FRM Part I · FRM Exam Part I · Machine Learning and Prediction
A confusion matrix for a credit model on 1,000 borrowers shows: true positives 60, false positives 40, false negatives 20, true negatives 880. What is the F1 score?
F1 is about 0.67. Precision is 60/100 = 0.60 and recall is 60/80 = 0.75, and F1 is their harmonic mean, 2×0.60×0.75/1.35 ≈ 0.667. Accuracy of 0.94 is misleading here because most borrowers did not default.
- A0.60
- B0.67Correct
- C0.75
- D0.93
Explanation
Precision = 60/100 = 0.60. Recall = 60/80 = 0.75. F1 = 2(0.60)(0.75)/(0.60+0.75) = 0.90/1.35 = 0.667. The 0.93 option is accuracy (940/1000), which is inflated by the many true negatives.
Did you get it right without looking?
One question tells you little. A timed set on Machine Learning and Prediction shows your real accuracy, how long you take and where you lose marks.
More Machine Learning and Prediction questions
- A fraud model is evaluated on 1,000 transactions. The confusion matrix shows: true positives 30, false positives 20, false negatives 10, tru…
- An analyst uses ridge regression with one predictor and no intercept, where the predictor has been scaled so that the sum of x squared equal…
- A bank uses the first three principal components of 12 equity factor returns as regressors in a model to predict portfolio losses (principal…
- Compared with a logistic regression using the same inputs, a deep neural network used for a bank's default prediction is most likely to pres…
- A quantitative analyst fits a very flexible model to 500 observations. It achieves a training mean squared error of 0.2 but a test mean squa…
- A risk team runs agglomerative hierarchical clustering on five funds using Euclidean distance. The first merge joins Funds A and B, which ar…