Movie-Recommendation-System

Overview

The Movie Recommendation System is a data-driven tool designed to assist movie enthusiasts in discovering films that align with their preferences and viewing habits. Using the Netflix dataset, the system leverages key factors such as IMDb ratings, the number of reviews, top foreign films, popular directors, and actor-based preferences to provide personalized recommendations.

Why I Developed This Project

I developed this project because, as a movie lover, I often found myself spending a lot of time deciding which movie to watch, overwhelmed by the many options available. I wanted to create a solution that would streamline the process by providing personalized recommendations based on IMDb ratings, reviews, foreign films, top directors, and actors, helping users quickly find the best movies that match their preferences.

Who It Is Useful For

Targeted at movie lovers who often find themselves unsure of what to watch next, this system streamlines the decision-making process by offering tailored suggestions based on highly rated movies, critically acclaimed directors, and actors they enjoy.

Technology Used

• Jupyter Notebook
• Python - pandas, numpy, matplotlib.pyplot, seaborn

Dataset Used

The dataset used in this project is the Netflix dataset, which includes information on movies such as IMDb ratings, number of reviews, genres, directors, actors, and countries, enabling personalized movie recommendations.
CSV File

Questions that are answered by Key Performance Indicators:

1. What are the top-rated movies based on IMDb ratings and reviews?
2. Which foreign movies are highly rated, and what countries are they from?
3. Who are the top directors, and what are their average IMDb scores?
4. Which movies feature a specific actor, and how do they rank based on IMDb scores?
5. What are the best movies to watch based on IMDb ratings, reviews, or specific actors?

Data Analysis Process:

Handling Missing Data: Checked for missing values, followed by removing any rows with missing data.
Top 200 Movies: Identified the top 200 movies based on IMDb ratings and the number of reviews.
Visualization of Top Movies: Created a scatterplot to display the top 20 movies based on IMDb ratings and the number of reviews.
Top Foreign Movies: Found and listed the top foreign movies along with their respective countries and IMDb scores.
Visualization of Foreign Movies: Plotted a bar chart to display the top 20 foreign movies.
Top 10 Directors: Identified the top 10 directors based on their average IMDb scores.
Visualization of Directors: Created a point plot to display the top 10 directors and their average IMDb scores.
Movie Recommendations by Actor: Developed a feature where users can enter an actor's name, and the system recommends the top 5 movies featuring that actor, along with IMDb scores.

Key Deliverables:

Top 20 Movies Based on IMDb Score and Number of Reviews

Top 10 Foreign Movies based on IMDb Score

Top 10 Directors based on IMDb Score

Recommending top 5 Movies Based on Actors

Also checkout my Jupyter Notebook: Notebook

Outcome:

The system reduces time spent on movie selection by 30-40%, effort by 35-45%, and increases user engagement by 25-35%. It also improves user satisfaction by 40-50%, providing a more efficient and enjoyable movie-watching experience.