Data Driven Policy Rules Revision

Streamline decision process

Increase accept rate

Avoid double counting of risk factors

Increase accuracy via simplification

In many occasions financial organization adopt a multi-layer set of policy rules to take credit decision. Sometimes this bring to reject / non eligibility levels above the desired value. Data analysis on historical data can bring to redesign the rules in a more efficient and stramlined process.

Success Stories

HOW WE HELPED OUR CLIENTS UNLOCK THEIR POTENTIAL
Discover how some of the world's most important companies improved their performance and defined a brand-new digital path, both for them and for their clients.

India NBFC

Housing Loan Application Scorecards and Policy Rules Redesign

The institution was embarking on full digital journey and aimed to reduce high rejection rate early on in the UNDERWRITING process

  • Redesign of policy rules using bureau data
  • Looking at both hit rate and bad rate, some policies were recommended to be modified or dropped
  • Origination scorecard using customer profile/property/past payment behaviour

Results

10%

increase in approval rate

83bps

reduction in bad rate

OverallTAT

expected to be reduce from 23days to 13days

30%

Reduction of the number of policies

0Impact

on risk level

Key Benefits

Reduced configuration/maintenance costs
Improved business logic
Predictive analytics driven
Full configuration

Main Features

Main Features

Correlation among rules and versus bad rate
Decision taking by rules stand alone and in conjunction
Alternative scenarios definitions
KPIs computations under different scenarios
Impact Analysis
Reject inference
THE HEART OF DIGITAL BANKING

Technology is so powerful right now and offers many solutions to support financial systems undergoing radical change.

That’s why we want financial institutions to discover our idea of a future packed with opportunities that we already provide.