I am preparing my Bachelor final thesis in computer engineering. I am currently planning out the work. My idea is to compare traditional approaches to building recommender systems to Graph Neural Network based approaches. The plan so far is to use the Movie Lens 100k dataset, which contains data on users, movies, and user-movie ratings. The task of the recommender system would be to predict the missing ratings for user A and recommend movies based on that (say top 5 highest predictions). I would present three approaches to this task:
- Traditional content-based filtering approach
- Traditional collaborative filtering based approach
- Graph Neural Network
Given this very general outline, would you guys say that this seems like a good project idea? The movie lens dataset seems to be quite popular when it comes to experimenting with GNN's, but you can suggest a better dataset for this setup.
Your project idea to compare traditional approaches to building recommender systems with Graph Neural Network (GNN) based approaches is solid and aligns well with the current trends in the field. Using the MovieLens 100k dataset is a good choice, especially for its popularity in recommender system research. However, your choice of dataset ultimately depends on your research questions and the specific aspects you want to investigate.
Here are a few considerations and suggestions:
- Badges
- Science topic