This folder contains machine learning coursework projects demonstrating practical application of supervised and unsupervised learning using Python.
1️⃣ Mercedes-Benz Greener Manufacturing (Regression)
Predicting vehicle test times to enhance manufacturing efficiency.
2️⃣ Employee Turnover Prediction (Classification & Clustering)
Identifying at-risk employees and uncovering attrition drivers for HR strategies.
3️⃣ Song Cohort Creation (Clustering)
Segmenting songs into thematic groups using unsupervised learning for recommendation engines.
- Python
- Pandas, NumPy, Matplotlib, Seaborn
- scikit-learn, XGBoost, imblearn
- Spotify API
✅ Data Cleaning & Feature Engineering: Preparing diverse datasets for modeling.
✅ EDA & Visualization: Identifying insights and patterns visually.
✅ Supervised Learning: Regression (XGBoost), Classification (Random Forest, Gradient Boosting).
✅ Unsupervised Learning: Clustering (K-Means) for segmentation.
✅ Advanced Techniques: PCA for dimensionality reduction, SMOTE for handling imbalance.
✅ Model Evaluation: Using MAE, Recall, AUC to align models with business goals.
These projects demonstrate a strong foundation in machine learning workflows for solving practical business problems across different domains.