Paper: arXiv 2507.23414

Authors: Oday Masoudi, Farhad Shahbazi, Mohammad Sharifi

Abstract

We employed Multifractal Detrended Fluctuation Analysis (MF-DFA) and Refined Composite Multiscale Sample Entropy (RCMSE) to investigate the complexity of Bitcoin, GBP/USD, gold, and natural gas price log-return time series. This study provides a comparative analysis of these markets and offers insights into their predictability and associated risks. Each tool presents a unique method to quantify time series complexity. The RCMSE and MF-DFA methods demonstrate a higher complexity for the Bitcoin time series than others. It is discussed that the increased complexity of Bitcoin may be attributable to the presence of higher nonlinear correlations within its log-return time series.

Complexity vs Empirical Score

  • Math Complexity: 9.5/10
  • Empirical Rigor: 3.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper is mathematically dense, employing advanced techniques like Multifractal Detrended Fluctuation Analysis (MF-DFA) and Refined Composite Multiscale Sample Entropy (RCMSE) with detailed derivations. However, it lacks backtesting, implementation code, or practical trading metrics, focusing instead on theoretical analysis of time series complexity.

Research Flowchart

  flowchart TD
  A["Research Goal: <br>Quantify Complexity of Financial Time Series"] --> B["Input Data: <br>Log-Returns of BTC, GBP/USD, Gold, Gas"]
  B --> C["Method 1: MF-DFA <br>Fractal Scaling & Multifractality"]
  B --> D["Method 2: RCMSE <br>Nonlinear Regularity & Predictability"]
  C --> E["Computational Analysis <br>Python (Numpy/PyEntropy)"]
  D --> E
  E --> F{"Key Findings"}
  F --> G["Bitcoin: Highest Complexity <br>Strong Nonlinear Correlations"]
  F --> H["Commodities/Forex: <br>Lower Complexity/Lower Entropy"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper applies Multifractal Detrended Fluctuation Analysis (MF‑DFA) and Refined Composite Multiscale Sample Entropy (RCMSE) to assess the complexity of Bitcoin, GBP/USD, gold, and natural gas log‑return series.

Source sentence
We employed Multifractal Detrended Fluctuation Analysis (MF-DFA) and Refined Composite Multiscale Sample Entropy (RCMSE) to investigate the complexity of Bitcoin, GBP/USD, gold, and natural gas price log-return time series. This research aims to apply Multifractal Detrended Fluctuation Analysis (MF-DFA) and Refined Composite Multiscale Sample Entropy (RCMSE) to overcome the limitations of traditional multiscale

Assumes 4

  • Time series must be sufficiently long for the multiscale sample entropy method to be reliable. data
    Source sentence
    Firstly, the time series must be sufficiently lengthy to be applicable in the MSE method.
  • Many financial time series are short, which can lead to inaccurate MSE results. data
    Source sentence
    Unfortunately, many financial time series are short, which complicates the acquisition of adequately lengthy data for this purpose. Consequently, the use of MSE may yield inaccurate results.
  • Logarithmic returns better capture market fluctuations and risk than raw price levels. model
    Source sentence
    In this study, the logarithmic returns of the data were used instead of the original price data, as they more accurately capture market fluctuations, which are indicative of risk.
  • The selected assets (cryptocurrency, forex, commodity, precious metal) provide a diverse set of volatility profiles and market drivers. market
    Source sentence
    The reason for choosing these assets is that they cover a spec-trum of asset types—cryptocurrencies, forex, commodities, and precious metals—each offering distinct volatility profiles, market drivers, and investor behaviors. This diver-sity helps us examine how complexity varies across assets with different economic roles and investor perceptions.

Data

  • Bitcoin, GBP/USD, Gold, Natural Gas daily price data · Yahoo Finance market-prices public
    up to 2024-12-02 · four assets (cryptocurrency, forex pair, gold, natural gas)
    Source sentence
    The data were sourced from the Yahoo Finance web-site, providing daily price reports.The datasets cover different time spans based on the availability of data for each asset, extending up to 2024-12-02. price data for Bitcoin, GBP/USD, gold, and natural gas, covering up to December 2, 2024.

Recognised sources: Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • RCMSE and MF‑DFA indicate higher complexity for Bitcoin compared to GBP/USD, gold, and natural gas. statistical
    Source sentence
    The RCMSE and MF-DFA methods demonstrate a higher complexity for the Bitcoin time series than others. It is discussed that the increased complexity of Bitcoin may be attributable to the presence of higher nonlinear correlations within its log-return time series.
  • Bitcoin exhibits the lowest entropy at small scales but higher entropy at larger scales, yielding the highest overall complexity (sum of entropy across scales). statistical
    Source sentence
    Bitcoin exhibits the lowest entropy at smaller scales but shows higher entropy at larger scales compared to the other assets. It also exhibits the highest overall complex-ity, calculated as the sum of entropy values across all scales.
  • Bitcoin and natural gas show wider probability density functions, reflecting higher volatility than GBP/USD and gold. statistical
    Source sentence
    The wider distribution of Bitcoin and natural gas indicates higher volatility in these assets. The overall findings of this research can be summarized as follows: Both the Bitcoin and Gas log-return time series exhibit higher volatility compared to GBP/USD and Gold, as reflected in their probability density function plots.
  • Bitcoin has the widest singularity spectrum, indicating a broad range of singularity exponents across time scales. statistical
    Source sentence
    Furthermore, Bitcoin exhibits the widest singularity spectrum, indicating a broad range of singularity exponents across different time scales.
  • All assets have Hurst exponents close to 0.5, suggesting a lack of linear autocorrelation. statistical
    Source sentence
    All assets demonstrate Hurst exponents close to 0.5, indicating a lack of linear dependencies in their data.

Checked by others

Supported by

  • Hidden Markov graphical models with state-dependent generalized hyperbolic distributions (2024)
    On the question: Which assets show the highest volatility as indicated by standard deviation or probability density width?
    Compare the findings

    This paper: Bitcoin and natural gas show wider probability density functions, reflecting higher volatility than GBP/USD and gold.

    That paper: Cryptocurrencies exhibit the highest volatility among the three asset classes, with the largest standard deviations and strong deviations from normality.

    Both findings rank Bitcoin (cryptocurrencies) as having the largest volatility; B also notes natural gas as high, while A compares crypto to two other classes (three total).

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (28)

  1. Permutation Transition Entropy: Measuring the Dynamical Complexity of Financial Time Series (2020)
  2. Entropy and Information Theory (2011)
  3. A Mathematical Theory of Communication (1948)
  4. Physiological Time-Series Analysis Using Approximate Entropy and Sample Entropy (2000)
  5. Permutation Entropy: A Natural Complexity Measure for Time Series (2002)
  6. Wavelet Entropy and Complexity–Entropy Curves Approach for Energy Commodity Price Predictability Amid the Transition to Alternative Energy Sources (2024)
  7. Multiscale Entropy Analysis of Complex Physiologic Time Series (2002)
  8. Multiscale Entropy Analysis of Traffic Time Series (2013)
and 20 more
  1. Multiscale Entropy Analysis of Biological Signals (2005)
  2. Entropy Measures for Biological Signal Analyses (2012)
  3. Multiscale Permutation Entropy of Physiological Time Series (2005)
  4. On Multiscale Entropy Analysis for Physiological Data (2006)
  5. Multiscale Entropy Analysis of Financial Time Series (2012)
  6. Who Dominate the Information Flowing Between Innovative and Traditional Financial Assets? A Multiscale Entropy-Based Approach (2024)
  7. Multi-Scale Approximate Entropy Analysis of Foreign Exchange Markets Efficiency (2012)
  8. Irregularity, Volatility, Risk, and Financial Market Time Series (2004)
  9. Approximate Entropy and Sample Entropy Algorithms in Financial Time Series Analyses (2022)
  10. Multiscale Sample Entropy and Cross-Sample Entropy Based on Symbolic Representation and Similarity of Stock Markets (2018)
  11. Modified Generalized Multiscale Sample Entropy and Surrogate Data Analysis for Financial Time Series (2018)
  12. Mosaic Organization of DNA Nucleotides (1994)
  13. Multifractal Detrended Fluctuation Analysis of Nonstationary Time Series (2002)
  14. Multifractal Analysis of the WTI Crude Oil Market, US Stock Market and EPU (2020)
  15. Inner Multifractal Dynamics in the Jumps of Cryptocurrency and Forex Markets (2024)
  16. The Multiscale Entropy Algorithm and Its Variants: A Review (2015)
  17. Analysis of Complex Time Series Using Refined Composite Multiscale Entropy (2014)
  18. Adaptive Computation of Multiscale Entropy and Its Application in EEG Signals for Monitoring Depth of Anesthesia During Surgery (2012)
  19. Multifractality and Non-Gaussianity of Eye Fixation Duration Time Series in Reading Persian Texts (2019)
  20. Tests for Skewness, Kurtosis, and Normality for Time Series Data (2005)

0 of 28 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.