Advertisement

Product Prediction and Recommendation in E-Commerce Using Collaborative Filtering and Artificial Neural Networks: A Hybrid Approach

  • Soma BandyopadhyayEmail author
  • S. S. Thakur
Chapter
  • 393 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 784)

Abstract

In modern society, online purchasing using popular website has become a new trend and the reason beyond it is E-commerce business which has grown rapidly. These E-commerce systems cannot provide one to one recommendation, due to this reason customers are not able to decide about products, and they may purchase. The main concern of this work is to increase the product sales, by keeping in mind that at least our system may satisfy the needs of regular customers. This paper presents an innovative approach using collaborative filtering (CF) and artificial neural networks (ANN) to generate predictions which may help students to use these predictions for their future requirements. In this work, buying pattern of the students who are going to face campus interviews has been taken into consideration. In addition to this, buying patterns of the alumni for luxurious items was also considered. This recommendation has been done for the products, and the results generated by our approach are quite interesting.

Keywords

Predictions Recommender system E-Commerce Collaborative filtering Nearest neighbors Artificial neural networks 

References

  1. 1.
    Burke, R.: Hybrid recommender systems: survey and experiments. User Model. User-Adap. Int. 12, 331–370 (2002)CrossRefGoogle Scholar
  2. 2.
    McNee, S., Riedl, J., Konstan, J.: Being accurate is not enough: how accuracy metrics have hurt recommender systems. In: 24th International Conference Human Factors in Computing Systems, Montréal, Canada, pp. 1097–1101 (2006)Google Scholar
  3. 3.
    Cosley, D., Lam, S., Albert, I., Konstan, J., Riedl, J.: Is seeing believing?: how recommender system interfaces affect users’ opinions. In: SIGCHI Conference on Human Factors in Computing Systems, Ft. Lauderdale, FL, pp. 585–592 (2003)Google Scholar
  4. 4.
    Ziegler, C., McNee, S., Konstan, J., Lausen, G.: Improving recommendation lists through topic diversification. In: 14th International World Wide Web Conference, Chiba, Japan, pp. 22–32 (2005)Google Scholar
  5. 5.
    Huang, Z., Chung, W., Chen, H.: A graph model for E commerce recommender systems. J. Am. Soc. Inform. Sci. Technol. 55(3), 259–274 (2004)CrossRefGoogle Scholar
  6. 6.
    Liu, Z.B., Qu, W.Y., Li, H.T., Xie, C.S.: A hybrid collaborative filtering recommendation mechanism for P2P networks. Futur. Gener. Comput. Syst. 26(8), 1409–1417 (2010)CrossRefGoogle Scholar
  7. 7.
    Paul, D., Sarkar, S., Chelliah, M., Kalyan, C., Nadkarni, P.P.S.: Recommendation of high-quality representative reviews in E-commerce. In: Proceedings of the Eleventh ACM Conference on Recommender Systems, Como, Italy, pp 311–315 (2017)Google Scholar
  8. 8.
    Baha’addin, F.B.: Kurdistan engineering colleges and using of artificial neural network for knowledge representation in learning process. Int. J. Eng. Innov. Tech. 3(6), 292–300 (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.MCKV Institute of EngineeringHowrahIndia

Personalised recommendations