A Hybrid Machine Learning Approach for Improving E-Commerce Recommendation Systems Using Python
DOI:
https://doi.org/10.32628/IJSRST251263Keywords:
Recommendation System, Content-Based Filtering, Collaborative Filtering, Hybrid Filtering, Python, Tensorflow, Lightfm, Scikit, Matplotlib, Evaluation MetricsAbstract
This paper presents a novel hybrid recommendation system approach that combines collaborative filtering, content-based filtering, and deep learning techniques to improve recommendation accuracy and overcome common challenges in e-commerce platforms. Our proposed model addresses key limitations such as the cold-start problem, data sparsity, and overspecialization by leveraging the complementary strengths of multiple recommendation strategies. Implementation using Python demonstrates significant performance improvements across various evaluation metrics compared to standalone methods, providing a practical framework for e-commerce recommendation systems.
📊 Article Downloads
References
BluePi. (n.d.). Hybrid recommender systems. https://bluepiit.com/blog/hybrid-recommender-systems
Patil, A. P., & Patil, V. M. (n.d.). Hybrid Recommender System Based on Collaborative Filtering and Content Based Filtering. International Journal of Advanced Engineering and Research Development. http://www.ejournal.aessangli.in/ASEEJournals/CE116.pdf
Deldjoo, Y., Elahi, M., Cremonesi, P., & Quadrana, M. (2020). Recommender systems leveraging content features of items: A literature survey. Expert Systems with Applications, 137, 113009. https://doi.org/10.1016/j.eswa.2019.07.018 DOI: https://doi.org/10.1016/j.eswa.2019.07.018
AmanX. (2023, June 5). Hybrid Recommendation System using Python. https://amanxai.com/2023/06/05/hybrid-recommendation-system-using-python/
Burke, R. (2019). Hybrid Recommender Systems: Survey and Experiments. arXiv. https://arxiv.org/abs/1901.03888
Liu, Y., Jin, X., Wang, Y., Li, Z., & Wang, X. (2024). A deep hybrid model for recommendation systems using graph neural networks. Scientific Reports, 14, 11321. https://doi.org/10.1038/s41598-024-79011-z DOI: https://doi.org/10.1038/s41598-024-79011-z
Hug, N. (n.d.). scikit-surprise: A Python library for recommender systems. PyPI. https://pypi.org/project/scikit-surprise/
Lyst. (n.d.). LightFM Documentation. https://making.lyst.com/lightfm/docs/home.html
Fernández-Tobías, I., Cantador, I., Kaminskas, M., & Ricci, F. (2012). A survey of hybrid recommender systems: Experiments and performance evaluation. http://pzs.dstu.dp.ua/DataMining/recom/bibl/Hybrid_Recommender_Systems_Survey_and_Experiments.pdf
Ben Frederickson. (n.d.). Implicit: Fast Python Collaborative Filtering for Implicit Datasets. PyPI. https://pypi.org/project/implicit/
MarketSy.ai. (2023). Hybrid Recommender Systems: A Beginner’s Guide. https://marketsy.ai/blog/hybrid-recommender-systems-beginners-guide
Brusilovsky, P. (n.d.). Hybrid Recommender Systems Summary. https://sites.pitt.edu/~peterb/3954-061/hybrid%20summary.doc
Patidar, A., & Raj, P. (2023). Enhanced Hybrid Recommendation System Using Machine Learning Algorithms. International Journal of Intelligent Systems and Applications in Engineering (IJISAE), 11(4), 2241–2247. https://www.ijisae.org/index.php/IJISAE/article/view/5715
Papers with Code. (n.d.). Improvement of E-Commerce Recommendation System Using Machine Learning Algorithms. https://paperswithcode.com/paper/improvement-of-e-commerce-recommendation
Zhang, S., Yao, L., Sun, A., & Tay, Y. (2020). Deep learning based recommender system: A survey and new perspectives. arXiv. https://arxiv.org/abs/2009.09748 DOI: https://doi.org/10.1145/3285029
Evidently AI. (n.d.). Evaluating Recommender Systems with Ranking Metrics. https://www.evidentlyai.com/ranking-metrics/evaluating-recommender-systems
Akshay, S. (2019, April 8). Evaluation metrics for recommendation systems – An overview. Towards Data Science. https://towardsdatascience.com/evaluation-metrics-for-recommendation-systems-an-overview-71290690ecba
Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4), 331-370. https://doi.org/10.1023/A:1021240730564 DOI: https://doi.org/10.1023/A:1021240730564
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
https://creativecommons.org/licenses/by/4.0
