🎬 Netflix Content Analysis Using AI/ML

A comprehensive data science project analyzing 16,000+ Netflix movies using machine learning techniques to identify regional genre preferences, predict movie success factors, and build AI-based recommendation systems.

📋 Table of Contents

• Overview
• Dataset
• Features
• Installation
• Usage
• Project Structure
• Results
• Technologies Used
• Author

🎯 Overview

This project performs end-to-end data analysis and machine learning on Netflix's movie catalog to extract actionable insights for content producers, platform managers, and viewers. The analysis covers:

• Exploratory Data Analysis (EDA) - Genre distributions, regional preferences, temporal trends
• Correlation Analysis - Relationships between budget, revenue, ratings, and popularity
• Machine Learning Models - Revenue prediction and success classification
• Recommendation System - Content-based filtering for personalized suggestions

📊 Dataset

Metric	Value
Total Movies	16,000
Time Period	2010 - 2025
Languages	74
Countries	114
Features	18

Key Features:

• title, director, cast - Movie information
• country, language - Regional data
• genres - Category classification
• budget, revenue - Financial metrics
• vote_average, vote_count, popularity - Audience metrics
• release_year - Temporal information

✨ Features

1. Data Preprocessing

• Missing value handling
• Feature extraction (primary genre, primary country)
• ROI calculation
• Success labeling (rating ≥ 7.0)

2. Exploratory Data Analysis

• Genre distribution visualization
• Regional preference analysis
• Financial performance by genre

3. Machine Learning Models

Model 1: Revenue Prediction (Regression)

• Algorithm: Random Forest Regressor
• Features: budget, ratings, popularity, genre, country
• Metric: R² Score

Model 2: Success Classification

• Algorithm: Random Forest Classifier
• Target: Binary (Successful/Not Successful)
• Metric: Accuracy, Precision, Recall, F1-Score

4. AI Recommendation System

• Content-based filtering
• Filters: genre, country, minimum rating
• Weighted scoring: rating (40%) + popularity (30%) + vote count (30%)

🚀 Installation

Prerequisites

• Python 3.8 or higher
• pip package manager

Setup

1. Clone the repository

git clone https://github.com/YOUR_USERNAME/netflix-content-analysis.git
cd netflix-content-analysis

2. Install dependencies

pip install -r requirements.txt

3. Launch Jupyter Notebook

jupyter notebook Netflix_Analysis_Project.ipynb

💻 Usage

1. Open Netflix_Analysis_Project.ipynb in Jupyter Notebook
2. Run cells sequentially using Shift + Enter
3. Follow the analysis flow:
   • Data Loading → Preprocessing → EDA → Correlation → ML Models → Recommendations

Quick Start

# Load and analyze data
import pandas as pd
df = pd.read_csv('netflix_movies_detailed_up_to_2025.csv')

# Get recommendations
recommend_movies(genre='Animation', country='Japan', min_rating=7.5, top_n=5)

📁 Project Structure

netflix-content-analysis/
│
├── Netflix_Analysis_Project.ipynb    # Main Jupyter notebook
├── netflix_movies_detailed_up_to_2025.csv  # Dataset
├── requirements.txt                   # Python dependencies
├── README.md                          # Project documentation
├── LICENSE                            # MIT License
└── .gitignore                         # Git ignore file

📈 Results

Key Findings

Finding	Value
Dominant Genre	Drama (22.7% of total)
Budget-Revenue Correlation	r = 0.75 (Strong)
Budget-Rating Correlation	r = 0.10 (Weak)
Japan's Top Genre	Animation (38.7%)
South Korea's Top Genre	Drama (31.3%)
China's Top Genre	Action (36.6%)

Model Performance

Model	Metric	Score
Revenue Prediction	R² Score	~0.85
Success Classification	Accuracy	~0.73

Strategic Recommendations

• For High ROI: Invest in Animation/Horror with controlled budgets
• For High Revenue: Focus on Action-Adventure-SciFi blockbusters
• For High Quality: Partner with Asian studios (Japan, Korea)

🛠 Technologies Used

• Python 3.x - Programming language
• Pandas - Data manipulation
• NumPy - Numerical computing
• Matplotlib & Seaborn - Data visualization
• Scikit-learn - Machine learning
• Jupyter Notebook - Interactive development

👤 Author

Ahmet Burak Güvercin

• Student ID: 190316073
• Project: Grand Project I
• University: Celal Bayar University - Computer Engineering

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Netflix for inspiration
• TMDB for movie data
• Scikit-learn documentation
• Kaggle community

---

⭐ If you found this project helpful, please give it a star!