Screening Off – The right answer for thinking about model bias - a podcast by Gary Angel
from 2021-01-31T22:10:42.023393
::
::
The Measurement Minute by Gary Angel
You can’t use a protected variable in a model and you shouldn’t use a proxy for it either. But how do you decide what’s a proxy and what isn’t given that age, race and gender are massively correlated to a wide range of likely predictive variables? The answer lies in a generally useful concept in data science: screening off.
Further episodes of The Measurement Minute
Further podcasts by Gary Angel
Website of Gary Angel