A Data Science Central Community
I was wondering if anyone has found any success in using external macro data (i.e. per capita income, unemployment rate, foreclosure data) in building out credit models. For the record, I model for small business loans where the personal credit data of the owner along with verifiable business information is typically most relevant to predicted performance.
How do you define macro data? macro/micro as defined by Economics? Strictly speaking, industry specific data, e.g. foreclosure is microeconomic data.
It depends on whether the data you are using has any relevancy to small business owners. if most of your target sample centered in IT sector, any indicators to do with IT will be relevant. For certain economies, small business has an irrelevant share of the macro-economy, making the lack of predictive power by the macro-data for the small business segment.