The Null Device

Financial anthropometry

The 19th-century idea of criminal anthropometry may be dead, but its spirit keeps reemerging. A study, on a peer-to-peer lending site, suggests that one can predict a person's creditworthiness from a photograph of their face:
The team recruited 25 Mechanical Turk workers and asked them to assess pictures of potential borrowers that had been posted on Prosper.com. In particular, they were asked to rate, on a scale of one to five, how trustworthy these people looked, and to estimate the percentage probability that each individual would repay a $100 loan. They were also asked to make several other assessments, such as the individual’s sex, race, age, attractiveness and obesity. The 25 results for each photograph were then averaged and analysed.
The researchers looked at 6,821 loan applications, 733 of which were successful. Their first finding was that the assessments of trustworthiness, and of likelihood to repay a loan, that were made by Mechanical Turk workers did indeed correlate with potential borrowers’ credit ratings based on their credit history. That continued to be so when the other variables, from beauty to race to obesity, were controlled for statistically. Shifty physiognomy, it seems, is independent of these things.
That shiftiness was also recognised by those whose money was actually at stake. People flagged as untrustworthy by the Mechanical Turks were less likely than others to be offered a loan at all. To have the same chance of getting one as those deemed most trustworthy they were required to pay an interest rate that was, on average, 1.82 percentage points higher, even when the effects of historical creditworthiness were statistically eliminated.
While the exact attributes that make someone look "shifty" have not been isolated, it could be only a matter of time until someone devises an algorithm for deriving a credit score from a face and implements it, either behind a CCTV camera or in a back office, fed by the numerous images of an individual which can be harvested from the intercloud.

Of course, it may not be the case that some sets of facial features correlate to financial unreliability. Another explanation could be that there are some sets of features which are seen as correlating to financial unreliability. Whether or not these features have any causal connection to the temperament, psychology or moral fibre of their bearer could be irrelevant; if people consistently think you look shifty, they'll treat you as if you were, even if you weren't originally.

There are 1 comments on "Financial anthropometry":

Posted by: Greg Sat Mar 21 10:00:43 2009

It's intriguing that people might be able to detect trustworthiness by facial photograph alone. The original paper (Duarte et al., 'Trust and Credit') is mostly boring economics-department stuff about markets - the interesting bit is left to one paragraph and two references. A good evol-psych ref is Brown et al. Are there nonverbal cues to commitment?' (available in Google Scholar), especially experiment three where subjects detected altruism via facial expression alone. Note that expression is the malleable aspect of facial appearance. As you point out above, it's a separate question whether cheaters and altuists are born or made. There is evidence for the former, but it's easy to imagine mechanisms for the latter.