Data Mining Project 2025 This repository contains the implementation of two core data mining tasks: Loan Approval Classification and Student Performance Regression. The project focuses on the full data science pipeline, from preprocessing to model evaluation.
Project Structure:
- Classification Task: Loan Approval Prediction Objective: Predict whether a loan application will be approved or rejected based on applicant data.
Dataset: Loan Approval Dataset.
Key Steps:
Preprocessing: Handling missing values, encoding categorical variables, and feature scaling.
Modeling: Training and testing classification models (e.g., Logistic Regression, Decision Tree, or Random Forest).
Evaluation: * Confusion Matrix: To visualize true vs. false predictions.
Accuracy: To measure the overall performance.
Visualization: Plotting Predicted vs. Actual results.
- Regression Task: Student Performance Prediction Objective: Predict the academic performance/score of students based on various demographic and study-related factors.
Dataset: Student Performance Dataset.
Key Steps:
Preprocessing: Data cleaning, normalization, and handling outliers.
Modeling: Training regression models (e.g., Linear Regression).
Evaluation Metrics:
R-Square (R²): To determine how well the model explains the variance.
MAE / RMSE: To measure the average magnitude of error in predictions.
Visualization: Scatter plots and regression lines for Predicted vs. Actual results.