Neural Networks Show Fewer False Positives On Bad Debt – Study
Credit risk models that use neural networks are the most accurate method for predicting repayment of non-performing loans, suggests a new study by academics – a method that could have implications for lenders and governments that plan. loan moratorium programs.
The study compares five approaches to model collection rates for consumer loans past due but not yet in default. Two of the models are based on classical regression techniques and three are based on machine learning. The conclusions were
Only users who have a paid subscription or are part of a corporate subscription can print or copy content.
To access these options, as well as all other subscription benefits, please contact [email protected] or check out our subscription options here: http://subscriptions.risk.net/subscribe
You cannot currently print this content. Please contact [email protected] to know more.
You cannot currently copy this content. Please contact [email protected] to know more.