Dominion Akinrotimi
Back to Projects
Python TF-IDF Recommender systems Evaluation

Hybrid Movie Recommender: Plot Text + People

The problem: recommend films someone is likely to enjoy next, using only what's known about the films: what they're about and who made them. No viewing history is needed, so it works for new users and new titles.

What I built: a recommender over 28,932 films from the TMDB April 2024 export. It blends plot similarity with director and cast similarity, and I tested it fairly against random and most-popular baselines.

View the code on GitHub

Results

Bar chart: the hybrid recommender scores 0.333 genre overlap against 0.154 for random films

Average genre overlap between each film and its 10 recommendations, on 2,000 test films.

ModelShare genreGenre overlap
Random films43.9%0.154
Most popular films36.9%0.103
People only (director + cast)65.4%0.298
Plot only (TF-IDF)64.2%0.284
Hybrid71.0%0.333

The hybrid more than doubles random genre overlap and beats either signal on its own. Its picks have the catalogue's typical popularity, so it isn't just pushing blockbusters.

Because you watched Spirited Away: The Boy and the Heron, Princess Mononoke, Ponyo, My Neighbor Totoro, Howl's Moving Castle.

How I tested it

How it works

Limitations

This is a rebuild of an earlier version whose evaluation was a placeholder. The new version replaces it with the held-out test above.

Need an AI or machine learning system like this?

I build and deploy models that solve real problems, from clinical research to products in production.