제한 볼츠만 기계를 이용한 협력필터링 기반 추천 시스템
Collaborative Filtering based Recommender System using Restricted Boltzmann Machines
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
추천 시스템은 전자 상거래 시에 고객들의 상품 선택의 편의를 제공하므로 반드시 구비되어야할 기능이다. 협력 필터링은 다른 사용자들이 선호하였던 상품이나 현 사용자가 과거 선호하였던상품들을 위주로 추천 리스트를 제공하는 기법으로서, 가장 널리 활용되는 대표적 기법이다. 최근딥러닝 인공지능 기술을 활용하여 추천 시스템의 성능 향상을 달성하는 연구가 활발히 진행되고있다. 본 연구에서는 사용자가 부여한 평가등급만을 이용하여 딥러닝 기술의 일종인 제한 볼츠만기계 학습을 통해 협력 필터링 기반의 추천 시스템을 개발한다. 또한 학습의 효율성과 성능을 위하여 학습 파라미터 변경 알고리즘을 제시한다. 제안 시스템의 성능 평가를 위하여 실험 분석을통해 기존의 다양한 전통적 협력 필터링 기법들과 비교 분석을 실시하였으며, 제안 알고리즘은기본적인 제한 볼츠만 기계 모델보다 우수한 성능을 가져오는 것으로 확인되었다.
Abstract
Recommender system is a must-have feature of e-commerce, since it provides customers with convenience in selecting products. Collaborative filtering is a widely-used and representative technique, where it gives recommendation lists of products preferred by other users or preferred by the current user in the past. Recently, researches on the recommendation system using deep learning artificial intelligence technologies are actively being conducted to achieve performance improvement. This study develops a collaborative filtering based recommender system using restricted Boltzmann machines of the deep learning technology by utilizing user ratings. Moreover, a learning parameter update algorithm is proposed for learning efficiency and performance. Performance evaluation of the proposed system is made through experimental analysis and comparison with conventional collaborative filtering methods. It is found that the proposed algorithm yields superior performance than the basic restricted Boltzmann machines.
참고문헌 (20)
- Sushma Jaiswal, "Survey on Recommender System Using Deep Learning Networks", Artificial Intelligence Evolution, pp.72~89 (2020), Universal Wiser Publisher Pte. Ltd[DOI]
- Mahdi Jalili, "Evaluating Collaborative Filtering Recommender Algorithms: A Survey", IEEE Access, 6, pp.74003~74024 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- X. Su, "A Survey of Collaborative Filtering Techniques", Advances in Artificial Intelligence (2009)[DOI]
- J. Liu, "Deep Learning Based Recommendation : A Survey", Lecture Notes in Electrical Engineering, 424, pp.451~458 (2017)
- Zeynep Batmaz, "A review on deep learning for recommender systems: challenges and remedies", Artificial Intelligence Review, 52(1), pp.1~37 (2019), Springer Science and Business Media LLC[DOI]
- Ruihui Mu, "A Survey of Recommender Systems Based on Deep Learning", IEEE Access, 6, pp.69009~69022 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- H. Wang, "Collaborative Deep Learning for Recommender Systems", The 21th ACM SIGKDD International ACM Conference on Knowledge Discovery and Data Mining, pp.1235~1244 (2015)
- Shuai Zhang, "Deep Learning Based Recommender System", ACM Computing Surveys, 52(1), pp.1~38 (2019), Association for Computing Machinery (ACM)[DOI]
- R. Salakhutdinov, "Restricted Boltzmann Machines for Collaborative Filtering", The 24th International Conference on Machine Learning (2007)
- G. Hinton, "Lecture Notes in Computer Science", pp.599~619 (2012)
- Y. Zheng, "A Neural Autoregressive Approach to Collaborative Filtering", The 33rd International Conference on Machine Learning (2016)
- S. Kang, "Deep Learning Based Recommender System Using Non-Rating Purchase Data", Master, pp.2016
- Shuiguang Deng, "On Deep Learning for Trust-Aware Recommendations in Social Networks", IEEE Transactions on Neural Networks and Learning Systems, 28(5), pp.1164~1177 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- K. Georgiev, "A Non-iid Framework for Collaborative Filtering with Restricted Boltzmann Machines", The 30th International Conference on Machine Learning, pp.III –1148~III–1156 (2013)
- L. Hu, "Deep Modeling of Group Preferences for Group-based Recommendation", The 28th AAAI Conference on Artificial Intelligence, pp.1861~1867 (2014)
- 변해원, "제한된 볼츠만 기계학습 알고리즘을 이용한 우리나라 지역사회 노인의 경도인지장애 예측모형", 융합정보논문지, 9(8), pp.248~253 (2019), 중소기업융합학회[DOI]
- G. Lee, "Development of Collaborative Deep Learning System for Fashion Recommendation", Master, pp.2019
- Abhaya Kumar Sahoo, "DeepReco: Deep Learning Based Health Recommender System Using Collaborative Filtering", Computation, 7(2), pp.1~25 (2019), MDPI AG[DOI]
- H. Larochelle, "Learning Algorithms for the Classification Restricted Boltzmann Machine", Journal of Machine Learning Research, 13, pp.643~669 (2012)[DOI]
- Dan Claudiu Cireşan, "Deep, Big, Simple Neural Nets for Handwritten Digit Recognition", Neural Computation, 22(12), pp.3207~3220 (2010), MIT Press - Journals[DOI]