Bulk Classification of Trading Activity
Cornell University - Department of Economics
Marcos Lopez de Prado
Hess Energy Trading Company; Lawrence Berkeley National Laboratory; RCC at Harvard University
Cornell University - Samuel Curtis Johnson Graduate School of Management
March 20, 2013
Johnson School Research Paper Series No. 8-2012
In this paper, we investigate the accuracy and efficacy of two methods for classifying trades, the tick rule and the bulk volume classification methodology. Our results indicate that the tick rule is a relatively good classifier of the aggressor side of trading, both for individual trades and in bulk. Bulk volume is shown to also be accurate for classifying buy and sell trades, but unlike the tick rule, bulk volume can also explain trading ranges for high-low prices. Thus, bulk volume would appear to be a useful tool for discerning trading intentions from market data.
Number of Pages in PDF File: 66
Keywords: Trade Classification, Bulk Volume Classification, flow toxicity, volume imbalance, market microstructure
JEL Classification: C02, D52, D53, G14working papers series
Date posted: January 23, 2012 ; Last revised: April 2, 2013
© 2013 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo8 in 0.360 seconds