Persistent Long Memory in Foreign Exchange Order Flow

Summary

This study examines whether order flow in the foreign exchange spot market has long memory, meaning that dependence in its behavior persists over extended periods. It analyzes three liquid currency pairs on a highly active electronic platform, using data that allows stable estimates within individual trading days rather than requiring observations to be pooled across days.

The study reports Hurst exponents near 0.7 for all three pairs on each sampled day, with similar findings when data spans multiple days. It also tests whether structural breaks could explain the apparent persistence and rejects that explanation in favor of genuine long memory. The findings suggest that this property continues across daily boundaries. The document provides no detail on the platform, sample dates, estimation procedures, or practical trading applications, so the reported result should be understood as an empirical finding for the studied data rather than a guarantee about other venues or periods.

Key ideas

• Order flow in the three studied FX spot pairs shows strong long memory.
• The estimated Hurst exponent is approximately 0.7 across pairs and sampled days.
• Results remain similar when observations span more than one trading day.
• Tests reject structural breaks as the explanation for the apparent persistence.

Tags

# The Long Memory of Order Flow in the Foreign Exchange Spot Market


# The Long Memory of Order Flow in the Foreign Exchange Spot Market









We study the long memory of order flow for each of three liquid currency pairs on a large electronic trading platform in the foreign exchange (FX) spot market. Due to the extremely high levels of market activity on the platform, and in contrast to existing empirical studies of other markets, our data enables us to perform statistically stable estimation without needing to aggregate data from different trading days. We find strong evidence of long memory, with a Hurst exponent of approximately 0.7, for each of the three currency pairs and on each trading day in our sample. We repeat our calculations using data that spans different trading days, and we find no significant differences in our results. We test and reject the hypothesis that the apparent long memory of order flow is an artifact caused by structural breaks, in favour of the alternative hypothesis of true long memory. We therefore conclude that the long memory of order flow in the FX spot market is a robust empirical property that persists across daily boundaries.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.