Tools
Tools
Rajeshirke, Shubham Sunil (2023) Multi-objective Recommender System for E-Commerce using Singular Value Decomposition (SVD) Matrix Factorization Technique. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (775kB) | Preview |
Preview |
PDF (Configuration manual)
Download (880kB) | Preview |
Abstract
In the current digital landscape, personalized recommendations are the key for enhancing user experience across different online platforms. In this research a Recommender system is built using advanced matrix factorization techniques. Leveraging the user behavior data this system will generate 3 recommendations as the output that will align with the users’ preferences. After thorough evaluation, the implemented system achieved impressive precision (0.92), indicating accurate item recommendations and Recall (0.64) indicates that the system captures substantial portion of relevant items. The balanced F1-score (0.68) confirms that the system does an excellent job in both accuracy and remembering relevant items. Also, the hit rate (1) shows that the system will be able to engage users consistently with the recommended items. However, the coverage metric (0.36) showcase that there is still room for improvement in the system in terms of exploring more items so that a wider range of user preferences can be catered for. Future directions include exploring more hybrid approaches, making use of more contextual data, and working on the scalability part to address larger datasets. This study highlights the potential of matrix factorization technique in the Recommender system. It shows that factors like engagement, diversification of products and scalability should also be considered for evaluation. The outcome of this research will give the new ecommerce brands a fresh perspective and motivate them to implement an advanced recommender system which will help the brand in enhancing user satisfaction and engagement across online platforms.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Chikkankod, Arjun UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Electronic Commerce |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 28 Dec 2024 15:07 |
| Last Modified: | 28 Dec 2024 15:07 |
| URI: | https://norma.ncirl.ie/id/eprint/7253 |
Actions (login required)
 |
View Item |