SENTIENT Case Study
Financial Solutions Provider Cuts Losses and Improves Approval Rates
Customer
Financial Solutions Provider
Industry
Banking & Finance
Function
Loan Approval, Credit Risk
Problem
Financial solutions provider seeks to reduce the losses associated with underwriting and loan defaults while improving the approval rate for loans.
Solution
The company managed to develop an ML predictive analytics engine with NLP capabilities to ascertain the risk of approving certain loan applications. This solution was complimented by existing underwriting methods to aid lenders in application processing.
Result
The company reported 33% decline in losses while improving approval ratings by 14% for borrowers; yielding substantial savings overall. The company was also more efficient at ordering risk across all types of borrowers, and provide clear explanations for the reasons for loan approval or denial.
More Use Cases
For the Finance Industry
Cyber Threats
Largest financial services company in South Africa uses ML to detect and prevent cyber threats in real-time
