Using Nonnegative Tensor Factorization to Find Market Activity Patterns

Summary

This work uses nonnegative tensor factorization (NTF) to identify trading activity patterns across multiple time scales in online financial markets. The method is first demonstrated with synthetic data, then applied to interbank transactions from Italy’s e-MID online market. It aims to expose latent patterns in trading activity and distinguish groups of banks whose behaviors include normal, early, or flash trading.

The authors also use the extracted patterns to examine how market activity changes during systemic disturbances, including the 2008 financial crisis. They report finding anomalies associated with endogenous and exogenous shocks and describe crisis-related trading modes. This is an exploratory analysis of a particular interbank market and historical dataset; the excerpt does not provide performance measures for trading strategies or establish that the discovered patterns generalize to other venues or periods.

Key ideas

• Nonnegative tensor factorization is applied to trading data at multiple time scales.
• Synthetic data is used to demonstrate the method before its application to real transactions.
• The e-MID analysis identifies distinct activity patterns among groups of banks.
• The framework is used to characterize unusual trading behavior during the 2008 crisis.
• The results describe patterns in one market and do not establish a trading strategy’s profitability.

Tags

# Extracting the multi-timescale activity patterns of online financial markets


# Extracting the multi-timescale activity patterns of online financial markets









Online financial markets can be represented as complex systems where trading dynamics can be captured and characterized at different resolutions and time scales. In this work, we develop a methodology based on non-negative tensor factorization (NTF) aimed at extracting and revealing the multi-timescale trading dynamics governing online financial systems. We demonstrate the advantage of our strategy first using synthetic data, and then on real-world data capturing all interbank transactions (over a million) occurred in an Italian online financial market (e-MID) between 2001 and 2015. Our results demonstrate how NTF can uncover hidden activity patterns that characterize groups of banks exhibiting different trading strategies (normal vs. early vs. flash trading, etc.). We further illustrate how our methodology can reveal "crisis modalities" in trading triggered by endogenous and exogenous system shocks: as an example, we reveal and characterize trading anomalies in the midst of the 2008 financial crisis.

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.