Beyond Accuracy: A Comparative Analysis of Recommendation Models Incorporating Quantitative and Qualitative Evaluation

Vijayakumar Nair, Visakh (2024) Beyond Accuracy: A Comparative Analysis of Recommendation Models Incorporating Quantitative and Qualitative Evaluation. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (875kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Recommendation systems plays a vital role in content delivery, user accusation and user retention in various domains. This research develops and compares two recommendation models – embedding-based ranking model and a behavioural pattern learning model – using data from the Findups Daily news application. This study evaluates these models on quantitative metrics and evaluation criteria analysis such as diversity, scalability and cold-start problem. This research underscores the importance of aligning recommendation systems with application-specific needs to optimize user engagement and satisfaction.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Uncontrolled Keywords:	Recommendation system; Content-Based Recommendation; Behavioural Analysis; Embedding; Recommendation Ranking
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	20 Jun 2025 11:04
Last Modified:	20 Jun 2025 11:04
URI:	https://norma.ncirl.ie/id/eprint/7972

Actions (login required)

View Item