AI Prompt for Building the Movie Recommendation System

In this tutorial, we build a complete end-to-end Movie Recommendation System using Machine Learning. The entire project including backend APIs, ML recommendation engine, and frontend UI can be generated using an AI coding assistant by simply using the prompt below. You can copy the prompt and paste it into any AI coding tool to automatically generate the full project.

You are a senior AI engineer and full-stack developer.

Create a complete End-to-End Movie Recommendation System using Machine Learning.

IMPORTANT REQUIREMENTS

1. Do NOT use any paid APIs or third-party AI services.
2. The recommendation engine must be built using pure Machine Learning.
3. The system must run on CPU only (no GPU required).
4. All code must be production-ready and modular.

TECH STACK

Backend

* Python
* FastAPI
* Scikit-learn
* Pandas
* NumPy

Frontend

* React.js
* Axios
* Tailwind CSS (optional)

Dataset

Use the MovieLens dataset.

PROJECT STRUCTURE

Create a complete folder structure:

movie-recommendation-system

backend/

app/
main.py
recommendation.py
preprocessing.py
model.py
utils.py

data/
movies.csv
ratings.csv

requirements.txt


frontend/

src/

components/
SearchMovie.jsx
MovieCard.jsx
Recommendations.jsx

pages/
Home.jsx

services/
api.js

App.js
index.js
package.json


BACKEND FEATURES

1. Load MovieLens dataset
2. Clean and preprocess the data
3. Implement Content Based Recommendation using:

   * TF-IDF
   * Cosine Similarity

4. Create a recommendation engine that returns top 10 similar movies


API ENDPOINTS

GET /movies

Returns movie list


GET /search?query=movie_name

Search movies


GET /recommend/{movie_id}

Returns top 10 recommended movies


ML LOGIC

Steps

1. Merge movies and ratings dataset
2. Create movie metadata features (genres + tags)
3. Convert text to vectors using TF-IDF
4. Calculate similarity using cosine similarity
5. Store similarity matrix


FRONTEND FEATURES

1. Movie search bar
2. Movie cards UI
3. Recommendation list
4. Movie poster
5. Responsive UI


FRONTEND FLOW

User searches movie

↓

Frontend calls backend API

↓

Backend returns recommendations

↓

Frontend displays similar movies


BONUS FEATURES

Add these advanced features

1. Trending movies section
2. Movie poster integration using public dataset
3. Loading spinner
4. Error handling
5. Clean UI


DELIVERABLES

1. Complete backend code
2. Complete frontend code
3. ML model implementation
4. API integration
5. Instructions to run the project locally


OUTPUT FORMAT

Provide the code step by step

1. Backend setup
2. ML model code
3. API endpoints
4. Frontend setup
5. React components
6. Integration
7. Run instructions


Ensure the project runs locally with simple commands

Backend

uvicorn main:app --reload


Frontend

npm start