This repository contains 4 Machine Learning projects completed as part of my Elevvo Internship.
Each task covers a different ML problem and demonstrates data processing, modeling, evaluation, and visualization skills.
| Task | Description | Key Techniques / Models | Results / Notes |
|---|---|---|---|
| 1.Student Score Prediction | Predict students' exam scores based on study hours | Linear Regression, Polynomial Regression | Polynomial Regression: MAE 0.27, R² 0.99 |
| 2.Customer Segmentation | Cluster mall customers into segments based on demographics and spending | K-Means, Silhouette Score, Power BI dashboard | 5 clusters: Cautious Wealthy, Moderate, Luxury Spenders, Impulsive, Budget-Conscious |
| 3.Loan Approval Prediction | Predict loan approval status | Logistic Regression, Decision Tree, KNN, Random Forest, Orange Data Mining workflow | Random Forest: 99.88% accuracy |
| 4.Sales Forecasting | Forecast future Walmart sales | Regression (Linear, Random Forest, XGBoost), ARIMA, Modified ARIMA, SARIMA | Forecasts visualized and compared with actual sales |
- Python: Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Statsmodels
- Orange Data Mining (Task 3)
- Power BI (Task 2 Dashboard)
Elevvo-Internship-Tasks/
├──README.md
├──Task1_StudentScorePrediction/
├──Task2_CustomerSegmentation/
├──Task3_LoanApprovalPrediction/
└──Task4_SalesForecasting/
- Datasets are not included if large; links to Kaggle datasets are provided in each task README.
- Each task folder contains: notebook(s), data (optional or sample), and any dashboards/workflows.
- Task 4 is focused on time series forecasting, while other tasks cover regression, classification, and clustering.
By Abdelwakil Mansour — Elevvo Internship Projects