FRM Part I · FRM Exam Part I · Machine-Learning Methods
A data scientist standardizes a feature using the training set, which has a mean of 40 and a standard deviation of 8. A test observation has a value of 56. What standardized value should be used for this test observation?
The standardized value is 2.0. Subtract the training mean of 40 from 56 to get 16, then divide by the training standard deviation of 8. Test data must be scaled using training-set statistics so that no information from the test set leaks into the model.
- A2.0Correct
- B7.0
- C1.6
- D0.2
Explanation
The test observation must be standardized with the training mean and standard deviation: (56 - 40) / 8 = 2.0. Using 56/8 = 7.0 ignores the mean. Dividing 16 by 10 would give 1.6, which uses an incorrect divisor. Dividing by 40 gives 0.4 rather than 0.2, so 0.2 is also wrong.
Did you get it right without looking?
One question tells you little. A timed set on Machine-Learning Methods shows your real accuracy, how long you take and where you lose marks.
More Machine-Learning Methods questions
- A hidden node in a neural network receives three inputs x1 = 2, x2 = -1 and x3 = 3 with weights 0.5, 2.0 and -0.4 respectively, and a bias o…
- Using the confusion matrix of 30 TP, 10 FP, 20 FN and 140 TN from a default classifier at a 0.5 threshold, the bank lowers the cutoff to 0.3…
- A K-nearest neighbors classifier predicts whether a firm will default using two features: leverage (ratio, range 0 to 5) and market capitali…
- A analyst compares penalized regressions on a data set with many correlated predictors, some of which are believed to be irrelevant. She wan…
- A node in a classification tree holds 40 observations: 30 non-defaults and 10 defaults. Using the Gini impurity, 1 minus the sum of squared …
- A model predicting loan losses achieves a mean squared error of 0.5 on the training sample but 4.0 on a held-out validation sample. Which in…