Improving the Accuracy of E-commerce Recommendation Systems using Matrix Factorization Method: A Case Study of Amazon
DOI:
https://doi.org/10.54097/s9w6tp04Keywords:
personalized recommendation, matrix factorization, e-commerce, collaborative filtering, Amazon.Abstract
Personalized recommendation systems are becoming an essential feature of online shopping platforms, where an abundance of products and information can be overwhelming to users. These systems play a pivotal role in enriching user experiences by suggesting relevant products based on users' past behavior and preferences. However, accurate recommendations present several challenges, including data sparsity, cold start issues for new users or products and recognizing intricate patterns across large datasets. This research seeks to improve Amazon's e-commerce recommendation system using matrix factorization methods to overcome some of its challenges. Matrix factorization dissects user/item interactions into lower dimensional latent factors which represent user and item preferences. At Matrix Factorization Methods Inc, the author studies their effectiveness in increasing recommendation accuracy while managing data sparsity and cold start issues in real-world Amazon data collection, preprocessing and various matrix factorization algorithms implementation and evaluation will be carried out and compared against baseline approaches to demonstrate their potential in increasing recommendation accuracy while meeting challenges posed by e-commerce recommendation systems.
Downloads
References
Desrosiers, C., & Karypis, G. (2011). A comprehensive survey of neighborhood-based recommendation methods. In Recommender systems handbook (pp. 107-144). Springer, Boston, MA.
Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30-37.
Schein, A. I., Popescul, A., Ungar, L. H., & Pennock, D. M. (2002). Methods and metrics for cold-start recommendations. In Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 253-260).
Paterek, A. (2007). Improving regularized singular value decomposition for collaborative filtering. In Proceedings of KDD Cup and Workshop (Vol. 2007, No. 1, pp. 5-8).
Lee, Y., & Lee, Y. K. (2018). Collaborative filtering with matrix factorization: A study on its acceleration. Applied Sciences, 8(3), 320.
Bobadilla, J., Ortega, F., Hernando, A., & Gutiérrez, A. (2013). Recommender systems survey. Knowledge-Based Systems, 46, 109-132.
Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In The adaptive web (pp. 325-341). Springer, Berlin, Heidelberg.
Gómez-Valverde, J. J., Yáñez-Marquina, L., Martínez-Béjar, R., & Rodríguez-García, M. Á. (2019). Improving collaborative filtering in recommender systems using item augmentation. Information Sciences, 498, 58-74.
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., & Chua, T. S. (2017). Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web (pp. 173-182).
Lops, P., De Gemmis, M., & Semeraro, G. (2011). Content-based recommender systems: State of the art and trends. In Recommender Systems Handbook (pp. 73-105). Springer, Boston, MA.
Adomavicius, G., & Tuzhilin, A. (2008). Context-aware recommender systems. In Proceedings of the 2008 ACM Conference on Recommender Systems (pp. 275-278). ACM.
Ma, H., Yang, H., Lyu, M. R., & King, I. (2008). Sorec: social recommendation using probabilistic matrix factorization. In Proceedings of the 17th ACM Conference on Information and Knowledge Management (pp. 931-940). ACM.
Baltrunas, L., Ludwig, B., & Ricci, F. (2011). Contextual recommendation diversification. In Proceedings of the 5th ACM Conference on Recommender Systems (pp. 237-240). ACM.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
