🎥 Movie Recommendation System - "Le Cruise"

📋 Overview

This project was created as part of our training at Wild Code School. The goal was to design and implement a movie recommendation system for a local cinema in the Creuse region of France. The cinema sought to modernize its services by offering personalized movie suggestions to its customers via an online platform. This project serves as a foundational prototype for their ambitions.

---

🛠️ Technologies & Tools Used

• Data Analysis: Pandas, Matplotlib, Seaborn, Plotly
• Machine Learning: Scikit-learn
• Programming Language: Python
• Project Management: Trello, Miro

---

🎯 Goals & Objectives

1. Analyze a dataset of movies (IMDb and TMDB databases) to identify trends and insights:
   • Actors' popularity over time.
   • Evolution of movie runtimes.
   • Highest-rated movies and their characteristics.
2. Develop a movie recommendation engine using machine learning algorithms.
3. Create a functional prototype with:
   • A statistical dashboard showcasing KPIs (Key Performance Indicators).
   • A recommendation feature allowing users to input a movie name and receive suggestions.

---

📅 Project Timeline

Week 1-2: Data Exploration and Visualization

• Focus: Appropriation and preliminary exploration of IMDb and TMDB datasets.
• Tools: Pandas, Matplotlib, Seaborn
• Key Deliverables: Basic visualizations and descriptive statistics.

Week 3-4: Data Cleaning and Correlation Analysis

• Focus: Data preprocessing, filtering, merging datasets, and correlation analysis.
• Tools: Pandas, Seaborn, Plotly
• Key Deliverables: Cleaned datasets, exploratory findings.

Week 5-6: Machine Learning Implementation

• Focus: Development of the recommendation system using collaborative filtering techniques.
• Tools: Scikit-learn
• Key Deliverables: Functional recommendation engine.

Week 7: Finalization and Demo

• Focus: Refining the application, creating an interface, and preparing for Demo Day.
• Key Deliverables: Fully functional prototype and project presentation.

---

🖼️ Key Features

• Dashboard for Statistics:
  • Analyze movie characteristics such as runtime, genres, popularity, and revenue.
  • Visualize actor trends and their contributions to the industry.
• Recommendation Engine:
  • Suggest movies based on user preferences using machine learning.
• User-Friendly Interface:
  • An accessible platform for local cinema customers.

---

📚 Resources

• Datasets:
  • IMDb Datasets
  • TMDB Datasets
• Project Management:
  • Trello Board
  • Miro Board
• Demographic and Cinema Studies:
  • INSEE Demographics Study
  • Film Genre Preferences by Age
  • Cinema Audience Statistics by Age (2022)

---

👥 Team Members

• Lavender Oyugi: Data Analysis & Machine Learning
  Email: [email protected]
  GitHub: Lavender Oyugi

• Nuno: Data Visualization & Integration
  Email: [email protected]

• Ludivine: Data Cleaning & Interface Design
  Email: [email protected]

📬 Contact Us

For any questions or suggestions regarding this project:

Lavender Oyugi: [email protected] Nuno: [email protected] Ludivine: [email protected]

---

🚀 How to Use

1. Clone the Repository

git clone https://github.com/lavenderoyugi/movie-recommendations-le-cruise.git