Credit Risk assessment aims to determine the probability of loss on a particular asset, investment or loan. The objective of assessing credit risk is to determine if an investment is worthwhile, what steps should be taken to mitigate risk, and what the return rate should be to make an investment successful.
An accurate Credit Risk Model allows the financial institution to provide fair prices to customers while ensuring predictable and minimal losses. At Zopa, we use machine learning to estimate Credit Risk.
In this talk, I will cover the steps involved in the creation of our Credit Risk Model, including variable pre-processing, target definition, variable selection and building and evaluation of the different machine learning models.