🎓 Student Performance Prediction using Machine Learning

---

📌 Project Overview

Student Performance Prediction is an end-to-end Machine Learning project that predicts a student's exam score based on academic, personal, and environmental factors.

This project demonstrates the complete machine learning workflow, including:

• 📂 Data Collection
• 🧹 Data Cleaning & Preprocessing
• 📊 Exploratory Data Analysis (EDA)
• 📈 Data Visualization using Matplotlib
• 🤖 Machine Learning Model Training
• 📉 Model Evaluation
• 💾 Model Saving using Joblib
• 🌐 Interactive Web Application using Streamlit

---

🎯 Problem Statement

Educational institutions often face challenges in understanding which factors most significantly influence student academic performance.

This project aims to:

• Analyze student performance factors
• Identify relationships between features
• Predict student exam scores
• Provide an interactive prediction system

---

📊 Dataset

Student Performance Factors Dataset

The dataset contains multiple features affecting student performance, including:

• Hours Studied
• Attendance
• Previous Scores
• Sleep Hours
• Motivation Level
• Teacher Quality
• Internet Access
• Family Income
• School Type
• Gender
• Parental Involvement
• Physical Activity
• Distance from Home
• Learning Disabilities
• Access to Resources

Target Variable

Exam_Score

---

🛠 Tech Stack

• Python
• Pandas
• NumPy
• Matplotlib
• Scikit-Learn
• Joblib
• Streamlit
• Jupyter Notebook
• VS Code
• Git & GitHub

---

📂 Project Structure

Student_Performance_Project/
│
├── app.py
├── README.md
├── requirements.txt
├── .gitignore
│
├── data/
│   ├── StudentPerformanceFactors.csv
│   └── student_clean.csv
│
├── models/
│   ├── student_performance_model.pkl
│   └── feature_names.pkl
│
├── notebooks/
│   └── analysis.ipynb
│
├── outputs/
│   └── graphs/
│
├── screenshots/
│
└── src/
    ├── preprocess.py
    ├── train.py
    └── predict.py

---

🔄 Machine Learning Workflow

Dataset
   │
   ▼
Data Cleaning
   │
   ▼
Exploratory Data Analysis
   │
   ▼
Feature Engineering
   │
   ▼
Train-Test Split
   │
   ▼
Random Forest Regressor
   │
   ▼
Model Evaluation
   │
   ▼
Model Saving
   │
   ▼
Prediction
   │
   ▼
Streamlit Web App

---

📊 Exploratory Data Analysis (EDA)

The project includes multiple visualizations using Matplotlib to understand the data and identify important trends.

📈 Exam Score Distribution

---

📚 Hours Studied Distribution

---

📝 Attendance Distribution

---

😴 Sleep Hours Distribution

---

📖 Hours Studied vs Exam Score

---

📊 Attendance vs Exam Score

---

🔥 Correlation Matrix

---

🌟 Feature Importance

---

🎯 Actual vs Predicted Scores

---

🤖 Machine Learning Model

Algorithm Used

✅ Random Forest Regressor

Why Random Forest?

• High prediction accuracy
• Handles non-linear relationships
• Robust against overfitting
• Works well on tabular datasets
• Provides feature importance

---

📈 Model Evaluation

The model is evaluated using:

• Mean Absolute Error (MAE)
• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• R² Score

---

🌐 Streamlit Web Application

The project also includes an interactive web application built using Streamlit.

Features

• Enter student information
• Predict exam score instantly
• Clean and responsive interface
• Machine learning powered prediction

Home Page

(Add screenshot)

screenshots/home.png

Prediction Result

(Add screenshot)

screenshots/result.png

---

🚀 Installation

Clone the repository

git clone https://github.com/pratimaasapkota/Student-Performance-Prediction.git

Move into the project directory

cd Student-Performance-Prediction

Install dependencies

pip install -r requirements.txt

Train the model

python src/train.py

Run prediction

python src/predict.py

Launch the Streamlit application

streamlit run app.py

---

📌 Future Improvements

• Hyperparameter tuning
• Compare multiple ML models
• Batch prediction using CSV upload
• Online deployment with Streamlit Community Cloud
• SHAP/LIME explainability
• Advanced dashboard with Plotly
• User authentication

---

📚 Learning Outcomes

This project helped me gain practical experience in:

• Data Cleaning
• Exploratory Data Analysis (EDA)
• Data Visualization
• Feature Engineering
• Machine Learning
• Model Evaluation
• Streamlit Application Development
• End-to-End ML Pipeline
• Git & GitHub Workflow

---

👩‍💻 Author

Pratima Sapkota

Computer Engineering Student

Interests

• Artificial Intelligence
• Machine Learning
• Data Science
• Deep Learning
• Full Stack Development

---

⭐ Support

If you found this project useful, please consider giving it a ⭐ on GitHub.

It motivates me to build more AI and Machine Learning projects!

---