Question: Question 1 Cross-validation is used to estimate generalization performance. A. True B. False Question 2 In the case of leakage, the model performance in the
Question 1
Cross-validation is used to estimate generalization performance.
A. True
B. False
Question 2
In the case of leakage, the model performance in the use case will be worse than expected.
A. True
B. False
Question 3
kNN techniques are efficient in the use phase of predictive modeling.
A. True
B. False
Question 4
Leakage can be identified by proper out of sample evaluation.
A. True
B. False
Question 5
Pruning is a technique for reducing complexity.
A. True
B. False
Question 6
A 2-nearest neighbor model is more likely to overfit than 20-nearest neighbor model
A. True
B. False
Question 7
What is NOT true about causality
A. The gold standard for measuring causality is A/B testing.
B. Causality can look like correlation.
C. Only models that contain the cause are useful.
D. Causality can sometimes be measured using predictive modeling.
Question 8
All else being equal, which of the following model induction techniques should be able to overfit the most?
A. Logistic Regression
B. Tree Induction
C. Naive Bayes
D. 1000-Nearest Neighbor
Question 9
Similarity measures are most essential for
A. Nave Bayes
B. Tree induction
C. Hierarchical clustering
D. Logistic regression
Question 10
Unsupervised data mining
A. Requires less effort early in the data mining process
B. Is easier to evaluate than supervised data mining
C. Cannot be applied if we have a well-defined target variable
D. Needs minimal domain knowledge
Question 11
A fitting curve plots
A. True positive rate vs. false positive rate
B. True positive rate vs. false negative rate
C. Generalization performance vs. size of training set
D. Generalization performance vs. model complexity
Question 12
Association finding techniques
A. Are unparalleled for hypothesis testing
B. Usually produce few results
C. Require domain knowledge validation
D. Give clearly actionable results
Question 13
Which of the following evaluation measures is least sensitive to the baserate
A. Accuracy
B. AUC
C. Lift
D. True Positive Rate
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
