Forecasting the Return Rate of Products in the Textile Industry through Feed Forward Neural Networks

Demir, Florian Tengiz (2024) Forecasting the Return Rate of Products in the Textile Industry through Feed Forward Neural Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The clothing industry appears as a sector that has existed for centuries, developed every year and will never end. The biggest losses in this sector are the cost of returned products to companies and the transportation and storage costs of products. Considering real-life conditions, less return means less waste, and less waste means more profit for companies. To best address these challenges and obtain objective, scientific results, this study introduces a new approach to predicting return rates using Feed-Forward Neural Networks, a new type of machine learning technique. In this study, to achieve optimal results in unbalanced data sets, samples in the minority class were increased with the Synthetic Minority Oversampling Technique, hyperparameter optimization was performed with RandomSearchCV, and a Feedforward Neural Networks model was established with an accuracy rate of 88.7% to estimate the return rates.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Uncontrolled Keywords:	Feed-Forward Neural Networks; SMOTE; Predicting Return Rates; Hyperparameter Optimization
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	02 Sep 2025 10:02
Last Modified:	02 Sep 2025 10:02
URI:	https://norma.ncirl.ie/id/eprint/8690

Actions (login required)

View Item