Problem Framing
Bias, Variance and Optimal Bayes Error
Statistical Analysis
Hypothesis Testing
Analysis of Variance
Machine Learning with Structured Data
Unsupervised Learning
Dimensionality Reduction
Clustring
Principle Component Analysis
Supervised Learning
Linear Regression
Continuous output (e.g. price)
Classification
Binary
Multiclass
Logistic Regression
Evaluating the Model Performance
Measures of performance
Confusion Matrix Accuracy, Precision, Recall, F1
Optimizing and Satisficing measures
Baseline Model