Skip to content
← All projects
Recommendation SystemsPrototype

Movie Recommender - NLP Content-Based Engine

A content-based recommender that suggests 5 similar movies from a selected title using NLP tag vectors and cosine similarity over a 4,806-film dataset.

Overview

A lightweight recommendation-system prototype that suggests similar movies using NLP tag vectors and cosine similarity.

A secondary project unless it gets a polished deployment, stronger README, and cleaner analysis story.

Impact

  • Precomputed a 4,806 x 4,806 similarity matrix with a simple Streamlit UI for title selection.
  • A quick-win project once it gets a reproducible notebook, posters, README, and deployment.
  • Intentionally listed as a prototype, not a flagship project.

What it shows

  • Vector-space recommendation basics.
  • Simple Streamlit productization for an ML prototype.
  • Precomputed similarity lookup over a medium-sized movie catalog.

Demo plan

  • Deploy as a Streamlit or Hugging Face Space quick demo.
  • Add poster thumbnails only if the asset source is stable and allowed.

Stack