{"title":"Recommender Systems Using Ensemble Techniques","authors":"Yeonjeong Lee, Kyoung-jae Kim, Youngtae Kim","volume":82,"journal":"International Journal of Computer and Information Engineering","pagesStart":1348,"pagesEnd":1352,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/17197","abstract":"
This study proposes a novel recommender system that uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user’s preference. The proposed model consists of two steps. In the first step, this study uses logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. Then, this study combines the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. In the second step, this study uses the market basket analysis to extract association rules for co-purchased products. Finally, the system selects customers who have high likelihood to purchase products in each product group and recommends proper products from same or different product groups to them through above two steps. We test the usability of the proposed system by using prototype and real-world transaction and profile data. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The results also show that the proposed system may be useful in real-world online shopping store.<\/p>\r\n","references":"[1] M. J. Pazzani, and D. Billsus, \u201cContent-Based Recommendation Systems,\u201d \r\nLecture Notes in Computer Science, vol. 4321, pp. 325\u2013341, 2007. \r\n[2] K. \u2013L. Wu, C. C. Aggarwal, and P. S. Yu, \u201cPersonalization with dynamic \r\nprofiler,\u201d in Proceedings of the Third International Workshop on \r\nAdvanced Issues of E-commerce and Web-based Information Systems, \r\n2001, pp. 12\u201320. \r\n[3] J. Breese, D. Heckerman, and C. Kadie, \u201cEmpirical analysis of predictive \r\nalgorithms for collaborative filtering,\u201d in Proceedings of the 14th \r\nConference on Uncertainty in Artificial Intelligence, San Francisco, CA, \r\n1998, pp. 43\u201352. \r\n[4] J. Konstan, B. Miller, D. Maltz, J. Herlocker, L. Gordon, and J. Riedl, \r\n\u201cGroupLens: Applying Collaborative Filtering to Usenet News,\u201d \r\nCommunication of the ACM, vol. 40, pp. 77\u201387, 1997. \r\n[5] M. J. Pazzani, \u201cA framework for collaborative, content-based and \r\ndemographic filtering,\u201d Artificial Intelligence Review, vol. 13, no. 5-6, pp. \r\n393\u2013408, 1999. \r\n[6] B. M. Sarwar, G. Karypis, J. A. Konstan, and J. Riedl, \u201cAnalysis of \r\nrecommendation algorithms for e-commerce,\u201d in Proceedings of \r\nConference on ACM Electronic Commerce, 2000, pp. 158\u2013167. \r\n[7] J. K. Kim, Y. H. Cho, W. J. Kim, J. R. Kim, and J. H. Suh, \u201cA \r\npersonalized recommendation procedure for Internet shopping support,\u201d \r\nElectronic Commerce Research and Applications, vol. 1, pp. 301\u2013313, \r\n2002. \r\n[8] J. K. Kim, J. H. Suh, D. H. Ahn, and Y. H. Cho, \u201cA personalized \r\nrecommendation methodology based on collaborative filtering,\u201d Journal \r\nof Intelligence and Information Systems, vol. 8, no. 2, pp. 139\u2013157, 2002. \r\n[9] Y. H. Cho, J. K. Kim, and S. H. Kim, \u201cA personalized recommender \r\nsystem based on Web usage mining and decision tree induction,\u201d Expert \r\nSystems with Applications, vol. 23, pp. 329\u2013342, 2002. \r\n[10] J. K. Kim, D. H. Ahn, and Y. H. Cho, \u201cDevelopment of a personalized \r\nrecommendation procedure based on data mining techniques for internet \r\nshopping malls,\u201d Journal of Intelligence and Information Systems, vol. 9, \r\nno.3, pp. 177\u2013191, 2003. \r\n[11] J. W. Kim, S. J. Bae, and H. J. Lee, \u201cSparsity Effect on Collaborative \r\nFiltering-based Personalized Recommendation,\u201d Asia Pacific Journal of \r\nInformation Systems, vol.14, no.2, pp. 131~149, 2004. \r\n[12] Y. H. Cho, and J. K. Kim, \u201cApplication of Web usage mining and product \r\ntaxonomy to collaborative recommendations in e-commerce,\u201d Expert \r\nSystems with Applications, vol. 26, pp. 233\u2013246, 2004. \r\n[13] Y. H. Cho, S. K. Park, D. H. Ahn, and J. K. Kim, \u201cCollaborative \r\nRecommendations using Adjusted Product Hierarchy: Methodology and \r\nEvaluation,\u201d Journal of the Korean Operations Research and \r\nManagement Science Society, vol. 29, no. 2, pp. 59\u201375, 2004. \r\n[14] J. K. Kim, D. H. Ahn, and Y. H. Cho, \u201cA Personalized Recommender \r\nSystem, WebCF-PT: A Collaborative Filtering using Web Mining and \r\nProduct Taxonomy,\u201d Asia Pacific Journal of Information Systems, vol. 15, \r\nno. 1, pp. 63\u201379, 2005. \r\n[15] D. Kim, and B. -J. Yum, \u201cCollaborative filtering based on iterative \r\nprincipal component analysis,\u201d Expert Systems with Applications, vol. 28, \r\nno. 4, pp. 823~830, 2005. \r\n[16] G. Adomavicius, and A. Tuzhilin, \u201cToward the next generation of \r\nrecommender systems: a survey of the state-of-the-art and possible \r\nextensions,\u201d IEEE Transactions on Knowledge and Data Engineering, \r\nvol. 17, no. 6, pp. 734\u2013749, 2005. \r\n[17] K. Kim, and. B. Kim, \u201cProduct Recommender System for Online \r\nShopping Malls using Data Mining Techniques,\u201d Journal of Intelligence \r\nand Information Systems, vol.11, no.1, pp. 191~205, 2005. \r\n[18] H. C. Ahn, I. Han, and K. Kim, \u201cThe Product Recommender System \r\nCombining Association Rules and Classification Models: The Case of G \r\nInternet Shopping Mall,\u201d Information Systems Review, vol.8, no.1, pp. \r\n181~201, 2006. \r\n[19] K. Kim, and H. Ahn, \u201cCollaborative filtering with a user-item matrix \r\nreduction technique for recommender systems,\u201d International Journal of \r\nElectronic Commerce, vol. 16, no. 1, pp. 107\u2013128, 2011. \r\n[20] M. Papagelis, D. Plexousakis, and T. Kutsuras, \u201cAlleviating the sparsity \r\nproblem of collaborative filtering using trust inferences,\u201d in iTrust, \r\nSpringer-Verlag, 2005, pp. 224\u2013239. \r\n[21] L. Breiman, \u201cHeuristics of instability in model selection,\u201d in Technical \r\nReport, Statistics Department, University of California at Berkeley, 1994. \r\n[22] L. Breiman, \u201cBagging predictors,\u201d Machine Learning, vol. 24, no. 2, pp. \r\n123\u2013140, 1996. \r\n[23] R. Tibshirani, and K. Knight, \u201cModel search and inference by bootstrap \r\n\u201cbumping\u201d,\u201d in Technical Report, University of Toronto, 1995. \r\n[24] T. Heskes, \u201cBalancing between bagging and bumping,\u201d in Advances in \r\nNeural Information Processing Systems, Cambridge, MIT Press, 1996, pp. \r\n466\u2013472. \r\n[25] Y. Lee, and S. Kwak, \u201cA study on training ensembles of neural networks: \r\na case of stock price prediction,\u201d Journal of Intelligence and Information \r\nSystems, vol. 5, no. 1, pp. 95\u2013101, 1999. ","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 82, 2013"}