The Conference Board uses cookies to improve our website, enhance your experience, and deliver relevant messages and offers about our products. Detailed information on the use of cookies on this site is provided in our cookie policy. For more information on how The Conference Board collects and uses personal data, please visit our privacy policy. By continuing to use this Site or by clicking "OK", you consent to the use of cookies. 
Text-Based High Latency, Low Frequency Signal Analysis and Cohort Equity Pricing

Latency assumptions in algorithm-based equity trading strategies have predisposed research towards low-latency optimization. To derive signal arbitrage, traders have taken advantage of fluidity in responses within the efficient market hypothesis (EMH). We study the effect of high latency corporate communication on equity price. Specifically, we examine trading advantages within patent-holding Russell 1000 competitive cohorts using (1) a genetic algorithm (GA) augmented with support vector regression (SVR) (2) as well as particle swarm optimization (PSO). Then we measure effect modeling with dynamic time warping (DTW) for performance estimation using random forest regressors (RFR). We quantify the equity effect of novel analysis of unstructured text in issued patents.

This working paper is complimentary.