ML based risk assessment solution helped the client reduce the loss incurred

Authored by Ameex Technologies on 10 Apr 2020

Client is a leading financial institution based in the US, offering different financial services.Personal loan being the primary offering and 70 % of customer acquisition happens through the digital medium.


To adopt smarter models of credit assessment that can parse huge volumes of data in truncated timelines, dynamically altering risk profiles as per real-time data. These models must generate insights for loan applications and minimize risks for decision-making process.


  • While processing a loan application, assessment of applicant’s repayment ability is a common practice and there are various parameters financial institutions follow to assess the overall risk against a loan application
  • Lenders commonly use measures of profitability and leverage to assess credit risk. Given two loan applicants – one with high profitability and high leverage, and the other with low profitability and low leverage – which applicant has lower credit risk? The complexity of answering this question multiplies when banks incorporate many other dimensions, they examine during credit risk assessment             
  • A manual risk analysis was a time-consuming process on top of the cost involved in the process


  • A Machine learning model has been developed that can adapt and learn intuitively. An ML pipeline is created that continuously feed data to the model, cleanses the data, extracts insights, and then draws predictive insights on new datasets
  • The Credit risk ML model produces expected default probabilities for each applicant by estimating the impact of a set of risk drivers such as current loans, financial state, liquidity ratio, or behavioral information such as loan/trade credit payment behavior
  • The Credit risk ML model is designed on generalized additive model (GAM) framework, in which non-linear transformations of each risk driver are assigned weights and combined into a single score

Business Impact:

  • The process of automating the risk analysis eliminated the need for the experts to analyze the default risk of the applicant, which saved time and resource for the company
  • With the implementation of this solution, the client was able to reduce the loan default percentage by 20%

Want to learn more about how we have helped our clients with their analytics journey? let’s connect!

Related Case Studies

Personalization and improved website performance increased the website traffic by 150%

Client is a leading financial group offering annuity, life insurance, and preneed products, helping… Read More

Insights on user activities helped client to increase their campaign effectiveness

Client is a leading insurance and risk management services provider for many educational institutes… Read More

Case Studies