Testing the Bulk Volume Classification Algorithm
54 Pages Posted: 20 Feb 2021
Date Written: December 2020
We document that the existing evidence that bulk volume trade classification (BVC) measures informed trading arises largely due to mis-specified tests. Simulations show that these tests detect spurious relationships in data containing only uninformed liquidity trades. We also assess the performance of BVC order imbalances in the NASDAQ HFT dataset, showing that BVC order imbalances underperform conventional order imbalance measures in detecting informed trading. The component of order flow designated by BVC as passive informed trading fails to predict returns with the correct sign. On balance, our evidence supports the use of conventional order imbalance measures to identify informed trading.
Keywords: Market Microstructure, Informed Trading, High-frequency Trading, Bulk Volume Classification, Trade classification, Order Imbalances, Simulation, Estimator Properties
JEL Classification: C18, G10, G14
Suggested Citation: Suggested Citation