An analyst working for a large bank created a decision tree model that can be us

Question

An analyst working for a large bank created a decision tree model that can be used to predict a potential borrower's likelihood of defaulting on the loan. Another analyst recommended that other models (such as k-nearest neighbors, neural networks, etc.) might be more accurate. Bank management, however, wanted to continue to use the decision tree, even if other algorithms were more accurate. What is the likely explanation for the management's view?

                It would probably too expensive to change models.

                Management did not believe that other models could be more accurate.

                Management believed that the decision tree would help the bank avoid lawsuits.

                Bank managers are notoriously resistant to change.

Explanation / Answer

Instead of decision tree, if we apply k-nearest neighborhood or neural networks, then it will be difficult to implement. If we have some cost or time constraint, then we have to go with decision trees, although kNN or neural networks yield better and more accurate results.

So the correct explanation for the management's view is:

It would be probably too expensive to change models. (Ans).

Related Questions

Navigate

• Browse (All)
• Browse A
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.