안을 모색한다. 본 연구에서, 제안한 일반화 NCF (G-NCF) 방법은 기존의 NCF 방법에 비하여 주요 평가 지표에서 평균적으로 우수한 특성을 보이지만, 평가지표의 산포가 다소 커지는 단점도 함께 가진다. 성능 비교를 위한 평가 지표로 MAP와 nDCG 등을 이용하였다.

Keywords

References

  1. Ba JL, Kiros JR, and Hinton GE (2016). Layer normalization, Available from: pre-print: arXiv:1607.06450
  2. Chaudhury S and Tewari A (2017). Online learning to rank with top-k feedback, Journal of Machine Learning Reseach, 18, 1-50.
  3. Harper FM and Konstan JA (2015). The MovieLens datasets: History and context, ACM Transactions on Interactive Intelligent Systems (TiiS), 5, 1-19.
  4. He X, Liao L, Zhang H, Nie L, Hu X, and Chua TS (2017). Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, 173-182.
  5. Kim HJ (2019). A study on collaborative filtering based on clustering method (Master's thesis), Sogang University, Seoul.
  6. Kim SE (2021). A study on collaborative filtering using deep neural network (Master's thesis), Sogang University, Seoul.
  7. Lee S, Cho Y, Lee JS, and Yu D (2020). Comparative study of recommender systems using movie rating data, Journal of the Korean Data & Information Science Society, 31, 975-991.
  8. Rendle S, Freudenthaler C, Gantner Z, and Schmidt-Thieme L (2012). BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, Montreal, QC, 452-461.
  9. Seo HJ (2018). Comparative study of heuristic approaches for collaborative filtering (Master's thesis), Sogang University, Seoul.
  10. Zhang Y, Li Q, Choi I, and Kim JK (2021). Information Systems Review, 23, 155-172.
  11. Zhang P and Su W (2012). Statistical inference on recall, precisiom and average precision under random selection. In Proceedings of 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2012), Chongqing, 1348-1352.