Downloads · 30 days
0
movie__recommender
vinetran/movie__recommender
movie__recommender is a machine learning model from vinetran. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
The project aims to build a movie recommender based on movie attributes (title, genre, age certification, production country, actors, imdb score, imdb number of votes, tmdb popularity, tmdb score, duration and descrip…
Access
Public
Updated Jun 1, 2023
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.joblib1.3 GB · 97%
At a glance
- Access
- Public
- Created
- May 31, 2023
- Updated
- Jun 1, 2023
- SHA
- 2aca6882
Model card
From the Hugging Face model README
Building Movie Recommender Project
The project aims to build a movie recommender based on movie attributes (title, genre, age certification, production country, actors, imdb score, imdb number of votes, tmdb popularity, tmdb score, duration and description/summary)
[Project data can be retrieved here] (https://www.kaggle.com/datasets/dgoenrique/netflix-movies-and-tv-shows). The data contains over 19,000 movies titles collected from different movie platforms: Netflix, Amazon prime movies, AppleTV, Disney+, HBO max and Paramount.
Recommendation is based on the similarity between movies which consists of 2 parts: similarity of the summaries and that of the remaining characteristics. For the first one, an autoencoders model was implemented. Cosine similarity was called for calculating similarites. The final similarity matrix was recuperated by taking average of these 2 similarity scores.
Finally, the movie recommender was deployed as a streamlit application. [The application can be reached here] (https://vinetran-movie--recommender-app-tn7gmf.streamlit.app/)
- Created
- May 31, 2023
- Updated
- Jun 1, 2023