Crowdsourcing peer firms

Using Internet traffic patterns from the Securities and Exchange Commission Electronic Data-Gathering, Analysis, and Retrieval (EDGAR) website, we show that firms appearing in chronologically adjacent searches by the same individual are fundamentally similar on multiple dimensions. In fact, traffic-based peer firms identified by our algorithm significantly outperform peer firms based on six-digit Global Industry Classification Standard (GICS) groupings in explaining cross-sectional variations in base firms' stock returns, valuation multiples, forecasted and realized growth rates, research and development expenditures, and various other key financial ratios. Our results highlight the usefulness of EDGAR data, as well as the latent intelligence in search traffic patterns.