Re: DM: Credit Score

[Andrew A. Kramer]

Jerry,

I agree with what Abraham and others have mentioned about
time-to-event / failure time bias. There might be an
additional factor at work, though. Your assumption is
that long-term customers would be more creditworthy.
The opposite might be true due to a mobility factor,
i.e. professionals with a high mobility rate are obstensibly
more affluent. Thus the effects due to right-censoring
mentioned by Lynd Bacon might be affected by an interaction
with annual income.

In any event I would strongly suggest digging deeper into your
data to learn about additional factors which may differentiate your 
customers.
The answer is never as straightforward as we would like.

Sincerely,

Andrew A. Kramer, Ph.D.
Future Analytics, Inc.
 

Musial Jerry wrote:

> Hi,
>         I am looking for help/resources related to credit scoring of
> 'existing' customers.  In particular, I am interested in how 
>researchers
> deal with tenure as it relates to whether or not one of our 
>customers will
> continue to pay their bills in a timely manner.  We intuitively 
>feel that
> the longer a customer has been with us (and paying us) the better 
>credit
> risk.  However, my initial results show that the longer a person 
>has been
> with us, the odds of his not paying increase.  Anyone have any 
>ideas?
>
> Thanks
> Jerry Musial
> BellSouth Cellular