Model Evaluation — learning path · Lensa ML

8 steps · Learning path

Model Evaluation

Validation, cross-validation, the bias–variance tradeoff, and pitfalls

1
Model Evaluation & Metrics
Precision, recall, F1, ROC curves, and regression metrics
2
Train, Validation & Test Sets
Splitting data to measure generalization and avoid overfitting
3
Cross-Validation
K-fold, stratified, and leave-one-out evaluation
4
Bias-Variance Tradeoff
Why models underfit or overfit — the fundamental decomposition
5
Learning Curves
Diagnosing underfitting and overfitting from training size
6
Class Imbalance & Resampling
SMOTE, class weights, and metrics beyond accuracy
7
Feature Selection
Filter, wrapper, and embedded methods for choosing features
8
Curse of Dimensionality
Why high-dimensional spaces break intuition and algorithms