Student_Performance-Predictor

This project demonstrates a Student Performnce Prediction and Analysis system built using Python in a Google Colab environment with linea regression . It applies data analysis and machine leaning to predict a student’s final score based on stdy-related metrics such as study hours, attendance, previous exam results, and assignments completed.

Project Overview

This project walks through the following :

1. Data Loading and Exploration – Load and inspect the dataset.
2. Data Cleaning and Preprocessing – Handle missing values, duplicates, and data types.
3. Visualization – Visualize relationships between metrics using charts and plots.
4. Model Building – Use Linear Regression to predict final scores.
5. Evaluation – Measure model performance using MAE, MSE, and R² metrics.
6. Prediction Tool – Predict student performance interactively by entering input metrics.

Technologies Used

• **Python **
• **Google Colab **
• Pandas for data handling
• NumPy for numerical operations
• Matplotlib & Seaborn for data visualization
• Scikit-learn (sklearn) for model training and evaluation

Key Visualizations

• Study Hours vs Final Score — Shows the direct relationship between time studied and performance.
• Distribution of Final Scores — Displays how final scores are spread across students.
• Pairplot of All Metrics — Illustrates relationships among all input variables.

Interactive Prediction Tool

You can input your own values for study hours, attendance, and other metrics to get a predicted final score. Example usage:

Enter number of study hours: 10 Enter attendance percentage: 85 Enter previous exam score: 70 Enter number of assignments done: 8 Predicted Final Score: 75.3