Bart Baesens

Big Data for Credit Scoring: Opportunities and Challenges

NO RATINGS
View Comments: Newest First | Oldest First | Threaded View
magneticnorth0
User Rank
Data Doctor
Re: Pros and Cons
magneticnorth0   10/31/2016 7:40:13 PM
NO RATINGS
That'd be a good use of socil media data, rbaz. I'd hope it wouldn't influence any more than 10% of the score.

Jamescon
User Rank
Editor
Re: Pros and Cons
Jamescon   10/18/2016 8:41:08 AM
NO RATINGS
@Lyndon. I think those people who post a constant stream of kitten photos might actually be poor credit risks. After all, if they spend that much time on Facebook they probably don't have real jobs.

Joking aside, social media activity for credit evaluations and other personal business, like insurance, would only be one of many factors in an evaluation. I can't imagine it having a great impact on the final score unless social posts reflected something like a disproportionate interest in gambling or driving 120 mph

Lyndon_Henry
User Rank
Blogger
Re: Pros and Cons
Lyndon_Henry   10/17/2016 10:14:37 PM
NO RATINGS
..

Kq4ym writes

It may become a bit sticky trying to figure out what many social media venues tell about a propect of customer.



 

And in his blog article Bart Baesens writes that "customers can easily buy Twitter followers to boost their credit scores."

I had no idea that bulking up my Twitter following would help to boost my credit score. Makes me wonder how many Twitterati out there have been posting cute kitten photos and other fluff just to try to attract more followers so they could qualify for a mortgage on a bigger house ...

 

kq4ym
User Rank
Data Doctor
Re: Pros and Cons
kq4ym   10/17/2016 2:34:23 PM
NO RATINGS
It may become a bit sticky trying to figure out what many social media venues tell about a propect of customer. And as pointed out  "Many countries prohibit the use of gender, age, marital status, national origin" as identifiers which may pose benefits and hindrances to the customers and busiiness interests.

rbaz
User Rank
Data Doctor
Re: Pros and Cons
rbaz   10/17/2016 11:06:31 AM
NO RATINGS
@tinym, I see social media data as an enhancer. It gives a source of validation and affirmation of a,profile not a definite characterization of the subject. A bid iffy and discomforting as far as I am concerned.

Michelle
User Rank
Data Doctor
Re: Pros and Cons
Michelle   10/16/2016 5:22:38 PM
NO RATINGS
I see an issue using social media data in this way - How do they account for accounts that use a persona rather than represent an actual person online? Many people present a narrow version of the true self online so as not to reveal much about them in real life.

Jamescon
User Rank
Editor
Pros and Cons
Jamescon   10/12/2016 4:14:06 PM
NO RATINGS
@Bart

Nice job laying out the benefits and challenges, really for the lender and the consumer. For the consumer the benefit is that they aren't being judged on just one or two data points. The irony is that the additional data points could have a negative impact on them if, for example, their social media activity reflects recklessness.

Information Resources
More Blogs from Bart Baesens
Organizations that are considering outsourcing options for their analytics initiatives need to take a critical look and plan carefully. Many companies find themselves opting for only limited outsourcing.
Radio Show
A2 Conversations
UPCOMING
Jessica Davis
Analytics: Make the Most of Data's Potential in 2017


1/19/2017   REGISTER   0
ARCHIVE
Jessica Davis
A2 Radio: Can You Trust Your Data?


12/20/2016  LISTEN   70
ARCHIVE
James M. Connolly
Retail Analytics: See Where Style Meets Statistics


12/6/2016  LISTEN   53
ARCHIVE
James M. Connolly
Why the IoT Matters to Your Business


11/29/2016  LISTEN   45
ARCHIVE
James M. Connolly
Will Data and Humans Become Friends in 2017?


11/22/2016  LISTEN   40
ARCHIVE
James M. Connolly
We Can Build Smarter Cities


10/20/2016  LISTEN   31
ARCHIVE
James M. Connolly
Visualization: Let Your Data Speak


10/13/2016  LISTEN   70
ARCHIVE
James M. Connolly
How Colleges and Tech Are Grooming Analytics Talent


9/7/2016  LISTEN   56
ARCHIVE
James M. Connolly
How Machine Learning Takes Handwriting Recognition to New Levels


8/25/2016  LISTEN   40
ARCHIVE
AllAnalytics
A Look at Tomorrow's Data Scientist


8/9/2016  LISTEN   83
ARCHIVE
James M. Connolly
Analytics and the Making of a President


7/21/2016  LISTEN   76
Information Resources
Quick Poll
Quick Poll
About Us  |  Contact Us  |  Help  |  Register  |  Twitter  |  Facebook  |  RSS