🎓 Student Academic Performance Prediction

A Machine Learning project that predicts student academic performance using academic, demographic, and behavioral attributes. The goal is to identify at-risk students early and support educators in making data-driven academic decisions.

---

📌 Problem Statement

Student performance depends on multiple factors such as study habits, attendance, previous grades, and demographic background. Educational institutions often struggle to detect struggling students early.

This project uses Machine Learning models to analyze student data and predict academic performance so that timely interventions can be made.

---

📊 Dataset

The dataset contains 1000+ student records with multiple attributes affecting academic performance.

Key Features

• Study Hours
• Attendance
• Previous Grades
• Demographic Information
• Behavioral Attributes

These features help the model learn patterns that influence student academic outcomes.

---

⚙️ Project Pipeline

The project follows a standard Machine Learning workflow:

1️⃣ Data Collection

• Imported dataset containing student academic records.

2️⃣ Data Preprocessing

• Data cleaning
• Handling missing values
• Feature selection
• Data transformation

3️⃣ Exploratory Data Analysis (EDA)

EDA was performed using:

• Pandas
• NumPy
• Matplotlib
• Seaborn

This helped identify relationships between study habits, attendance, and exam performance.

4️⃣ Feature Engineering

Created relevant variables to improve model learning and prediction capability.

5️⃣ Model Development

Implemented Machine Learning models using Scikit-Learn:

• Linear Regression
• Random Forest

6️⃣ Model Evaluation

Model performance was evaluated using:

• R² Score
• Mean Absolute Error (MAE)
• Root Mean Square Error (RMSE)

---

🛠️ Technologies Used

Category	Tools
Programming Language	Python
Data Analysis	Pandas, NumPy
Data Visualization	Matplotlib, Seaborn
Machine Learning	Scikit-learn
Environment	Jupyter Notebook

---

📈 Results

Key insights from the analysis:

• Students with higher attendance and study hours tend to perform better academically.
• Behavioral and demographic factors influence student performance patterns.
• Random Forest model achieved better predictive performance compared to baseline models.

---

🚀 Future Improvements

Possible enhancements for the project:

• Implement advanced models like XGBoost and Gradient Boosting
• Deploy the model as a web application
• Create a dashboard for educators
• Integrate real-time academic data

---

📂 Project Structure

Student-Academic-Performance-Prediction
│
├── dataset
│   └── student_data.csv
│
├── notebooks
│   └── analysis.ipynb
│
├── models
│   └── trained_model.pkl
│
├── README.md
└── requirements.txt

---

👩‍💻 Author

Neha Shit Computer Science Engineering Student

GitHub: https://github.com/Neha501 LinkedIn: https://www.linkedin.com/in/neha-shit

---

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