Quantifying Cryptocurrency Unpredictability: A Comprehensive Study of Complexity and Forecasting
This paper analyzes cryptocurrency time-series unpredictability using complexity and forecasting methods, revealing noise-like behavior and limitations of advanced models.
What it examines
The paper studies cryptocurrency price unpredictability by analyzing time series of major coins. It uses complexity measures like permutation entropy and the Complexity-Entropy plane, alongside statistical, machine learning, and deep learning models for forecasting. The goal is to assess if crypto data resembles random noise.
What it concludes
The study shows that cryptocurrency series behave like noise, with simple statistical methods often outperforming complex models. These findings imply challenges for crypto forecasting and offer insights for risk management and trading strategy design. Future work should include additional factors to improve predictions.
Evidence objects
Researchers reveal that cryptocurrency time-seriesLitecoin, Binance Coin, Bitcoin, Ethereum, and XRPdisplay extreme unpredictability, closely mimicking Brownian motion, with advanced complexity-entropy and spectral techniques unequivocally exposing behavior similar to diverse colored noises.
key_findings bullet 1 · key_findings · validation V0
Surprisingly, nave forecasting models remarkably outperform sophisticated statistical, machine learning, and deep learning methods across various forecast horizons, challenging conventional wisdom and emphasizing inherent difficulties in predicting cryptocurrency price movements.
key_findings bullet 2 · key_findings · validation V0
Integrating complexity measures with model comparisons, the study introduces novel metrics such as the permutation Jensen-Shannon distance, using 2020--2023 data and a rolling-window strategy, despite relying solely on univariate analysis.
key_findings bullet 3 · key_findings · validation V0
This unique empirical analysis combines established complexity measures (e.g., permutation entropy and $CH\text{-}plane$) with various forecasting models to examine cryptocurrency time-series. Its counterintuitive findingnaive models outperform advanced machine and deep learning techniqueschallenges expected norms, revealing substantial challenges in market prediction while offering an impressively novel, incremental yet impactful methodological integration.
key_findings bullet 4 · key_findings · validation V0
Raw abstract and provenance
Abstract: This paper offers a thorough examination of the univariate predictability in cryptocurrency time-series. By exploiting a combination of complexity measure and model predictions we explore the cryptocurrencies time-series forecasting task focusing on the exchange rate in USD of Litecoin, Binance Coin, Bitcoin, Ethereum, and XRP. On one hand, to assess the complexity and the randomness of these time… ▽ More This paper offers a thorough examination of the univariate predictability in cryptocurrency time-series. By exploiting a combination of complexity measure and model predictions we explore the cryptocurrencies time-series forecasting task focusing on the exchange rate in USD of Litecoin, Binance Coin, Bitcoin, Ethereum, and XRP. On one hand, to assess the complexity and the randomness of these time-series, a comparative analysis has been performed using Brownian and colored noises as a benchmark. The results obtained from the Complexity-Entropy causality plane and power density spectrum analysis reveal that cryptocurrency time-series exhibit characteristics closely resembling those of Brownian noise when analyzed in a univariate context. On the other hand, the application of a wide range of statistical, machine and deep learning models for time-series forecasting demonstrates the low predictability of cryptocurrencies. Notably, our analysis reveals that simpler models such as Naive models consistently outperform the more complex machine and deep learning ones in terms of forecasting accuracy across different forecast horizons and time windows. The combined study of complexity and forecasting accuracies highlights the difficulty of predicting the cryptocurrency market. These findings provide valuable insights into the inherent characteristics of the cryptocurrency data and highlight the need to reassess the challenges associated with predicting cryptocurrency's price movements. △ Less
Source row: 1625 · abstract type: unknown