Researchers asked people on Amazon’s Mechanical Turk to look at pictures of loan applicants on the peer-to-peer lending site Prosper.com. The Mechanical Turkers rated whether the faces looked trustworthy. The ratings, it turned out, correlated with the loan applicants’ credit histories.
Here’s a snip from The Economist’s story:
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.
