**Q.2 **

Universal Bank is a relatively young bank growing rapidly in terms of overall customer acquisition. The majority of these customers are liability customers (depositors) with varying sizes of relationship with the bank. The customer base of asset customers (borrowers) is quite small, and the bank is interested in expanding this base rapidly to bring in more loan business. In particular, it wants to explore ways of converting its liability customers to personal loan customers (while retaining them as depositors). A campaign that the bank ran last year for liability customers showed a healthy conversion rate of over 9% success. This has encouraged the retail marketing department to devise smarter campaigns with better target marketing. The goal is to use k-NN to predict whether a new customer will accept a loan offer. This will serve as the basis for the design of a new campaign.The file UniversalBank.csv contains data on 5000 customers. The data include customer demographic information (age, income, etc.), the customer's relationship with the bank (mortgage, securities account, etc.), and the customer response to the last personal loan campaign (Personal Loan). Among these 5000 customers, only 480(= 9.6%) accepted the personal loan that was offered to them in the earlier campaign.Partition the data into training (60%) and validation (40%) sets.Remember to transform categorical predictors with more than two categories into dummy variables first. Specify the success class as 1 (loan acceptance), and use the default cutoff value of0.5.

Q1-A: a. Consider the following customer:Age = 40, Experience = 10, Income = 84, Family = 2, CCAvg = 2, Education_1= 0, Education_2 = 1, Education_3 = 0, Mortgage = 0, Securities Account = 0,CD Account = 0, Online = 1, and Credit Card = 1. Perform a k-NN classification with all predictors except ID and ZIP code using k = 1.

**Q2-A**

The customer will accept the loan offer. True or False

**Q2-B **

What is a choice of k that balances between overfitting and ignoring the predictor information? Choose the closest one.

A. 1

B. 3

C. 7

D. 10

**Q2-C **

Match the data in the confusion matrix (use the closest values to the ones that you've obtained) that resulted from using the best k with the respective elements, where 0's correspond to non-takers and 1's - to takers.

Fraction of TP in the confusion matrix

Fraction of TN in the confusion matrix

Fraction of FP in the confusion matrix

Fraction of FN in the confusion matrix

Data:0.006;0.891; 0.035;0.0675

**Q2-D **:Consider the following customer: Age = 40, Experience = 10, Income = 200, Family = 10, CCAvg = 2, Education = 1, Mortgage = 1, Securities. Account = 1, CD.Account = 3, Online = 1, CreditCard = 1.

*Question:*

The customer is a non-taker. True or False?

**Q2-E **: Repartition the data, this time into training, validation, and test sets (50% : 30% :20%). Apply the k-NN method with the k chosen above. Compare the confusion matrix of the test set with that of the training and validation sets. Match the rates (the closest value) with the respective values:

Train True Positive Rate, TPR (TP/P)

Validation TPR

Test TPR

Training True Negative Rate, TNR (TN/N)

Validation TNR

Test TNR

Data:0.996,0.741,0.643,0.996,0.993,0.676

**Q.2-F*KNN yields a uniform rule that can be applied to each new record to be predicted. True or False?

**Q.2-G**Which of the following is not a part of the KNN learning?

A. Calculation of the distance from a new record to each of the training records

B. Selection of the n-closest training records

C. Determining the average target value for the n-closest training records

D. Scoring the target value to the new record

E. Fitting the distances to the training set