Course Recommendation System

Overview

This repository contains the source code for a course recommendation system that utilizes data from CSV files sourced from Coursera, edX, Skillshare, and Udemy. The system employs a TF-IDF (Term Frequency-Inverse Document Frequency) model for Natural Language Processing (NLP) to analyze course content and predict recommendations based on similarity.

How it Works

• The system utilizes CSV files from Coursera, edX, Skillshare, and Udemy to gather course data.
• TF-IDF (Term Frequency-Inverse Document Frequency) model is employed for NLP to analyze course content.
• TF-IDF evaluates the importance of words in documents within a corpus. In this context, it helps understand and compare the content of courses across different platforms.
• Flask, a Python web framework, facilitates the integration of the system.
• The user interface is developed using HTML, CSS, and JavaScript.
• Users interact with the system through a frontend interface where they can enter preferences or queries.
• The backend processes this information, computes similarities using TF-IDF, and provides personalized course recommendations from the diverse dataset.

Dataset

The dataset used in this project can be found on Kaggle: Multi-Platform Online Courses Dataset-https://www.kaggle.com/datasets/zeesolver/multi-platform-online-courses-dataset

Screenshots

Home Page

Recommendation Page

Chat Page

About Page

Contributors

• Siddhanth Sridhar(@sidd2305)
• Shreya Chaurasia(@shreyyasiaa)
• Yashwanth Reddy(@yashwanth05)

Feel free to contribute and improve the system!

For any questions or issues, please contact siddhanth2305@gmail.com.