How can you predict the likelihood of whether a borrower would pay back a loan?
To answer that question several economist studied the peer-to-peer lending site, Prosper. Potential borrowers on Prosper must write a brief description of why they need a loan and why they are good credit risk. Potential lenders then use that information to decide whether to provide the money. Overall, about 13 percent of borrowers defaulted on their loan.
The economists found that the language that potential borrowers use is a strong predictor of their probability of paying back. As Seth Stephens-Davidowitz writes:
Listed below are ten phrases the researchers found that are commonly used when applying for a loan. Five of them positively correlate with paying back the loan. Five of them negatively correlate with paying back the loan. In other words, five tend to be used by people you can trust, five by people you cannot. See if you can guess which are which.
God, promise, debt-free, minimum payment, lower interest rate, will pay, graduate, thank you, after-tax, hospital.
You might think—or at least hope—that a polite, openly religious person who gives his word would be among the most likely to pay back a loan. But in fact this is not the case. This type of person, the data shows, is less likely than average to make good on their debt.
Here are the phrases used in loan applications by people most likely to pay them back: debt-free, lower interest rate, after-tax, minimum payment, graduate.
And here are the phrases used by those least likely to pay back their loans: God, promise, will pay, thank you, hospital.
The key finding, as Stephens-Davidowitz notes, is that, “If someone writes ‘I promise I will pay back, so help me God,’ he is among the least likely to pay you back.”
This conclusion is a depressing, though not all that surprising, commentary on integrity in the modern age. The most untrustworthy are often the most likely to expect people to trust them based on nothing more than their pledge of honor or an oath to God. Most of us recognize that strangers are not going to trust us with their money just because we say we’re good God-fearing people.
Yet we should still be concerned about how the misuse of religious language will affect our own credit-worthiness. As Stephens-Davidowitz points out:
A consumer looking for a loan in the near future might not merely have to worry about her financial history but also her online activity. And she may be judged on factors that seem absurd—whether she uses the phrase “Thank you” or invokes “God,” for example. Further, what about a woman who legitimately needs to help her sister in a hospital and will most certainly pay back her loan afterwards? It seems awful to punish her because, on average, people claiming to need help for medical bills have often been proven to be lying. A world functioning this way starts to look awfully dystopian.
Big Data is exploding. It has helped us find the websites we want to see, the people we want to talk to, the jobs we want to apply for.
But the power of Big Data raises a host of ethical questions. In particular: Do corporations have the right to judge our fitness for their services based on abstract but statistically predictive criteria not directly related to those services?