In this article, we examine whether incorporating complexity measures as features in deep learning (DL) algorithms enhances their accuracy in predicting forex market volatility. Our approach involved the gradual integration of complexity measures alongside traditional features to determine whether their inclusion would provide additional information that improved the model’s predictive accuracy. For our analyses, we employed recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent units (GRUs) as DL model architectures, while using the Hurst exponent and fuzzy entropy as complexity measures. All analyses were conducted on intraday data from four highly liquid currency pairs, with volatility estimated using the Range-Based estimator. Our findings indicated that the inclusion of complexity measures as features significantly enhanced the accuracy of DL models in predicting volatility. In achieving this, we contribute to a relatively unexplored area of research, as this is the first instance of such an approach being applied to the prediction of forex market volatility. Additionally, we conducted a comparative analysis of the three models’ performance, revealing that the LSTM and GRU models consistently demonstrated a superior accuracy. Finally, our findings also have practical implications, as they may assist risk managers and policymakers in forecasting volatility in the forex market.
7 September 2022 in International Review of Financial Analysis
This article investigates the dynamical complexity and fractal characteristics changes of the Bitcoin/US dollar (BTC/USD) and Euro/US dollar (EUR/USD) returns in the period before and after the outbreak of the COVID-19 pandemic. More specifically, we applied the asymmetric multifractal detrended fluctuation analysis (A-MF-DFA) method to investigate the temporal evolution of the asymmetric multifractal spectrum parameters. In addition, we examined the temporal evolution of Fuzzy entropy, non-extensive Tsallis entropy, Shannon entropy, and Fisher information. Our research was motivated to contribute to the comprehension of the pandemic’s impact and the possible changes it caused in two currencies that play a key role in the modern financial system. Our results revealed that for the overall trend both before and after the outbreak of the pandemic, the BTC/USD returns exhibited persistent behavior while the EUR/USD returns exhibited anti-persistent behavior. Additionally, after the outbreak of COVID-19, there was an increase in the degree of multifractality, a dominance of large fluctuations, as well as a sharp decrease of the complexity (i.e., increase of the order and information content and decrease of randomness) of both BTC/USD and EUR/USD returns. The World Health Organization () announcement, in which COVID-19 was declared a global pandemic, appears to have had a significant impact on the sudden change in complexity. Our findings can help both investors and risk managers, as well as policymakers, to formulate a comprehensive response to the occurrence of such external events.
The COVID-19 pandemic has had an unprecedented impact on the global economy and financial markets. In this article, we explore the impact of the pandemic on the weak-form efficiency of the cryptocurrency and forex markets by conducting a comprehensive comparative analysis of the two markets. To estimate the weak-form of market efficiency, we utilize the asymmetric market deficiency measure (MDM) derived using the asymmetric multifractal detrended fluctuation analysis (A-MF-DFA) approach, along with fuzzy entropy, Tsallis entropy, and Fisher information. Initially, we analyze the temporal evolution of these four measures using overlapping sliding windows. Subsequently, we assess both the mean value and variance of the distribution for each measure and currency in two distinct time periods: before and during the pandemic. Our findings reveal distinct shifts in efficiency before and during the COVID-19 pandemic. Specifically, there was a clear increase in the weak-form inefficiency of traditional currencies during the pandemic. Among cryptocurrencies, BTC stands out for its behavior, which resembles that of traditional currencies. Moreover, our results underscore the significant impact of COVID-19 on weak-form market efficiency during both upward and downward market movements. These findings could be useful for investors, portfolio managers, and policy makers.
In the frame of complex systems research, methods used to quantitatively analyze specific dynamic phenomena are often used to analyze phenomena from other disciplines on the grounds that are governed by similar dynamics. Technical analysis is considered the oldest, currently omnipresent, method for financial markets analysis, which uses past prices aiming at the possible short-term forecast of future prices. This work is the first attempt to explore the applicability of technical analysis tools on disturbance storm time () index time series, aiming at the identification of similar features between the time series during magnetic storms (MSs) and asset price time series. We employ the following financial analysis tools: simple moving average (), Bollinger bands, and relative strength index (), formulating an analysis approach based on various features, appearing in financial time series during high volatility periods, that could be found during the different phases of the evolution of an MS (onset, main development, and recovery phase), focusing on the temporal sequence they occur. The applicability of the proposed analysis approach is examined on several MS events and the results reveal similar behavior with the financial time series in high volatility periods. We postulate that these specialized data analysis methods could be combined in the future with other statistical and complex systems time series analysis methods in order to form a useful toolbox for the study of geospace perturbations related to natural hazards.