Credit Risk Analytics and Modeling services help organizations identify and segregate high risk from low risk accounts that helps in maximizing recoveries, minimizing collections costs, reducing NPA's and bad debts and maximizing profitability.
Case Study 1
Market Equations helps a financial services firm develop a Credit Risk predictive model to improve credit collections and maximize returns.
Approach:
Market Equations performed the ETL, Strength and feature analysis and built scorecards to meet the objectives and address the clients business challenge. A scorecard was built using historical data on delinquent accounts. A higher score implied a higher propensity of repayment that implied targeting these accounts for settlement as a priority.
Outcome:
The Analyses helped the client take preventive action by identifying individual members who have higher probabilities of default. Market Equation helped the client:
- Maximize Recovery-Revenue
- Minimize Collection Costs
- Optimize Collection Efforts
- Identify possible NPA Accounts
- Identify 'Good'/No Action/Auto-Resolution Accounts
- Overall Collection Strategies for various Accounts
Case Study 2
Market Equations helps a leading bank analyze their different businesses in different locations (based on profit centers) to serve as a purpose of DSS for decision makers. Market Equations worked on the banks loan data marts such as personal loan, education loan, vehicle loan, housing loan etc to run different levels of analysis on Loan Amount, type of loans, payment schedules, interest rates, defaulter list, penal interest calculations etc.
Outcome:
- Created List and Cross Tab Reports
- Implemented Drill-up and Drill-down Paths
- Created new reports as per client Requirement
- Unit Testing of Reports
The client experienced substantial cost savings by leveraging our expertise in data analytics for the above activities which would otherwise have been very expensive and difficult to execute due to lack of capability in the clients location.