Квизы: Model Evaluation

Measure a model the way data scientists and interviewers do: precision, recall, confusion matrices, ROC/AUC, cross-validation and regression metrics.

Средний Квизов: 5 · вопросов: 50 около 32 минуты
0/5сдано Экзамен по разделу 20 вопросов вперемешку. За 80% - сертификат.
Теги:
1 Accuracy, Precision & Recall Средний Compute accuracy, precision, recall and F1 from small counts and pick the right metric for the job. #metrics#interview 10 вопр. · ~6 мин Не начат Начать
2 Confusion Matrix Средний Read binary and multi-class confusion matrices and pull every metric out of them. #metrics#classification 10 вопр. · ~6 мин Не начат Начать
3 ROC Curve & AUC Сложный Understand what the ROC curve plots, what AUC really measures and where it misleads. #metrics#roc-auc 10 вопр. · ~8 мин Не начат Начать
4 Cross-Validation Средний Use k-fold, stratified, grouped and time-based splits correctly and avoid data leakage. #validation#interview 10 вопр. · ~6 мин Не начат Начать
5 Regression Metrics Средний Compute MAE, MSE, RMSE and R² by hand and know how outliers and units affect each one. #metrics#regression 10 вопр. · ~6 мин Не начат Начать