"I've already finished watching my favourite movie.... Now what?" I have often found myself in this situation.... I'm sure you have too, and how annoying it is to find something that will interest me! We don't always have as much time as we'd like, so it's always good to watch content that matches what we like.
That's why I decided to create a film recommender, so that I don't have to waste time searching manually and still choose something I don't really like!
✏️ - Thanks to a Tf-idf matrix and other techniques it is possible to obtain the similarity between a given movie and the rest of movies.
🛠 - Jupyter Notebooks have been used because of their ease of use and convenience for exploratory data analysis, along with the Python language.
🚩 - The main challenge was to understand how to find the similarity between a given movie and the rest of the movies, because not all the movies well rated may be of my interest (e.g. Toy Story is very well rated. However, that doesn't mean I'd be interested in it, but that it's a very beloved movie by everyone).
There is no executable. The notebook with the movie recommender system can be found in the "src" folder.
- Improving the recommendations by modifying some of the parameters.
- Adding the genres to improve the actual recommendation system.
- Adding the option of getting recommendations based on the genre.
- Including metadata and tags data from the other CSV to improve the recommendations.