請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88390完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 蔡政安 | zh_TW |
| dc.contributor.advisor | Chen-An Tsai | en |
| dc.contributor.author | 歐怡君 | zh_TW |
| dc.contributor.author | Yi-Chun Ou | en |
| dc.date.accessioned | 2023-08-11T16:04:19Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-11 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-24 | - |
| dc.identifier.citation | [1] Hyeyoung Ko, Suyeon Lee, Yoonseo Park, and Anna Choi. A survey of recom mendation systems: Recommendation models, techniques, and application fields. Electronics, 11(1), 2022.
[2] Dr Anne-Kathrin Klesse Phyliss Jia Gai. Why recommendations on netflix, amazon, or wechat could be more influential than you think. Forbes, 04 2020. [3] Bernard Marr. Netflix used big data to identify the movies that are too scary to finish. Forbes, 04 2018. [4] Il Im and Alexander Hars. Does a one-size recommendation system fit all? the ef fectiveness of collaborative filtering based recommendation systems across different domains and search modes. ACM Trans. Inf. Syst., 26:4, 2007. [5] Abhijeet Ghoshal, Syam Menon, and Sumit Sarkar. Recommendations using infor mation from multiple association rules: A probabilistic approach. Inf. Syst. Res., 26(3):532–551, September 2015. [6] Yehuda Koren and Robert Bell. Advances in Collaborative Filtering, pages 77–118. Springer US, Boston, MA, 2015. [7] Mehrbakhsh Nilashi, Othman Ibrahim, and Karamollah Bagherifard. A recom mender system based on collaborative filtering using ontology and dimensionality reduction techniques. Expert Systems with Applications, 92:507–520, 2018. [8] Hyeyoung Ko, Suyeon Lee, Yoonseo Park, and Anna Choi. A survey of recom mendation systems: Recommendation models, techniques, and application fields. Electronics, 2022. [9] Francesco Ricci, Lior Rokach, and Bracha Shapira. Introduction to Recommender Systems Handbook, pages 1–35. Springer US, Boston, MA, 2011. [10] Ana Belén Barragáns-Martínez, Enrique Costa-Montenegro, Juan C. Burguillo, Marta Rey-López, Fernando A. Mikic-Fonte, and Ana Peleteiro. A hybrid content based and item-based collaborative filtering approach to recommend tv programs enhanced with singular value decomposition. Information Sciences, 180(22):4290– 4311, 2010. [11] Bogdan Walek and Vladimir Fojtik. A hybrid recommender system for recommend ing relevant movies using an expert system. Expert Systems with Applications, 158:113452, 2020. [12] J.J. Buckley, W. Siler, and Douglas Tucker. A fuzzy expert system. Fuzzy Sets and Systems, 20(1):1–16, 1986. [13] Taushif Anwar, V. Uma, and Gautam Srivastava. Rec-CFSVD++: Implementing Recommendation System Using Collaborative Filtering and Singular Value Decom position (SVD)++. International Journal of Information Technology & Decision Making (IJITDM), 20(04):1075–1093, July 2021. [14] Laisong Kang, Shifeng Liu, Daqing Gong, and Mincong Tang. A personalized point-of-interest recommendation system for O2O commerce. Electronic Markets, 31(2):253–267, June 2021. [15] Liang Xiang and Qing Yang. Time-dependent models in collaborative filtering based recommender system. In 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, volume 1, pages 450–457, Sep. 2009. [16] Shuai Zhang, Lina Yao, Aixin Sun, and Yi Tay. Deep learning based recommender system: A survey and new perspectives. ACM Comput. Surv., 52(1), feb 2019. [17] Zahra Zamanzadeh Darban and Mohammad Hadi Valipour. Ghrs: Graph-based hy brid recommendation system with application to movie recommendation. Expert Systems with Applications, 200:116850, 2022. [18] Hang Zheng, Xing Xing, Qiuyang Han, Mindong Xin, and Yong Niu. Uiae: Col laborative filtering for user and item based on auto-encoder. In 2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC), pages 1–6, 2021. [19] Florian Strub, Jérémie Mary, and Preux Philippe. Collaborative Fil tering with Stacked Denoising AutoEncoders and Sparse Inputs. In NIPS Workshop on Machine Learning for eCommerce, Montreal, Canada, De cember 2015. [20] Sheng Li, Jaya Kawale, and Yun Fu. Deep collaborative filtering via marginal ized denoising auto-encoder. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, CIKM ’15, page 811– 820, New York, NY, USA, 2015. Association for Computing Machinery. [21] Yihao Zhang, Chu Zhao, Mian Chen, and Meng Yuan. Integrating stacked sparse auto-encoder into matrix factorization for rating prediction. IEEE Access, 9:17641– 17648, 2021. [22] Milad Ahmadian, Mahmood Ahmadi, Sajad Ahmadian, Seyed Mohammad Ja far Jalali, Abbas Khosravi, and Saeid Nahavandi. Integration of deep sparse autoen coder and particle swarm optimization to develop a recommender system. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 2524–2530, Oct 2021. [23] Yakun Li, Jiadong Ren, Jiaomin Liu, and Yixin Chang. Deep sparse autoencoder prediction model based on adversarial learning for cross-domain recommendations. Knowledge-Based Systems, 220:106948, 2021. [24] Francesco Ricci, Lior Rokach, and Bracha Shapira. Introduction to Recommender Systems Handbook, pages 1–35. Springer US, Boston, MA, 2011. [25] Ruo-Qian Wang. A recommender system-inspired cloud data filling scheme for satellite-based coastal land use classification. International Journal of Applied Earth Observation and Geoinformation, 109:102770, 2022. [26] Xin Luo, Mengchu Zhou, Yunni Xia, and Qingsheng Zhu. An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender sys tems. IEEE Transactions on Industrial Informatics, 10(2):1273–1284, 2014. [27] Alexandrin Popescul, Lyle H. Ungar, David M Pennock, and Steve Lawrence. Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments, 2013. [28] Mustansar Ali Ghazanfar and Adam Prügel-Bennett. The advantage of careful im putation sources in sparse data-environment of recommender systems: Generating improved svd-based recommendations. Informatica (Slovenia), 37:61–92, 2013. [29] Stef Buuren and Catharina Groothuis-Oudshoorn. Mice: Multivariate imputation by chained equations in r. Journal of Statistical Software, 45, 12 2011. [30] Sanxing Cao, Nan Yang, and Zhengzheng Liu. Online news recommender based on stacked auto-encoder. In 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), pages 721–726, 2017. [31] Siti Nurmaini, Annisa Darmawahyuni, Akhmad Noviar Sakti Mukti, Muham mad Naufal Rachmatullah, Firdaus Firdaus, and Bambang Tutuko. Deep learning-based stacked denoising and autoencoder for ecg heartbeat classification. Electronics, 9(1), 2020. [32] Diana Ferreira, Sofia Silva, António Abelha, and José Machado. Recommendation system using autoencoders. Applied Sciences, 10(16), 2020. [33] Zahra Zamanzadeh Darban and Mohammad Hadi Valipour. GHRS: graph-based hybrid recommendation system with application to movie recommendation. CoRR, abs/2111.11293, 2021. [34] Shuai Zhang, Lina Yao, and Xiwei Xu. Autosvd++: An efficient hybrid collab orative filtering model via contractive auto-encoders. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’17, page 957–960, New York, NY, USA, 2017. Association for Computing Machinery. [35] Helge Langseth and Thomas D. Nielsen. Scalable learning of probabilistic latent models for collaborative filtering. Decision Support Systems, 74:1–11, 2015. [36] Julio Barbieri, Leandro G.M. Alvim, Filipe Braida, and Geraldo Zimbrão. Au toencoders and recommender systems: Cofils approach. Expert Systems with Applications, 89:81–90, 2017. [37] Yan Leng, Rodrigo Ruiz, Xiaowen Dong, and Alex ’Sandy’ Pentland. Interpretable recommender system with heterogeneous information: A geometric deep learning perspective. SSRN Electronic Journal, 2020. [38] Soyeon Caren Han, Taejun Lim, Siqu Long, Bernd Burgstaller, and Josiah Poon. Glocal-k: Global and local kernels for recommender systems. Association for Com puting Machinery, 2021. [39] Suvash Sedhain, Aditya Krishna Menon, Scott Sanner, and Lexing Xie. Autorec: Autoencoders meet collaborative filtering. Proceedings of the 24th International Conference on World Wide Web, 2015. [40] Siyuan Guo, Ying Wang, Hao Yuan, Zeyu Huang, Jianwei Chen, and Xin Wang. Taert: Triple-attentional explainable recommendation with temporal convolutional network. Information Sciences, 567:185–200, 2021. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88390 | - |
| dc.description.abstract | 在資訊蓬勃的時代，人們經常難以有效率的在眾多訊息中獲取所需的資訊，因此，推薦系統在資訊過濾上扮演了重要的角色。本研究的目的是建立一個推薦模型，依照使用者的偏好提供商品推薦。本研究提出的推薦模型是由資料填補和神經網絡模型 (自動編碼器)組成。我們使用了兩份數據集，MovieLens 100K和Cellphone數據集，來驗證和比較我們與其他推薦系統模型的性能。其中，評分數有許多缺失值，我們使用三種填補方法 (填零、SimpleImputer和IterativeImputer)處理缺失值。資料集的特徵包括「僅評分數」或「評分數、使用者偏好和人口資訊」。模型訓練中，本研究嘗試了兩種 (Adagrad、RMSprop)分類器和三個不同的學習率 (0.001, 0.01, 0.1)，並以均方誤差 (RMSE)來評估模型的準確率。結果顯示，訓練特徵同時放入評分數與使用者的資訊，並以IterativeImputer方法填補缺失值時，我們提出的模型表現優於其他推薦系統。此外，不同的優化器和學習率在性能上沒有顯著差異。整體而言，相較於先前的模型，本研究之準確率進步了13.5%。最後，以商品的餘弦相似度 (Cosine similary)對使用者做商品推薦。 | zh_TW |
| dc.description.abstract | In the information explosion era, it is difficult for people to effectively search for the required information from the massive content. Therefore, recommendation systems play a crucial role in information filtering. The purpose of this study is to build a recommendation model to provide users with product recommendations according to their preferences. In this paper, we propose a recommendation model composed of an imputation method and a neural network model (using autoencoder). Two benchmark datasets, MovieLens 100K and Cellphone datasets, are used to verify and compare our proposed model with other recommendation systems. Three imputation methods (Fill with 0, SimpleImputer, and IterativeImputer) are implemented here for dealing with the large proportion of missing values in the rating scores. The features of the dataset includes “rating numbers only” or “rating numbers, user preference, and demographic information”. During the model training, experiments were performed with two classifiers (Adagrad and RMSprop) and three learning rates (0.001, 0.01, 0.1). The accuracy of the model was evaluated using root mean square error (RMSE). The results show that our proposed model performs better than other recommendation systems when using both rating numbers and user information as training features, along with the IterativeImputer method for missing values. Moreover, the different optimizers and learning rates have no significant difference in performance. Overall, this study shows that our proposed model can improve the accuracy up to 13.5% compared to other models. In addition, the recommendations for users are made based on the cosine similarity of items. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-11T16:04:18Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-11T16:04:19Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xi List of Tables xiii Chapter 1 Introduction 1 1.1 Background ................................................. 1 1.2 Recommendation System ...................................... 2 Chapter 2 Literature Review 7 2.1 Matrix factorization-based recommendation models ........... 7 2.2 Autoencoder-based recommendation models .................... 8 Chapter 3 Materials 11 3.1 Data Overview ............................. 11 3.1.1 MovieLens 100K Datasets ................ 11 3.1.2 Cellphones Datasets..................... 12 3.2 Data Preprocessing......................... 13 3.3 Analysis of MovieLens 100K Data............ 14 3.4 Analysis of Cellphone Data ................ 16 Chapter 4 Methodology 19 4.1 Data Imputation ............................ 20 4.2 Autoencoder Model .......................... 21 4.3 Prediction Architecture..................... 22 4.4 Recommendation System....................... 24 4.5 Model Evaluation............................ 25 Chapter 5 Experimental Results 27 5.1 Environment .............................. 27 5.2 Main Results ............................. 27 Chapter 6 Conclusion 39 References 41 | - |
| dc.language.iso | en | - |
| dc.subject | 資料稀疏性 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 資料填補 | zh_TW |
| dc.subject | 推薦系統 | zh_TW |
| dc.subject | 自動編碼器 | zh_TW |
| dc.subject | Recommendation system | en |
| dc.subject | Data sparsity | en |
| dc.subject | Data imputation | en |
| dc.subject | Autoencoder | en |
| dc.subject | Deep learning | en |
| dc.title | 結合深度自動編碼器與資料填補之推薦系統 | zh_TW |
| dc.title | The Recommendation System Combining Deep Autoencoder and Data Imputation | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 邱春火;薛慧敏 | zh_TW |
| dc.contributor.oralexamcommittee | Chun-Huo Ciou;Huey-Ming Hsueh | en |
| dc.subject.keyword | 推薦系統,資料稀疏性,資料填補,深度學習,自動編碼器, | zh_TW |
| dc.subject.keyword | Recommendation system,Data sparsity,Data imputation,Deep learning,Autoencoder, | en |
| dc.relation.page | 48 | - |
| dc.identifier.doi | 10.6342/NTU202301570 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-07-24 | - |
| dc.contributor.author-college | 共同教育中心 | - |
| dc.contributor.author-dept | 統計碩士學位學程 | - |
| 顯示於系所單位： | 統計碩士學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 8.7 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。