Hacker News Reader

Comment by salomonk_mur | Hacker News Reader

Besides the security part, many companies us that data in their Machine Learning models. I've used it myself extensively over the past 10 years in Fintech.

As a small tidbit of information, did you know iPhone users are ~40% less likely to default on a small loan than Android users (at least in my country).

And the differences go all the way to specific models, OS versions, installed apps, IP range, browser of choice...

View on HN

Sure but isn’t this due to income disparities between iPhone and android users? Android is available in more cheaper models so poorer groups include more android users. A bank is going to care more about proof of income than what phone OS you use, will they not?

You can normalize data in order to isolate the effects of a given variable. Essentially, you just change the question from 'Are android users more likely to default on a loan?' to 'Given that all other factors are roughly equal, are android users significantly more likely to default on a loan' and then you do some complex math I don't understand to determine whether income disparities are actually a factor or if the model phone you own affects your likelihood of repaying a loan without regard to your income.

Think about it this way - banks are prohibited from asking certain questions. However, if they have a strong correlation with another factor, then they can ask that and get the same result.

Banks are absolutely allowed to ask for your income and credit history. Why would phone model be a better signal than credit score, for loan defaults?

Reply on news.ycombinator.com