Supervised Learning

  1. Model Evaluation and Validation
    1. Evaluation Metrics for Regression
      1. Error-based Metrics
        1. Mean Absolute Error
          1. Definition and Interpretation
            1. Robustness to Outliers
            2. Mean Squared Error
              1. Definition and Properties
                1. Sensitivity to Outliers
                2. Root Mean Squared Error
                  1. Scale Interpretation
                    1. Comparison with MAE
                    2. Mean Absolute Percentage Error
                      1. Symmetric Mean Absolute Percentage Error
                      2. Correlation-based Metrics
                        1. R-squared
                          1. Coefficient of Determination
                            1. Interpretation Guidelines
                              1. Limitations
                              2. Adjusted R-squared
                                1. Penalty for Model Complexity
                                  1. Comparison with R-squared
                                2. Residual Analysis
                                  1. Residual Plots
                                    1. Normality Tests
                                      1. Homoscedasticity Assessment
                                        1. Autocorrelation Analysis
                                      2. Evaluation Metrics for Classification
                                        1. Confusion Matrix
                                          1. True Positives
                                            1. True Negatives
                                              1. False Positives
                                                1. False Negatives
                                                  1. Multi-class Confusion Matrix
                                                  2. Basic Classification Metrics
                                                    1. Accuracy
                                                      1. Definition and Calculation
                                                        1. Limitations with Imbalanced Data
                                                        2. Precision
                                                          1. Positive Predictive Value
                                                            1. Interpretation
                                                            2. Recall
                                                              1. Sensitivity
                                                                1. True Positive Rate
                                                                2. Specificity
                                                                  1. True Negative Rate
                                                                    1. Complement of False Positive Rate
                                                                    2. F1-Score
                                                                      1. Harmonic Mean of Precision and Recall
                                                                        1. Balanced Performance Measure
                                                                        2. F-beta Score
                                                                          1. Weighted Harmonic Mean
                                                                            1. Beta Parameter Interpretation
                                                                          2. Advanced Classification Metrics
                                                                            1. ROC Curve
                                                                              1. True Positive Rate vs False Positive Rate
                                                                                1. Threshold Selection
                                                                                  1. Interpreting ROC Curves
                                                                                  2. Area Under ROC Curve
                                                                                    1. AUC Interpretation
                                                                                      1. Comparison Across Models
                                                                                      2. Precision-Recall Curve
                                                                                        1. Precision vs Recall Trade-off
                                                                                          1. When to Use PR Curves
                                                                                          2. Average Precision
                                                                                            1. Area Under PR Curve
                                                                                            2. Multi-class and Multi-label Metrics
                                                                                              1. Macro Averaging
                                                                                                1. Micro Averaging
                                                                                                  1. Weighted Averaging
                                                                                                    1. Per-class Metrics
                                                                                                    2. Class Imbalance Considerations
                                                                                                      1. Impact on Different Metrics
                                                                                                        1. Appropriate Metric Selection
                                                                                                          1. Stratified Sampling
                                                                                                        2. Cross-Validation Techniques
                                                                                                          1. Hold-out Validation
                                                                                                            1. Train-Validation-Test Split
                                                                                                              1. Proportion Guidelines
                                                                                                                1. Random vs Stratified Splitting
                                                                                                                2. K-Fold Cross-Validation
                                                                                                                  1. Procedure Description
                                                                                                                    1. Choosing K Value
                                                                                                                      1. Computational Considerations
                                                                                                                      2. Stratified K-Fold Cross-Validation
                                                                                                                        1. Maintaining Class Proportions
                                                                                                                          1. Benefits for Imbalanced Data
                                                                                                                          2. Leave-One-Out Cross-Validation
                                                                                                                            1. Extreme Case of K-Fold
                                                                                                                              1. Computational Intensity
                                                                                                                                1. Variance Characteristics
                                                                                                                                2. Time Series Cross-Validation
                                                                                                                                  1. Forward Chaining
                                                                                                                                    1. Temporal Dependencies
                                                                                                                                    2. Nested Cross-Validation
                                                                                                                                      1. Model Selection and Evaluation
                                                                                                                                        1. Inner and Outer Loops
                                                                                                                                          1. Unbiased Performance Estimation
                                                                                                                                        2. Bias-Variance Tradeoff
                                                                                                                                          1. Bias Definition
                                                                                                                                            1. Systematic Error
                                                                                                                                              1. Underfitting Relationship
                                                                                                                                              2. Variance Definition
                                                                                                                                                1. Model Sensitivity
                                                                                                                                                  1. Overfitting Relationship
                                                                                                                                                  2. Irreducible Error
                                                                                                                                                    1. Decomposition Analysis
                                                                                                                                                      1. Managing the Tradeoff
                                                                                                                                                        1. Model Complexity Effects
                                                                                                                                                          1. Regularization Impact
                                                                                                                                                            1. Ensemble Methods Benefits

                                                                                                                                                        Previous

                                                                                                                                                        7. Probabilistic Models

                                                                                                                                                        Go to top

                                                                                                                                                        Next

                                                                                                                                                        9. Advanced Topics in Supervised Learning