Dynamic text-based industry classifications and endogenous product differentiation

"We study how firms differ from their competitors using new dynamic measures of product differentiation based on novel text based analysis of 50,673 product descriptions from firm 10-K statements filed yearly with the Securities Exchange Commission. This year-by-year set of firm product differentiation measures allows us to generate a set of dynamic industry classifications and new measures of industry structure and competition. Competitiveness and market structure measures based on these new classifications better correlate with firm profitability than do classifications based on SIC or NAICs. Using these new dynamic industry classifications, we examine endogenous product differentiation. We show that firms use R&D and advertising to differentiate themselves from competitors and increase their profitability"--National Bureau of Economic Research web site.