The Conduits of Price Discovery: A Machine Learning Approach
EFA 2021; AFA 2022
48 Pages Posted: 14 Oct 2020 Last revised: 13 Jan 2022
Date Written: October 13, 2020
Abstract
When examining information flow into prices, empirical literature usually focusses on direct conduits such as order submissions. Meanwhile, theory suggests that market conditions should have substantial additional effects. Empirical analyses of such effects are methodologically challenging and therefore uncommon. We bypass these challenges using a machine learning technique that allows for multiple conditioning variables. Consistent with theory, price discovery is notably affected by such conditions as the state of the limit order book, price history, bid-ask spread, and order arrival frequency. The state of the book and price history stand out as conduits, whose magnitudes rival that of order submissions.
Keywords: price discovery, order submission strategies, machine learning
JEL Classification: G14, G15
Suggested Citation: Suggested Citation