https://github.com/anwarulh007/eduprotect--student-dropout-analysis
EduProtect is a valuable tool for educators, parents, and students in India. By providing accurate predictions and facilitating collaboration, it aims to address the critical issue of student dropouts and ensure a brighter future for all. Used Java in App development and Python for the ML Algorithm in Google Colab.
https://github.com/anwarulh007/eduprotect--student-dropout-analysis
matpoltlib numpy python random-forest-classifier sckiit-learn
Last synced: 5 months ago
JSON representation
EduProtect is a valuable tool for educators, parents, and students in India. By providing accurate predictions and facilitating collaboration, it aims to address the critical issue of student dropouts and ensure a brighter future for all. Used Java in App development and Python for the ML Algorithm in Google Colab.
- Host: GitHub
- URL: https://github.com/anwarulh007/eduprotect--student-dropout-analysis
- Owner: Anwarulh007
- License: mit
- Created: 2024-03-16T13:31:10.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-05-20T11:54:55.000Z (about 1 year ago)
- Last Synced: 2025-07-04T08:04:49.247Z (about 1 year ago)
- Topics: matpoltlib, numpy, python, random-forest-classifier, sckiit-learn
- Language: Jupyter Notebook
- Homepage:
- Size: 2.64 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: License.txt
Awesome Lists containing this project
README
## Eduprotect - Student Dropout Prediction
**Project Overview**
This project addresses the pressing issue of student dropouts in Indian schools by leveraging machine learning and mobile app development. It provides a comprehensive solution for predicting dropout likelihood and facilitating collaboration between educators, parents, and students.
**Key Features**
* Data-Driven Analysis: Employs advanced data analysis techniques to identify key factors influencing dropout rates.
* Predictive Model: Utilizes a Random Forest classifier, trained on a robust dataset, to accurately predict dropout probability.
* Mobile App Interface: Offers a user-friendly mobile app built with Android Studio, allowing for easy data input and prediction retrieval.
* Collaborative Platform: Facilitates collaboration between counselors and skill-based centers to provide timely support to students at risk.
**Dataset Overview**
**Technologies**
* Programming Languages: Python and Java
* Machine Learning: Random Forest
* Development Environments: Google Colab and Android Studio
* Libraries and Frameworks: Matplotlib, Scikit-learn, Pandas, NumPy,
## How to Use 🚀
To run the project locally on your machine:
1. **Clone the Repository**:
```bash
git clone https://github.com/Anwarulh007/EduProtect--Student-Dropout-Analysis
2. **Open the Project**:
Navigate to the project folder and open the index.html file in your web browser to explore the website locally.
**Visualization**
Let's see the distribution of Dropout Rates with respect to School Type using bar chart or pie chart
**School wise Dropout Rates**
Insights 🔹
There has been maximum number of dropouts from Government School.
-----------------------------------------------------------------------------------------------------------------------------------
**Location wise Dropout Rates**
Insights 🔹
The greatest percentage of dropouts has come from rural areas.
-----------------------------------------------------------------------------------------------------------------------------------------------
**Gender wise Dropout Rates**
Insights 🔹
The largest percentage of dropouts have been women.
-----------------------------------------------------------------------------------------------------------------------------------------------
**Caste wise Dropout Rates**
Insights 🔹
The ST caste has had the highest percentage of dropouts.
-----------------------------------------------------------------------------------------------------------------------------------------------
**Standard wise Dropout Rates**
Insights🔹
The highest percentage of dropouts came from the eighth standard.
----------------------------------------------------------------------------------------------------------------------------------------------
**Age wise Dropout Rates**
Insights🔹
The age group of 12 years old accounts for the highest percentage of dropouts.
----------------------------------------------------------------------------------------------------------------------------------------------
**Overall Dropout Rates based on all Categories**
Insights🔹
Age/Standard category dropout rates have been the highest.
----------------------------------------------------------------------------------------------------------------------------------------------
**Total Dropout Percentage**
----------------------------------------------------------------------------------------------------------------------------------------------
**Output**
**Contributing** 🤝
We welcome your contributions to enhance the platform and improve user experience! Feel free to open a pull request or issue if you have any suggestions or features to add.
**Contribution Guidelines**:
Fork the repository.
Create a new branch for your feature or bug fix.
Make your changes and submit a pull request.
**Usage**
* Login or Create an Account: Users can create an account or login to access the application.
* Input Student Data: Enter relevant information about the student, such as socio-economic background, academic performance, and other factors.
* Receive Prediction: The application will use the predictive model to calculate the dropout likelihood and provide a prediction.
* Access Resources: Counselors and skill-based centers can join the app to access resources, connect with students, and offer support.
**License**
This project is licensed under the MIT License.
## Made with 🤍 by Anwarul Haque