Credit Scoring
Better predict the risk of default or delinquency
In all credit lending businesses such as banks or NBFIs, a high rate of non-performing loans equates with increased loan write-offs, delayed income from interest and costs associated with debt collection. It is therefore essential, before granting a new credit, to quantify each applicant’s creditworthiness and predict their risk of default or delinquency.
Business Driver
Better predict the risk of default or delinquency for loans granted to new or existing customers and reduce costs of debt collection
Data Needed
A sample of loans that can be divided into “goods” and “bads” on the basis of a credit event such as
- default or delinquency,
- data on principal owner if available (e.g., income, professional background, net worth, available credit, prior delinquencies),
- information on business (e.g., turnover, net profit, liabilities, number of employees, NACE code)
Deliverable
- Probability that a credit applicant will default or become delinquent
Methods Used
- Discriminant Analysis
- Linear Regression
- Logistic Regression
- Poisson
- K-Nearest Neighbours
- Decision Trees
- Probabilistic Neural Networks
Get in touch with us
InsightOut Analytics
InsightOut Analytics is a consulting firm for Data Science, Machine Learning & AI.
We develop complete business solutions which enable our clients to stay competitive in their industries by taking data-driven decisions.
The content of this website does not necessarily reflect the official position of the European Union. For details on other programs co-financed by the European Union, see www.fonduri-ue.ro
Get in touch