ВЕСТНИК КазНПУ им. Абая, серия «Физико-математические науки», №
3
(7
9
), 2022 г.
151
determining the competitiveness, viability and profitability of banks. Credit scoring is considered one of the
more powerful sets for systematizing bank buyers as part of the credit assessment process to reduce the current
and expected risk of a bad credit situation of the buyer. To build a credit scoring model, you need to have high-
quality data about borrowers, such as how the accuracy of the model depends on the data you choose to study
it. Proper data is essential for predicting various types of lending, for example, for consumer loans and business
loans, the models will differ [1].
For the subsequent construction of the model and assessment of its quality, it is important to consider the
ratio of the amount of data corresponding to the default of customers and successful solvency. For the model
to work correctly, it is necessary to have approximately the same number of both default and successful orders
in the data. It is extremely important for the study to precisely determine the loan defaults, so there should be
many such examples in the data.
Достарыңызбен бөлісу: