Date of Graduation
5-2025
Document Type
Thesis
Degree Name
Bachelor of Science in Data Science
Degree Level
Undergraduate
Department
Data Science
Advisor/Mentor
Schubert, Karl D.
Committee Member
Samantapudi, Rama Krishna Raju
Second Committee Member
Shipp, Justin
Abstract
In e-commerce, enhancing Natural Language Processing (NLP) models' understanding of search queries can significantly improve product relevance and overall user experience. Even with advancements in the search space, being able to accurately classify items for shopping queries remains challenging due to noisy data, ambiguous user intent, and the wide range of products available. This research aims to explore different strategies implementing and improving queryproduct classification. The methodology involves a comparative assessment of various model performances for multi-class product classification, data augmentation techniques for handling class-imbalances, and the design of the User Interface (UI) of a Human-In-The-Loop (HITL) Machine Learning (ML) system. The hope is that this approach will lead to enhancements in query-product matching, with direct implications for better search results and product recommendations
Keywords
Data Science; E-commerce; Machine Learning
Citation
Cordes, C. G. (2025). Understanding and Evaluating Multi-class Product Classification Methods for E-commerce. Data Science Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/dtscuht/21
