Recurrence Plot and Recurrence Quantification Analysis Techniques for Detecting a Critical Regime. Examples from Financial Market Indices

TL;DR

This paper demonstrates how Recurrence Plot and Recurrence Quantification Analysis can detect critical regimes in financial markets, such as bubbles, before they burst, using real market data from DAX and NASDAQ indices.

Contribution

It introduces practical methods for applying RP and RQA to identify early warning signs of financial bubbles in non-linear, non-stationary market data.

Findings

RP and RQA detect critical regimes before bubble bursts

NASDAQ bubble initial time estimated to be October 19, 1999

Methods applicable to real financial data for early warning signals

Abstract

Recurrence Plot (RP) and Recurrence Quantification Analysis (RQA) are signal numerical analysis methodologies able to work with non linear dynamical systems and non stationarity. Moreover they well evidence changes in the states of a dynamical system. We recall their features and give practical recipes. It is shown that RP and RQA detect the critical regime in financial indices (in analogy with phase transition) before a bubble bursts, whence allowing to estimate the bubble initial time. The analysis is made on DAX and NASDAQ daily closing price between Jan. 1998 and Nov. 2003. DAX is studied in order to set-up overall considerations, and as a support for deducing technical rules. The NASDAQ bubble initial time has been estimated to be on Oct. 19, 1999.