A proper decision has to be made before a user can be issued a loan, part of which is the machine
learning algorithm being used for making predictions. The algorithm after it has been fed and trained on customers' historical dataset can forecast the likelihood of a new user as either going to pay back or default on his/her loan.
A prediction value equivalent to 2 indicates that a user is going to pay back a loan while a value of 5 means Past Due.
The confidence score is a way of quantifying the uncertainty of an estimate. It is a number between 0 and 100. A score of 100 is likely an exact match, while a score of 0 means, that no matching prediction was found. The higher the score- the greater the confidence in the prediction.