Tools
Tools
Salim Badhusha, Shafik Rahman (2024) Personalized Fashion Recommendations in Dynamic Fashion Trends. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
This study examines the complexities in using RecBole sequential algorithms in suggesting fashion goods for H&M users, while acknowledging the distinct difficulties presented by the fashion industry’s cyclical trends. The research thoroughly covers the crucial stages of data preparation, model development, training, and filtering, assuring compliance with industry norms and adhering to data integrity and ethics. An important addition is the establishment of a structured process for making recommendations in multiple stages, specifically designed to include the time-related aspects that are inherent in fashion data. By using a large dataset from H&M, thorough testing demonstrates the intricate performance of RecBole sequential algorithms. The study examines how well the algorithms perform in suggesting things in the ever-changing fashion environment of H&M. Different models using two main sequential algorithms, GRU4Rec and Bert4Rec were built and evaluated.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Cosgrave, Noel UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Fashion Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 05 Jun 2025 13:33 |
| Last Modified: | 05 Jun 2025 13:33 |
| URI: | https://norma.ncirl.ie/id/eprint/7760 |
Actions (login required)
 |
View Item |