Question: Consider the following data concerning credit default: Age Loan Default D1 D2 25 40 000 N 102 000 104 35 60 000 N 82 000
Consider the following data concerning credit default:
| Age | Loan | Default | D1 | D2 |
| 25 | 40 000 | N | 102 000 | 104 |
| 35 | 60 000 | N | 82 000 | 69 |
| 45 | 80 000 | N | 62 000 | 92 |
| 20 | 20 000 | N | 122 000 | 28 |
| 35 | 120 000 | N | 22 000 | 125 |
| 52 | 18 000 | N | 124 000 | 55 |
| 23 | 95 000 | Y | 47 000 | 98 |
| 40 | 62 000 | Y | 80 000 | 74 |
| 60 | 100 000 | Y | 42 000 | 117 |
| 48 | 220 000 | Y | 78 000 | 225 |
| 33 | 150 000 | Y | 8 000 | 154 |
Age and Loan are two numerical variables (predictors) and Default is the target.
Use the k-NN algorithm with k=3 and the given training set to classify an unknown case (Age=48 and Loan=142 000) using Euclidean distance, and without Normalisation for the following cases:
- Use the loan amount as is and
- Use the loan amount in 1000 units.
You are also required to comment on your result.
The calculation for both part (i) and (ii) are included in the data table: columns D1 and D2
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
