Douglas Merrill, the CEO of ZestFinance, writes in Forbes that more data for making an underwriting decision is usually better; but if this data is fed into a traditional underwriting model, using logistic regression, it will not do much good; instead Merrill writes, “Lenders can make far more accurate predictions by loading all of that new data (along with the mountain of data they already have) into a machine learning model that uses hundreds of variables to make trillions of calculations to produce a better decision”; he also reminds us that no model is recession proof but machine learning models using huge amounts of data can at least act as an early warning system for an economic downturn. Source.