Document Type

Honors Thesis

Abstract

This study explores the effectiveness of a hybrid recommendation system for e-commerce by integrating content-based, collaborative, and popularity-based models. Traditional individual algorithms have inherent limitations, such as handling new users or items data sparsity and ensuring relevance and diversity in suggestions. The hybrid model seeks to overcome these challenges by leveraging the strengths of all three methods, thus potentially offering more precise, personalized product suggestions. The performance of each model and its integration into a hybrid system are evaluated through logistic regression analysis. Initial results indicate that the hybrid system significantly outperforms the individual models in terms of accuracy and user satisfaction. This research underscores the potential of hybrid recommendation systems to enhance user experience and support businesses in optimizing their online platforms. Importantly, the study provides practical insights for e-commerce enterprises aiming to refine their customer interaction strategies, demonstrating the real-world relevance of the research.

Disciplines

Computer Engineering

Publication Date

5-2024

Language

English

Faculty Mentor of Honors Project

Christopher Conly

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.