LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (April 2005, week 3)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Fri, 15 Apr 2005 09:56:07 -0700
Reply-To:     "Choate, Paul@DDS" <pchoate@DDS.CA.GOV>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Choate, Paul@DDS" <pchoate@DDS.CA.GOV>
Subject:      Re: Question about FICO credit score
Comments: To: Hari Nath <hari_s_nath@YAHOO.COM>

Hari -

http://www.hsh.com/pamphlets/aboutfico.html

A Model of You Scoring models like the one developed by Fair, Isaac have always been shrouded in mystery, especially when it comes to specifics. Generally speaking, though, they utilize your credit history, income, outstanding debt and debt utilization over the years, access to credit, and other indicators of your financial behavior to determine how likely you are to pay your bills on time, or if at all.

A numerical score is then developed, typically ranging from 300 to 850, with the low end of the scale indicating a poor credit risk. This can tell a lender whether or not he'll lend to you. For example, a credit score of 620 is frequently cited as a "cutoff point" for loans which can be funded by Fannie Mae or Freddie Mac. Below that, and you're usually off into the private "sub-prime" market, where rates are higher.

What's in your score? According to Fair, Isaac, the breakdown of your FICO score is as follows:

35% of the score is determined by payment histories on your credit accounts, with recent history weighted a bit more heavily than the distant past; 30% is based upon the amount of debt you have outstanding with all creditors; 15% is produced on the basis of how long you've been a credit user (a longer history is better if you've always made timely payments); 10% is comprised of very recent history, based on your efforts to obtain loans or credit lines in the past few months; 10% is calculated from the mix of credit you hold, including installment loans (like car loans), leases, mortgages, credit cards, etc. Other models being employed are sure to utilize these in various weightings, plus other data that may be fed in to the model. These might include your address or zip code, how often you've moved and other public and private information about you.

What It Means So, now you've got a score. Why should you care? Increasingly, lenders are trying to fund loans with prices (rates, fees and terms) that more precisely match your risk. In theory, someone with a 850 score should get much better rates than someone with a 650 score.

So far, though, it hasn't exactly worked that way, at least not that precisely. There are several grades of credit which have arisen, most notably below the 620 line (A-, B, C, D). But above the 620 line, everyone pretty much pays the same. Lenders can penalize you for poorly managing credit, but don't much reward you for effectively and wisely managing your debt, at least so far.

hth

Paul Choate DDS Data Extraction (916) 654-2160

-----Original Message----- From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of Hari Nath Sent: Friday, April 15, 2005 9:22 AM To: SAS-L@LISTSERV.UGA.EDU Subject: Question about FICO credit score

Hi all, This is not strictly a SAS question. I was curious to know about the credit score rating system. Noramally, the Credit score ranges from 300 to 850 as showed by most credit card companies and i knew that they use SAS for analyzing business data. Can somebody tell me on what critical factors they consider for deciding the credit score rating pattern and what statistical analysis they use to achieve the credit score rating.

Any suggestions are welcome,

Thanks SAS-L,

Regards, Hari


Back to: Top of message | Previous page | Main SAS-L page