Financial companies struggle to find the balance between maximizing revenue when offering a line of credit to an applicant, and minimizing the propensity of the applicant to default on payment. The conflict between maximizing profit and the constraints put on customer authorization campaigns to minimize risk often leaves significant revenue opportunities unrealized.
The sheer number of mathematical possibilities when profiling hundreds of thousands of data points against many possible increases in incremental credit line offerings means traditional tools such as spreadsheets are ineffective. Using Datawatch Angoss the amount of time to code sophisticated optimization models is eliminated due to the automated application of statistical algorithms to the data. Even without experience in advanced analytics programming, data science teams can build models that examine the strength in patterns and relationships in their applicant’s data. With the insight derived from visual outputs such as decision and strategy tree graphics, credit authorization teams can:
- Determine the appropriate budget required for a campaign that would return the highest revenues
- Predict which distribution source (ex: email, call centre, direct mail) an applicant would likely respond from to an offer of a credit line increase
- Understand which applicant would be considered at risk if an increase in line of credit was accepted
- Apply business rules to decision trees to optimize outreach campaigns. Classifying segmented applicant groups can visually show which customer profiles (made up of a variety of demographic and economic variables) should be targeted to maximize the greatest return with the least amount of risk involved