Increase Robustness SDAE with Imputing Missing Value To Eliminate Users Sparse Data in Case E-Commerce Recommender System
Keywords:recommender system, collaborative, deep SDAE, deep learning, sparse data, users sparse
Online shopping needs a computer machine to serve product information sale for customer or buyer candidate. Relevant information served by ecommerce system famous called recommender system. The successful to applied, it will have impact to increase of marketing target achievement. The character of information served by recommender system have to be special, personalized, relevant and fit according customer profiling. There are four kind of recommender system model, however there is one model that was successful to be applied in real ecommerce industry that popular named collaborative filtering. Collaborative filtering approach need a record users or customers activity in the past to generate recommendation for example rating record, purchasing record, testimony about product. The majority collaborative filtering approaches rely on rating as fundamental computation to calculate product recommendation. However, just a little number of consumers who willing give rating for products less than a percent, according to several convince datasets such MovieLens. This problem causes of sparse product rating that will impact to product recommendation accuracy level. Sometime, in extreme condition, it is impossible to generate product recommendation. Several efforts have been conducting to handle product sparse rating, however they fail to generate product recommendation accurately when face extreme sparse data, such as matrix factorization family include SVD, NMF, SVD++. This research aims to develop a model to handle users sparse rating involving deep SDAE. One of the efforts to produce better output in handling this data sparse, our strategy is to imputing missing value by statistical method so that the input in SDAE is closer to the feasibility of data that is not too sparse. According to our experiment involve deep learning, TensorFlow, MovieLens datasets, evaluation method by root mean square error (RMSE), our approach involves reducing input missing value could address users sparse rating and increase robustness over several existing approach.
 G. R and G. J, â€œGet the right mix of bricks and clicks,â€ Harv. Bus. Rev., 2000.
 Hanafi, N. Suryana, and A. Sammad, â€œEvaluation of e-Service Quality, Perceived Value on Customer Satisfaction and Customer Loyalty: A Study in Indonesia.â€ Medwell Journal, pp. 1892â€“1900, 2017.
 C. A. Gomez-uribe and N. Hunt, â€œThe Netflix Recommender System : Algorithms , Business Value ,â€ vol. 6, no. 4, 2015.
 J. Davidson and B. Liebald, â€œThe YouTube video recommendation system The YouTube Video Recommendation System,â€ no. August, 2014.
 J. Ben Schafer, J. Konstan, and J. Riedl, â€œE-commerce recommendation applications,â€ Appl. Data Min. to Electron. â€¦, pp. 115â€“153, 2001.
 Hanafi, N. Suryana, and A. Sammad, â€œAN UNDERSTANDING AND APPROACH SOLUTION FOR COLD START PROBLEM ASSOCIATED WITH RECOMMENDER SYSTEM : A LITERATURE REVIEW,â€ J. Theor. Appl. Inf. Technol., vol. 96, no. 09, 2018.
 L. Candillier, K. Jack, F. Fessant, and F. Meyer, Recommender systems, vol. 40, no. 3. 1997.
 E. Ã‡ano and M. Morisio, â€œHybrid recommender systems: A systematic literature review,â€ Intell. Data Anal., vol. 21, no. 6, pp. 1487â€“1524, 2017.
 F. M. Harper and J. A. Konstan, â€œThe MovieLens Datasets: History and Context,â€ ACM Trans. Interact. Intell. Syst., vol. 5, no. 4, p. 19:1--19:19, 2015.
 X. Wang and Y. Wang, â€œImproving Content-based and Hybrid Music Recommendation using Deep Learning,â€ pp. 627â€“636.
 S. Jaradat, â€œDeep Cross-Domain Fashion Recommendation,â€ Proc. Elev. ACM Conf. Recomm. Syst. - RecSys â€™17, pp. 407â€“410, 2017.
 K. Park, J. Lee, and J. Choi, â€œDeep Neural Networks for News Recommendations,â€ CIKMâ€™17, Novemb. 6-10, 2017, Singapore, 2017.
 P. Covington, J. Adams, and E. Sargin, â€œDeep Neural Networks for YouTube Recommendations,â€ Proc. 10th ACM Conf. Recomm. Syst. - RecSys â€™16, pp. 191â€“198, 2016.
 Y. Koren, R. Bell, and C. Volinsky, â€œMatrix Factorization Techniques for Recommender Systems,â€ pp. 42â€“49, 2009.
 A. van den Oord, S. Dieleman, and B. Schrauwen, â€œDeep Content-Based Music Recommendation,â€ pp. 2643â€“2651, 2013.
 Hanafi, N. Suryana, and abd samad hasan Basari, â€œHYBRIDIZATION APPROACH TO ELIMINATE SPARSE DATA BASED ON NONNEGATIVE MATRIX FACTORIZATION & DEEP LEARNING,â€ J. Theor. Appl. Inf. Technol., vol. 96, no. 14, pp. 4502â€“4512, 2018.
 R. Salakhutdinov and A. Mnih, â€œProbabilistic Matrix Factorization.,â€ Proc. Adv. Neural Inf. Process. Syst. 20 (NIPS 07), pp. 1257â€“1264, 2007.
 C. Wang and D. M. Blei, â€œCollaborative topic modeling for recommending scientific articles,â€ Proc. 17th ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD â€™11, p. 448, 2011.
 S. Zhang, W. Wang, J. Ford, and F. Makedon, â€œLearning from Incomplete Ratings Using Non-negative Matrix Factorization,â€ Proc. 2006 SIAM Int. Conf. Data Min., pp. 549â€“553, 2006.
 H. Wang and D. Yeung, â€œCollaborative Deep Learning for Recommender Systems arXiv : 1409 . 2944v1 [ cs . LG ] 10 Sep 2014,â€ no. July 2015, 2014.
 B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, â€œIncremental Singular Value Decomposition Algorithms for Highly Scalable Recommender Systems,â€ Am. Lab., vol. 37, no. 10, p. 4, 2005.
 U. Ocepek, J. Rugelj, and Z. Bosni??, â€œImproving matrix factorization recommendations for examples in cold start,â€ Expert Syst. Appl., vol. 42, no. 19, pp. 6784â€“6794, 2015.
 C. C. Chen, Y. H. Wan, M. C. Chung, and Y. C. Sun, â€œAn effective recommendation method for cold start new users using trust and distrust networks,â€ Inf. Sci. (Ny)., vol. 224, pp. 19â€“36, 2013.
 A. Gunawardana, â€œA Survey of Accuracy Evaluation Metrics of Recommendation Tasks,â€ vol. 10, pp. 2935â€“2962, 2009.
View Full Article:
How to Cite
LicenseAuthors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under aÂ Creative Commons Attribution Licensethat allows others to share the work with an acknowledgement of the work''s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal''s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeÂ The Effect of Open Access).