International Journal of Scientific & Technology Research

IJSTR@Facebook IJSTR@Twitter IJSTR@Linkedin
Home About Us Scope Editorial Board Blog/Latest News Contact Us

IJSTR >> Volume 9 - Issue 1, January 2020 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

E-Commerce Recommender System Using Product Data

[Full Text]



Rajesh Kumar E, Kakani Jyotsna, Keerthana Ganta, Ramya Sirisha Nori



Content-based filtering, Convolutional neural networks, Inverse Document Frequency, One hot encoding, Recommender systems, Term Frequency, Word2Vec



In previous days, before buying a product, people used to get suggestions from our close friends, family or people known. This is the basic idea of recommender systems. Recommender systems work with the same idea of predicting a product that a customer may like to buy. Recommender systems can be used in different areas to recommend products such as books, apparel, accessories, movies according to the items viewed. A recommender system is a system that helps to expect and recommend similar products to the given input of the product. In many online e-commerce websites like Amazon, Myntra and other sites, one can find sections like “recommended for you”, “products related to this item”, “customers also viewed” when a person views certain product. These are the recommended sections.



[1] Guan Shengfang, “Apparel Recommendation System Evolution, An Empirical Review”, International Journal of Clothing Science and Technology, Vol. 28 Iss 6 pp, 2016.
[2] Richa Sharma and Rahul Singh, “Evolution of recommender systems”, Indian Journal of Science and Technology, Vol 9(20), May 2016.
[3] Shah Khusro, Zafar Ali and Irfan Ullah, “Recommendation systems issues and challenges”, Information Science and Applications (ICISA) 2016.
[4] Brent Smith and Greg Linden, “Two Decades of Recommender systems at amazon”, in IEEE Computer Society, 2017.
[5] Zhang, J.-D., Chow, C.-Y ”SEMAX: Multi-task Learning for Improving Recommendations” ,IEEE Access,2018.
[6] R. R. Salakhutdinov,”Probabilistic matrix factorization”, in Proc. NIPS, 2008, pp. 1257–1264.
[7] S.Zhang, “enabling kernel-based attribute aware matrix factorization for rating prediction”, IEEE Trans. Knowl. Data Eng., vol. 29, no. 4, pp. 798–812, Apr. 2017.
[8] P.Covington, “Deep learning based recommender system: A survey and new perspectives”, [Online]. Available: https://arxiv.org/abs/1707.07435
[9] Wang, H., Wang, N., Yeung, “Collaborative Deep Learning for Recommender Systems”. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’2015.
[10] Kedar Potdar, “A Comparative Study of Categorical Variable Encoding Techniques for Neural Network Classifiers”, International Journal of Computer Applications 175(4):7-9 • October 2017.
[11] D. Kim, C. park, “Convolutional matrix factorization for document context-aware recommendation”, in Proc. ACM RecSys, pp. 233–240, 2016.
[12] R. Catherine and W. Cohen, ``TransNets: Learning to transform for recommendation,'' in Proc. ACM RecSys, pp. 288–296, 2017.
[13] D. Bahdanau, K. Cho, and Y. Bengio ”Neural machine translation by jointly learning to align and translate'', in Proc. ICLR, 2015, pp. 1–15.
[14] J. Tang, H. Gao, X. Hu, and H. Liu, ``Context-aware review helpfulness rating prediction'', in Proc. ACM RecSys, 2013, pp. 1–8.