Skip to content

Latest commit

 

History

History
143 lines (104 loc) · 5.57 KB

File metadata and controls

143 lines (104 loc) · 5.57 KB

Movie-Recommendation-Engine-Project

Generic badge Generic badge Generic badge

Generic badge Generic badge


Explore the app here »

Challenge - 3 : ALGORITHMS


Problem Description :


Sorting Algorithms play an important role in recommendation engines. By the end of the project, the following questions should be answered : - What role is played by sorting algorithms in recommendation engine. - Which sorting algorithm is used in this project and why?

In this project, i have implemented Recommendation Engine for Movies.



Answering the questions :


Different approaches, choosing an approach and why. To understand the role of sorting algorithms and make a choice, one should know the different types of filtering algorithms present. They are:

  1. Content-based filtering - In this, content is recommended to a user based on the past content-interaction of the same user.
  2. Collaborative filtering - In this, content is recommended to a user based on the similarity of that user's content-interaction to another user's content-interaction. Users with similar activities are recommeded similar contents.
  3. Hybrid filtering - This is a combination of Content-based and Collaborative filtering.

My objective was to implement an approach that would be :

  • relevant to the user (content similarity)
  • avoid cold start to the problem Therefore, content-based filtering approach has been used in this project.




Demo




Home

image image image

Movies & TV series catlog

image image

Details

image image image



Features

Recommendation App has the following features:

  • Recommends movies using Content based Recommendation engine.
  • Movies and TV shows section.
  • Categories wise movies.
  • Movies and TV shows details view.
  • Search suggestions.
  • Movies trailer feature is restricted to sign in.
  • Responsiveness to mobile, tablet and pc views.

Selecting the dataset :


Link to the dataset: https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata/discussion?select=tmdb_5000_movies.csv The datasets are also available with this repo, in a folder titled api_utils

The following were the factors kept in mind while selecting the dataset :

  • Relevant and useful data
  • Different and diverse attributes (to facilitate content-based filtering approach)
  • Manageable computational load

Project Flow :

  1. Dataset Analysis
  2. Data Pre-processing
  3. Model Building (using text vectorization and cosine similarity)
  4. Model Testing
  5. Establishing web connection (using Reactjs and Flask Api)

Prerequisites

You must have the following installed:

Build Instructions

Running the Web App on your Local System

To run the web app in your local device, run the following commands in your terminal:-

Clone the GitHub repository into your local device by running the following command:

git clone https://github.com/AshishUjjwal/Recommendation-Engine-Movie-Website
cd Recommendation-Engine-Movie-Website

In the project directory: You need to switch on two terminals.

Terminal 1:

cd 'FrontEnd- React'
npm install
npm start

Terminal 2:

cd 'BackEnd- Flask'
python -m venv venv
venv/scripts/activate
pip install -r requirements.txt
python app.py

Then you are good to go!!

GitHub repo size GitHub code size in bytes