1 Consider the following case for the next TWO questions.

We will apply the KNN approach to the Supreme data set. This data set includes 85 predictors that measure demographic characteristics for 5,822 individuals. The response variable is Purchase, which indicates whether or not a given individual purchases a caravan insurance policy.

In this example, we split the observations into a test set, containing the first 1000 obs, and a training set, containing the remaining obs. We fit a KNN model on the training data using K=1, 3, and 5. Suppose that there are some significant costs to try to sell insurance to a given individual and the company has limited resources. For instance, a salesperson must visit each potential customer. If the company tries to sell insurance to a random selection of customers, then the success rate will be only 1%, which is far too low given the costs involved. Instead, the company would like to try to sell insurance only to customers who are likely to buy it.

The number of classes in this classification problem is:

Group of answer choices

2

85

1, 3, 5

2 Consider the following results of a logistic regression of credit card default:

	coefficient
Intercept	-10.50
Balance	0.0040

For a balance of $2,500, the conditional probability of default is

Group of answer choices

0.3775

0.5744

0.1545

0.2891

0.2142

0.1091