Bulk volume classification and information detection

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...

Full description

Saved in:
Bibliographic Details
Published in:Journal of banking & finance 2019-06, Vol.103, p.113-129
Main Authors: Panayides, Marios A., Shohfi, Thomas D., Smith, Jared D.
Format: Article
Language:English
Subjects:
Bulk volume
Classification algorithms
Informed trading strategies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0378-4266
1872-6372
DOI:10.1016/j.jbankfin.2019.04.001