Sei sulla pagina 1di 16

# Based on paper on Profitbased acquisition strategy

## for credit cards by RT

Stewart
Presented by Piyush

## Credit Card Profit & Loss

1. Revenue

Spends/Interchange
Finance charges
Others

2. Cost

Fixed costs
Acquisition costs
Other operating costs

3. Loss

acquisition

## Potential Revenue NOT considered

Approve or Decline decision based solely on
risk
High

Risk

Low

High

Cut of
Decline

Approve

Credit Score

## Few Credit Card Jargons

Bad Rate / Charge-Of rate Ratio of number of customers defaulting on credit cards
to the total number of customers.

## Credit /FICO score

A score representing thecreditworthinessof a person.

Objective

model revenue.

## Use revenue models along with risk models for

acquisition decisions.

profit
1.

2.

Methodology

## Modeling problem Predict cumulative spends during first 2 years of accounts

life

Independent variables
Credit bureau data
Account application data

Training data
A sample data set of 300,000 credit card accounts

Segmentation
Segments based on credit bureau scores.
Multiple spend models.

Model details - I

## Log(Spend) used as response variable

Modeling equation
log(Spend) = + 1 X1 + 2 X2 + 3 X 3 +......
where , 1, are regression parameters

Model details - II

## Independent variables (X1 , X2 , ...)

Binning approach used
Increases model stability
Easier implementation
Capture non-linear relationships

## Correlated with spend but uncorrelated with Risk

Examples
Applicants monthly income
[\$0-\$2500] , [\$2500-\$5000] ,..

## Age of oldest revolving trade in months

[0-71] , [71-999]

Challenges
1.

2.

## Structural Change / Population drift

Revenue is highly correlated with risk

1.

2.

## Structural Change / Population drift

Revenue is highly correlated with risk

1.

2.

variables

Results

## Example - Model for

segment FICO (720-760)
Spend shows a positive
slope.
Charge-of line is
approximately horizontal.

FICO Only
FICO and
Spend score

Approval
rate(%)
90%
83%

Rate
Mean
(%) Spend (\$)
1.60% 15,032
1.60%

16,617

Conclusion

revenue model