Student Performance Prediction

A machine learning–powered web app that predicts whether a student will pass or fail based on demographic, educational, and test-related factors. The app uses a trained classifier model and applies proper feature encoding to deliver accurate predictions with confidence scores.

🚀 Features

• ✔️ Predicts Pass / Fail
• ✔️ Shows confidence percentage
• ✔️ Uses trained ML model (student_model.pkl)
• ✔️ Encodes categorical features using mapping + saved columns
• ✔️ Smooth, modern UI with a soft pink academic theme
• ✔️ Fast predictions using Streamlit

How It Works

1. Dataset

Uses the expanded student performance dataset including features such as:

• Gender
• Ethnicity
• Parental education
• Lunch type
• Test preparation course
• Math, Reading, Writing scores

2. Preprocessing

• Categorical encoding using label maps
• Ensuring training and inference columns match (model_columns.pkl)
• Handling feature order
• No missing data during prediction because missing fields are filled with default zeroes

3. ML Model

• Model type: Binary Classification (Pass / Fail)
• Preprocessing & training done inside the Jupyter Notebook
• Saved as student_model.pkl

4. Prediction Output

• 🔍 Pass/Fail prediction
• 📊 Confidence score (probability)
• Clean success/error messages

Tech Stack

• Python
• Streamlit
• Pandas
• Scikit-Learn
• Pickle
• NumPy

📦 Installation & Setup

1️⃣ Clone the repository

git clone https://github.com/your-username/your-repo-name.git
cd your-repo-name

2️⃣ Create virtual environment

python -m venv venv

3️⃣ Activate environment

Windows:

venv\Scripts\activate

Mac/Linux:

source venv/bin/activate

4️⃣ Install dependencies

pip install -r requirements.txt

5️⃣ Run the Streamlit app

streamlit run app.py

📁 Project Structure

│── app.py                               # Streamlit web app
│── Student Performance Prediction.ipynb # Model training notebook
│── Expanded_data_with_more_features.csv # Dataset
│── student_model.pkl                    # Trained ML model
│── model_columns.pkl                    # Correct column order for inference
│── requirements.txt
└── README.md

Dataset

Available on Kaggle : https://www.kaggle.com/datasets/desalegngeb/students-exam-scores

🌐 Live Demo

https://studentperformancebot.streamlit.app/

📸 Screenshots