Project Abstract

With the ever-growing scale of movie production, it is more important than ever for effective recommendation systems to help users discover new and emerging content. As a result of this project, viewers can spend more time watching and less time deliberating over an activity that the average person already dedicates four hours a day to. The primary aim of this project was to develop a fully functioning web application that provides movie recommendations with a higher user satisfaction score than those offered by leading video streaming platforms. This was accomplished by implementing three core recommendation algorithms, embedding them within the backend software, and conducting a user study to assess both the efficiency of the user interface and the effectiveness of the recommendations. The frontend user interface was developed using React, the backend using Django, and Python for the machine learning algorithms. All of these technologies were combined to create the full development stack. Upon completion, the project successfully met its objectives, resulting in a web application that delivered higher satisfaction ratings than the industry standard. The system allows users to view detailed information about movies, receive personalized recommendations through all three algorithms, and manage their accounts through a fully functional user system. This project made it more apparent to me than ever how essential recommendation systems are and how they could be far more refined in practically every other field. With the general scale of the internet ever-increasing, this field will continue to see development and improvements that will provide great benefit to individuals, businesses and the world.

Keywords: Machine Learning, Web Application, Recommendation Algorithms

 Conference Details

Session: A

Location: Sir Stanley Clarke Auditorium at 11:00 13:00

Markers: Casey Hopkins, Matt Roach

Course: BSc Software Engineering 3yr FT

Future Plans: I’m continuing studies