Bulk Classification of Trading Activity

David Easley, Marcos M. Lopez de Prado, Maureen O'Hara
2012 Social Science Research Network  
How best to discern trading intentions from market data? We examine the accuracy of three methods for classifying trade data: bulk volume classification (BVC), Tick Rule and Aggregated Tick Rule. We develop a Bayesian model of inferring information from trade executions, and show the conditions in which tick rules or bulk volume classification will predominate. Empirically, we find that Tick rule approaches and BVC are relatively good classifiers of the aggressor side of trading, but bulk
more » ... classifications are better linked to proxies of information-based trading. Thus, BVC would appear to be a useful tool for discerning trading intentions from market data. 2 4 See, for example, Lee and Ready (1991), Ellis, Michaely and O'Hara (2000), and Chakrabarty, Moulton and Shilko [2012]. 5 This problem is also particularly acute in the new swap trading markets. Dodd Frank currently requires reporting of non-block trades to the Swap Data Repository but current reporting rules allow a 30 minute delay. So there is no way to determine the correct order of trades. 6 See Hasbrouck (2013) for an excellent analysis of quote volatility and its implications. 7 See also Easley, et al. (2012a) where we apply this technique in estimating VPIN measures, and Gollapulli and Bose (2013) who use this approach to estimate order imbalances in swap markets. 8 We start the first bar with the second transaction in our sample, so that the algorithm has a 0 for initialization.
doi:10.2139/ssrn.1989555 fatcat:p56w3ge2lfbbdjic3vebscuuxu