Machine Learning (ML)

Algorithms that learn patterns from data instead of being explicitly programmed.

---

Machine Learning optimizes model parameters so that predictions generalize from examples.

• Main types: Supervised, unsupervised, and reinforcement learning.
• Workflow: Data preparation → training → validation → testing/monitoring.
• Risks: Overfitting, data leakage, distribution shifts (data/concept drift).
• Best practices: Proper data splits, baselines, reproducible pipelines, and task-appropriate metrics.