https://github.com/gehad-ahmed30/recommender_system

A content-based recommender system for Udemy courses using NLP and cosine similarity. It analyzes course titles to suggest similar courses based on keyword relevance. Perfect for learning how basic recommendation engines work using real data.
https://github.com/gehad-ahmed30/recommender_system

cosine-similarity data-science machine-learning neattext nlp python recommendation-engine recommender-system udemy-dataset

Last synced: about 1 month ago
JSON representation

A content-based recommender system for Udemy courses using NLP and cosine similarity. It analyzes course titles to suggest similar courses based on keyword relevance. Perfect for learning how basic recommendation engines work using real data.

• Host: GitHub
• URL: https://github.com/gehad-ahmed30/recommender_system
• Owner: gehad-Ahmed30
• Created: 2025-07-09T21:59:02.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-07-09T22:07:47.000Z (about 1 year ago)
• Last Synced: 2025-09-19T08:07:36.688Z (10 months ago)
• Topics: cosine-similarity, data-science, machine-learning, neattext, nlp, python, recommendation-engine, recommender-system, udemy-dataset
• Language: Jupyter Notebook
• Homepage:
• Size: 44.9 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Udemy Courses Recommender System 🎓🔍

This project is a case study in building a simple **Recommender System** using real-world Udemy course data. The system suggests similar courses based on course titles using **Natural Language Processing (NLP)** and **Cosine Similarity**.

---

## 📁 Dataset

The dataset used contains metadata about Udemy courses such as:

- Course title

- Price

- Number of subscribers

- Level

- Subject

- Published date

- Profit

---

## 🛠️ Technologies & Libraries Used

- Python

- pandas, numpy

- matplotlib, seaborn

- `neattext` for text preprocessing

- `sklearn` for feature extraction and similarity calculation

---

## 🔎 Steps in the Project

1. **Data Import & Exploration**

   - Load and explore the Udemy dataset

2. **Data Preprocessing**

   - Clean course titles by removing stopwords and special characters

3. **Feature Extraction**

   - Use `CountVectorizer` to convert course titles into token vectors

4. **Similarity Calculation**

   - Compute **Cosine Similarity** between all course titles

5. **Recommendation Engine**

   - Build a function to recommend similar courses based on a selected title

---

## 📦 How to Use

You can call the main function:

```python

recommend_course('Beginner to Pro - Financial Analysis in Excel 2017', numrec=5)