[stevejb]

Using the Propser.com data set (a peer-to-peer lending market), I used MTurk to analyze the images of people applying for a loan. This was used in a finance research project with 3 University of Washington professors of Finance.

The idea was that the Prosper data set contained all of the information that a lending officer would have, but they also had user-submitted pictures. We wanted to see if there was value in the information conveyed in the pictures. For example, if they had a puppy or a child in the picture, did this increase the probability that the loan would get funded? That sort of thing. It was a very fun project!

Paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1343275

[hiddencost]

Yikes. Have you ever considered that you were hurting people?

[xwowsersx]

How so? Read the paper. The methodology was entirely observational. They did not intervene in the prosper.com loan market or interact with the borrowers. If anything, the paper identified a form of bias that exists in the real world, namely that people commonly "perceived" as less trustworthy are penalized despite their actual creditworthiness.

[akerl_]

The paper is a study of an existing market. They looked at data about people who had requested loans and data about which of those loans were funded, with the intent of seeing whether or not lenders were being biased by requester photos. They found that they were.

Say more about how studying that bias is hurting people?

[stevejb]

Yeah, whenever there are human subjects there is an IRB which is necessary. But, beyond that, we didn't participate in the market in any way. We wanted to see if there was bias there, and how much of it. I think I may have used the word 'value' in a bad way in my description. Not 'value' as in 'can we exploit people?' but value as in statistical significance. E.g. if you applied for a loan and your profile picture contained yourself with a child, did that help you, hurt you, or was it neutral?