Bulk volume classification and information detection
Date
2019Author
Panayides, Marios A.Shohfi, Thomas D.
Smith, Jared D.
ISSN
0378-4266Source
Journal of Banking & FinanceVolume
103Pages
113-129Google Scholar check
Metadata
Show full item recordAbstract
Using European stock data from two different venues and time periods for which we can identify each trade's aggressor, we test the performance of the bulk volume classification (Easley et al. (2016) BVC) algorithm. BVC is data efficient, but may identify trade aggressors less accurately than “bulk” versions of traditional trade-level algorithms. BVC-estimated trade flow is the only algorithm related to proxies of informed trading, however. This is because traditional algorithms are designed to find individual trade aggressors, but we find that trade aggressor no longer captures information. Finally, we find that after calibrating BVC to trading characteristics in out-of-sample data, it is better able to detect information and to identify trade aggressors. In the new era of fast trading, sophisticated investors, and smart order execution, BVC appears to be the most versatile algorithm.