Supervised Machine Learning: Regression and Classification

What you'll learn

• Frame regression and classification problems and choose appropriate targets, loss functions, and evaluation metrics
• Prepare data and engineer features; handle missing, noisy, and imbalanced datasets
• Implement core algorithms: linear/logistic models, regularization, kNN, SVM, trees, random forests, and gradient boosting
• Apply dimensionality reduction and feature selection to improve model performance and interpretability
• Design robust train/validation/test splits, use cross-validation, and prevent data leakage
• Calibrate probabilities, set decision thresholds, and make cost-aware decisions using appropriate metrics
• Build reproducible pipelines, automate hyperparameter tuning, and track experiments
• Interpret model behavior, evaluate fairness and risk, and prepare models for deployment and monitoring
• Deliver an end-to-end capstone project that demonstrates production-style predictive modeling

Prerequisites

Basic Python, linear algebra, and probability; familiarity with pandas or Jupyter notebooks is helpful.

Skills you'll gain

• Supervised learning
• Regression modeling
• Classification & probabilistic prediction
• Feature engineering & data wrangling
• Model evaluation & calibration
• Cross-validation & experiment design
• Hyperparameter tuning & pipelines
• Dimensionality reduction & feature selection
• Model interpretability & fairness
• Deployment and monitoring