Final Year Project · Applied Machine Learning
Personalized Movie Recommendation System
University of London · BSc Computer Science, Machine Learning and AI · CM3070
A solo final-year project. I compared five recommendation models, from an SVD baseline to a PyTorch autoencoder and a from-scratch Restricted Boltzmann Machine, then blended the two most useful into a weighted hybrid and tested it with 10 people.
How the work ran
From data preparation to user testing. Open a stage to see the method.
Preparation
The five models
Pick a model to see its approach, test metrics and tradeoffs.
Methodology caveats
What worked
What users challenged
What changed
Limitations
Future work
Ideas from the report’s future-work section. None of these were built.