簡易檢索 / 詳目顯示

回結果列表
研究生： 吳震
WU ZHEN
論文名稱： 應用進化演算法為基礎之用戶特徵分群及矩陣分解法於推薦系統之協同過濾
Applying Evolutionary-based User Characteristic Clustering and Matrix Factorization to Collaborative Filtering in Recommender Systems
指導教授： 郭人介
Ren-Jieh Kuo
口試委員: 羅士哲
Shih-Che Lo
歐陽超
Chao Ou-Yang
學位類別： 碩士
Master
系所名稱： 管理學院 - 工業管理系
Department of Industrial Management
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 61
中文關鍵詞： 推薦系統 、協同過濾 、進化演算法 、用戶特徵分群 、矩陣分解
外文關鍵詞： Recommender systems, Collaborative filtering, Evolutionary algorithm, User characteristic clustering, Matrix factorization
相關次數： 點閱：172  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近年來，隨著眾多的網路服務業的興起，推薦系統得到前所未有的廣泛應用，用戶可以從網路輕鬆獲得所需的信息、產品或服務，商家也可以通過推薦系統增加額外的收入。但是在當今的推薦系統中，資料規模非常大，評分資料的稀疏性嚴重影響推薦的品質。
    本研究提出一種基於遺傳演算法的結合用戶特徵分群和矩陣分解法的推薦演算法，並使用輪廓係數為用戶分群提供依據，再通過使用指數排名選擇技術優化原本的基於進化的矩陣分解推薦系統。
    本研究之實驗使用兩組評分資料集驗證提出的演算法，並使用MAE（mean square error）、精確度（precision）、召回率（recall）、F得分四種評比指標與現存的基於進化的矩陣分解推薦系統進行比較。根據實驗結果證實，本研究所提出的UC-EAMF之性能在標準資料集中得以獲得較現存的基於進化的矩陣分解優異之表現。

    In recent years, with the rise of numerous Internet service industries, recommendation systems have been widely used as never before. Users can easily obtain the information, products or services they need from the Internet, and businesses can also increase additional income through the recommendation system. However, in today's recommendation system, the data scale is very large, and the sparsity of the scoring data seriously affects the quality of the recommendation.
    This research proposes a recommendation algorithm based on evolutionary algorithm that combines user characteristic grouping and matrix factorization, and uses silhouette coefficient to provide a basis for user clustering, and then optimizes the original evolutionary-based matrix factorization recommendation system by using exponential ranking selection technology.
    The experiment of this research uses two sets of rating data sets to verify the proposed algorithm, and uses four evaluation indicators of MAE (mean square error), precision, recall, F score to evaluate performance. And the performance of the proposed method is compared with the existing evolutionary-based matrix factorization. According to the experimental results, the performance of the proposed UC-EAMF can be obtained better than that of the existing evolutionary-based matrix factorization for the benchmark data sets.

    摘要 I ABSTRACT II 致謝 III CONTENTS IV LIST OF FIGURES VI LIST OF TABLES VII CHAPTER 1 INTRODUCTION 1 1.1 Research Background and Motivation 1 1.2 Research Objectives 2 1.3 Research Scope and Constraints 2 1.4 Thesis Organization 2 CHAPTER 2 LITERATURE REVIEW 4 2.1 Recommender Systems 4 2.1.1 Collaborative Filtering 7 2.1.2 Matrix Factorization 8 2.2 Clustering Algorithm 10 2.2.1 K-means Algorithm 11 2.2.2 User Characteristic Similarity 14 2.3 Evolutionary Computation 15 2.3.1 Selection Techniques 16 2.3.2 Evolutionary-based Matrix Factorization 18 CHAPTER 3 METHODOLOGY 19 3.1 Research Framework 19 3.2 Proposed Method 20 3.3 Pseudocode for the Proposed Algorithm 27 3.4 Performance Evaluation 28 CHAPTER 4 EXPERIMENTAL RESULTS 29 4.1 Datasets 29 4.2 Performance Measurement 29 4.3 Parameter Setting 31 4.4 Experimental Results 38 4.5 Statistical Hypothesis 45 4.6 Time Complexity 47 CHAPTER 5 CONCLUSIONS AND FUTURE RESEARCH 48 5.1 Conclusions 48 5.2 Contributions 48 5.3 Future Research 48 REFERENCES 50

    Ba, Q., Li, X., and Bai, Z., Clustering collaborative filtering recommendation system based on SVD algorithm. 2013 IEEE 4th International Conference on Software Engineering and Service Science, 963-967, 2013.
    Bennett, J., and Lanning, S., The netflix prize. In proceedings of the KDD Cup Workshop, 3-6, 2007.
    Bobadilla, J., Ortega, F., Hernando, A., and Gutiérrez, A., Recommender systems survey. Knowledge-Based Systems, 46, 109-132, 2013.
    Burke, R., Hybrid web recommender systems. P. Brusilovsky, A. Kobsa, W. Nejdl (Eds.), The Adaptive Web, 377-408, 2007.
    Cramer, N.L., A representation for the adaptive generation of simple sequential programs. In Proceedings, International Conference on Genetic Algorithms and their Applications, 183-187, 1985.
    Devi, S.G., Selvam, K., and Rajagopalan, S., An abstract to calculate big O factors of time and space complexity of machine code ,2011.
    Esslimani, I., Brun, A., and Boyer., A., Densifying a behavioral recommender system by social networks link prediction methods. Social Network Analysis and Mining, 1, 159–172, 2010.
    Fogel, L.J., Owens, A.J., and Walsh, M.J., Artificial Intelligence through Simulated Evolution, John Wiley, 1966.
    Gai, P.J., and Klesse, A.K., Making Recommendations more effective through framings: impacts of user- versus item-based framings on recommendation click-throughs. Journal of Marketing, 83(6), 61–75, 2019.
    Goldberg, D.E., and Deb, K., A comparative analysis of selection schemes used in genetic algorithms, Foundations of Genetic Algorithms, 1, 69-93, 1991.
    Herlocker, L., Konstan, J.A., Terveen, L.G., and Riedl, J.T., Evaluating collaborative filtering recommender systems, Acm Transactions on Information & System Security, 22(1), 5-53, 2004.
    Holland, J.H., Adaptation in Natural and Artificial Systems. Mich., Ann Arbor:Univ. of Michigan Press, 1975.
    Holland, J.H., Holland Adaptation in natural and artificial systems, 1992.
    Horváth, T., and de Carvalho, A.C.P.L.F., Evolutionary computing in recommender systems: a review of recent research. Nat Comput, 16, 441–462, 2017.
    Idrissi, N., and Zellou, A., A systematic literature review of sparsity issues in recommender systems. Social Network Analysis and Mining, 10, 15, 2020.
    Jalili, M., Ahmadian, S., Izadi, M., Morad, P., i and Salehi, M., Evaluating collaborative filtering recommender algorithms: a survey. In IEEE Access, 6, 74003-74024, 2018.
    Jin, Q., Zhang, Y., Cai, W., and Zhang, Y., A new similarity computing model of collaborative filtering. In IEEE Access, 8, 17594-17604, 2020.
    Karatzoglou, A., and Hidasi, B., Deep learning for recommender systems, In Proceedings of the Eleventh ACM Conference on Recommender Systems (RecSys '17). Association for Computing Machinery, 396–397, 2017.
    Kilani, Y., Otoom, A.F., Alsarhan, A., and Almaayah, M., A genetic algorithms-based hybrid recommender system of matrix factorization and neighborhood-based techniques. Journal of Computational Science, 28, 78-93, 2018
    Kwok, J., Zhou, Z., and Xu, L., Machine Learning, 2016.
    Liji, U., Chai, Y., and Chen, J., Improved personalized recommendation based on user attributes clustering and score matrix filling. Computer Standards & Interfaces, 57, 59-67, 2018.
    Lika, B., Kolomvatsos, K., and Hadjiefthymiades., S., Facing the cold start problem in recommender systems. Expert Systems with Applications, 41, 2065-2073, 2014.
    Lozano, J.A., Pena, J.M., and Larranaga, P., An empirical comparison of four initialization methods for the k-means algorithm. Pattern Recognition Lett., 20, 1027-1040, 1999.
    Lu, J., Wu, D., Mao, M., Wang, W., and Zhang, G., Recommender system application developments: A survey. Decision Support Systems, 74, 12-32, 2015.
    Mehta, R., and Rana, K., A review on matrix factorization techniques in recommender systems. 2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA), 269-274, 2017.
    Meteren, R.V., and Someren, M.V., Using content-based filtering for recommendation. Proceedings of ECML 2000 Workshop: Maching Learning in Information Age, 47–56, 2000.
    Navgaran, D.Z., Moradi, P., and Akhlaghian, F., Evolutionary based matrix factorization method for collaborative filtering systems. 21st Iranian Conference on Electrical Engineering (ICEE), 1-5, 2013.
    Rechenberg, I., Evolution strategy: optimization of technical systems by means of biological evolution. Fromman-Holzboog, 104, 1973.
    Shukla, A., Pandey, H.M., and Mehrotra, D., Comparative review of selection techniques in genetic algorithm, 2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE), 515-519, 2015.
    Snasel, V., Platos, J., and Kromer, P., Developing genetic algorithms for Boolean matrix factorization. Proceedings of the Dateso 2008 Annual International Workshop on DAtabases,61-70, 2008.
    Tobias, B., and Thiele L., A comparison of selection schemes used in genetic algorithms, 1995.
    Wu, Z., Li, G., Liu, Q., Xu, G., and Chen, E., Covering the sensitive subjects to protect personal privacy in personalized recommendation. In IEEE Transactions on Services Computing, 11, 3, 493-506, 2018.
    Yin, C., Shi, L., Sun, R., and Wang, J., Improved collaborative filtering recommendation algorithm based on differential privacy protection. J Supercomput 76, 5161–5174, 2019.
    Yu, K., Schwaighofer, A., Tresp, V., Xu, X., and Kriegel, H., Probabilistic memory-based collaborative filtering. In IEEE Transactions on Knowledge and Data Engineering, 16, 1, 56-69, 2004.

    QR CODE