Life expectancy, earnings, education of the populations at large? That isn't evidence of racism, these populations don't engage in remotely comparable behaviors, have remotely comparable histories, or cultures. I'm talking about situations that are specifically and actively differentiated _due to_ race alone.

If Asians are approved for bank loans at higher rates than black people, that doesn't mean that it's harder to get a loan as a black person than it is as an Asian person. What I am talking about is that if you were a black person with a given credit score, with a given salary, capital, etc, and you were less likely to get a loan than an Asian with exactly the same criteria, only then would this be you being discriminated against on the basis of your race.

When talking about discrimination against Asians, the examples I'm giving are ones in which the Asian individual can meet or surpass all of the objective criteria necessary for an outcome, but their race is the active factor that harms them. Last I read, if Ivy Leagues were unaware of any racial identifiers, and simply had the objective criteria of SAT scores, GPA, extra-curricular achievements, Asians would make up 40% of their universities. When we say that black Americans have a shorter life expectancy, earnings, or education do you understand how that isn't remotely comparable? You haven't controlled for anything. If you say that there is an epidemic of black students not being admitted to schools despite having identical qualifications as other applicants, only then are you bringing up a comparable example to what I'm discussing.

> if you were a black person with a given credit score, with a given salary, capital, etc, and you were less likely to get a loan than an Asian with exactly the same criteria,

This experiment has been done multiple times, and yes this is exactly what happens. In business loans, home loans, ...

See e.g. https://www.huduser.gov/publications/pdf/aotbe.pdf for paired tests comparing white/black and white/hispanic shoppers, done by HUD. I have seen similar tests in the past which asian shoppers, but you’ll have to search around a bit.

That study looks like it might do a good job of controlling for the relevant factors, although the thing that seems to be the most difficult to control for is credit. It makes some references to credit history, but the most rigorous study I had seen in the past (https://www.revealnews.org/article/for-people-of-color-banks...) had failed to take credit history into account, which the lenders then claimed was the source of the discrepancy that they had found. I think with the pair model in the study you referenced, it would be feasible to have applicants paired together based off of information they have provided themselves, including credit, although I'd like to hear more about it/what tolerances they allowed for/what kind of discrepancies were found in the outcomes.

I admit that I'm also disinclined to believe that lenders are in any way concerned with making decisions according to any other criteria than what would return them the highest profits, but I will take a look in greater detail at the study you referenced. It seems exceedingly idiotic to me that lenders would take a datapoint as arbitrarily useless as race into consideration, but I suppose the same could be said for universities taking less qualified applicants for the same reason. Obviously, this would be precisely the sort of discrimination that I would take serious issue with, if present, so I'll be make sure to look into the study. Thanks for the reference. There is a LOT of piss-poor analysis into this issue that controls for virtually nothing, and typical reporting will very often simply differentiate average loan sizes to people of ethnicities, likelihood to get loan approvals, etc, as just baseline differences between populations.

I understand if lenders want to keep their evaluation process secretive, as there could theoretically be a competitive advantage in the manner in which they calculate risk, but I think that the way this stuff is audited could be done in a much clearer fashion. Maybe something like "lenders have to publicly disclose all features they take into consideration in their approval model." And then some independent audit should run some random sample set of their approvals through a sensible model, and then the banks would have to justify what it is in their model that produces any major differences in approval rates. The mechanisms in place to make sure that this stuff is being done appropriately seem like they're horribly designed.