enter image description here In the first problem, it's been told to accept the maximum number of good customers, if at least 98% of the customers that are do not repay their debt correctly identified.

I am confused about what is meant by this? Do I need to train the models and set the threshold value accordingly so that I may obtain 98% accuracy? And for the second one, I need to decrease the threshold value so that accuracy comes down to 85%?

I am stuck in this for a while. Please help me show the correct path. Thanks.

data: German Credit Risk data.

Variables: Several independent variables with the dependent variable "Credit_Risk" which responses in "Good" and "Bad".


1 Answer 1

  1. The goal is to identify at least 98% of the customers, that do not repay their debt. So the bank can "accept a maximum number of 'good' customers, that can be granted loans" Here the goal is focused on the bad customers.

  2. There should be at least 85% good customers accepted while the side focus is to reject as many bad customers as possible.

I think the difference between 1) and 2) is identifying bad customers in 1) and good customers in 2)

  • $\begingroup$ Thanks for your helpful comment. But I need to get things a little clearer. Suppose I have 700 good and 300 bad cases. So for question 1, my task is to predict 98% of these 300 bad cases? And the similar thing for the 2nd question? And to do this, should I train a model and set the threshold value accordingly so that I get 98% of the bad category correctly identified? (for the 1st question) $\endgroup$ Apr 12, 2021 at 1:31
  • $\begingroup$ Yes, this is exactly how I interpret this $\endgroup$
    – Turnvater
    Apr 12, 2021 at 7:09
  • $\begingroup$ Thanks for your kind suggestion. I guess this should be the right interpretation too. $\endgroup$ Apr 12, 2021 at 15:12

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.