Using Crowd-Sourced Earnings Estimates in an Automated Trading Strategy

The purpose of our research in this instance was to determine if there are opportunities to generate alpha in US equities, using crowd-sourced earnings estimates data as a basis for overnight market movement prediction. We show how with simple mathematical techniques, we can identify pricing inefficiencies which we can exploit to generate excess returns. We take the theory of stock market overreaction as a basis for our model.

Read the Report

We began our research with a hypothesis based on the relative optimism or pessimism of short term versus long term Estimize estimates. We postulated that relatively higher optimism in short-term earnings forecasts compared to long-term forecasts leads to negative price movement after the actual earnings announcement. In this case, the announcement will probably miss the short term expectation, and the stock price will fall. On the other hand, where long term optimism is followed by short term, pre-announcement, pessimism then this predicts positive stock price movement.

We implemented the strategy in the Deltix QuantOffice research platform and performed multiple experiments testing our initial hypothesis including the construction of dollar-neutral and beta-neutral portfolios to isolate the strategy performance from that of the market. This strategy in its various forms, including un-hedged and hedged, generated attractive risk-adjusted returns. 

Read the Report