Observing Cryptocurrencies through Robust Anomaly Scores

Bae, Geumil; Kim, Jang Ho

doi:10.3390/e24111643

Cited by 4 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The properties of the cryptocurrency price return time series are now close to those observed in mature financial markets such as Forex [11]. However, it has long been believed that the cryptocurrency market, which itself is strongly correlated [12][13][14][15][16][17][18], especially during the COVID-19 period [19][20][21][22][23], has dynamics that is separate from the traditional financial markets [24][25][26][27][28] and that bitcoin can even serve as a hedge or safe haven [29,30] with respect to the stock market, Forex or the commodity market. The hedging potential of bitcoin was even compared to gold [31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 72%

Cryptocurrencies Are Becoming Part of the World Global Financial Market

Wątorek

Kwapień

Dróżdż

2023

Entropy

View full text Add to dashboard Cite

In this study the cross-correlations between the cryptocurrency market represented by the two most liquid and highest-capitalized cryptocurrencies: bitcoin and ethereum, on the one side, and the instruments representing the traditional financial markets: stock indices, Forex, commodities, on the other side, are measured in the period: January 2020–October 2022. Our purpose is to address the question whether the cryptocurrency market still preserves its autonomy with respect to the traditional financial markets or it has already aligned with them in expense of its independence. We are motivated by the fact that some previous related studies gave mixed results. By calculating the q-dependent detrended cross-correlation coefficient based on the high frequency 10 s data in the rolling window, the dependence on various time scales, different fluctuation magnitudes, and different market periods are examined. There is a strong indication that the dynamics of the bitcoin and ethereum price changes since the March 2020 COVID-19 panic is no longer independent. Instead, it is related to the dynamics of the traditional financial markets, which is especially evident now in 2022, when the bitcoin and ethereum coupling to the US tech stocks is observed during the market bear phase. It is also worth emphasizing that the cryptocurrencies have begun to react to the economic data such as the Consumer Price Index readings in a similar way as traditional instruments. Such a spontaneous coupling of the so far independent degrees of freedom can be interpreted as a kind of phase transition that resembles the collective phenomena typical for the complex systems. Our results indicate that the cryptocurrencies cannot be considered as a safe haven for the financial investments.

show abstract

Section: Introductionmentioning

confidence: 72%

Cryptocurrencies Are Becoming Part of the World Global Financial Market

Wątorek

Kwapień

Dróżdż

2023

Entropy

View full text Add to dashboard Cite

show abstract

“…Researchers have extensively studied calendar anomalies and volatility in bitcoin markets using GARCH models, including asymmetric GARCH models [10,34]. Particularly asymmetric GARCH models are well-suited to simulate anomalies and volatility in cryptocurrencies because they can capture asymmetric volatility patterns [35].…”

Section: Literature Reviewmentioning

confidence: 99%

A Forecasting Model Approach: Investigating Calendar Anomalies and Volatility Patterns in the Cryptocurrency Market

Sahu,

Ramírez,

Kim

2024

Preprint

View full text Add to dashboard Cite

This paper investigates calendar anomalies, volatility patterns, and the best forecasting model for predicting volatility in the cryptocurrency market, focusing on ten prominent cryptocurrencies: Binance USD, Bitcoin, Binance Coin, Cardano, Dogecoin, Ethereum, Solana, Tether, USD Coin, and Ripple. Spanning from January 2016 to December 2023, the study utilizes sophisticated statistical models such as GARCH (p,q), EGARCH (p,q), and GJR-GARCH (p,q) to analyze precise changes in market dynamics and the impact of day-of-week fluctuations on cryptocurrency returns. Empirical evidence reveals significant findings regarding the persistence of volatility, positive and negative news effects on volatility, and day-of-week effects on cryptocurrency returns. Post-COVID-19, Sunday emerges as the least volatile day for cryptocurrencies, while Thursdays and Tuesdays exhibit greater volatility. Binance, Ethereum, Dogecoin, and Tether show anomalies where returns on Tuesday and Thursday significantly differed from those on other days of the week. Many other currencies, like the USD coin, Cardano, and Ripple, show anomalies only in the pre-COVID-19 period. The findings highlight the best forecast model for volatility for each top cryptocurrency, offering practical implications for investors, traders, regulators, and policymakers. These insights emphasize the importance of understanding and addressing calendar anomalies in the cryptocurrency market for informed decision-making, trading strategies, regulatory frameworks, and market stability.

show abstract

“…Tosunoğlu et al (2023) advanced the literature by employing artificial neural networks to analyze the day-of-the-week anomaly in cryptocurrencies, offering insights into the predictability of various currencies. Furthermore, Bae and Kim (2022) explored robust anomaly scores in cryptocurrencies, highlighting the impact of network factors on cryptocurrency returns. Grobys and Junttila (2020) delved into speculation and lottery-like demand in cryptocurrency markets, shedding light on the short-term reversal effects observed in the cross-section of cryptocurrencies.…”

Section: Sonal Sahumentioning

confidence: 99%

Eficiencia del mercado y anomalías de calendario pos-COVID: perspectivas de bitcoin y ethereum

Sahu

2024

TAJ

View full text Add to dashboard Cite

Este estudio investiga los efectos del día de la semana en el mercado digital, con un enfoque en bitcoin y ethereum, abarcando desde el 1º de julio de 2020 hasta el 31 de diciembre de 2023, en el período posterior al COVID-19. Empleando pruebas paramétricas y no paramétricas junto con el modelo GARCH (1,1), se analizó la dinámica del mercado. Los hallazgos indican un efecto significativo del día de la semana en ethereum, caracterizado por notables variaciones de rendimiento entre diferentes días, mientras que itcoin no muestra anomalías de calendario discernibles, lo que sugiere una mayor eficiencia del mercado. La susceptibilidad de ethereum a estos efectos subraya las complejidades actuales del mercado. Las disparidades en las anomalías del calendario surgen de la evolución de la dinámica del mercado, las diferencias metodológicas y la naturaleza especulativa del comercio de criptomonedas. Además, el mercado descentralizado y global complica la identificación precisa de los efectos en todo el mercado. Este estudio proporciona evidencia empírica sobre los efectos del día de la semana en el mercado de criptomonedas, lo que facilita a los inversionistas refinar las estrategias comerciales y la gestión de riesgos. Se justifica realizar más investigaciones para explorar los mecanismos subyacentes y monitorear los desarrollos regulatorios y tecnológicos para obtener información de los inversionistas.

show abstract

Observing Cryptocurrencies through Robust Anomaly Scores

Cited by 4 publications

References 49 publications

Cryptocurrencies Are Becoming Part of the World Global Financial Market

Cryptocurrencies Are Becoming Part of the World Global Financial Market

A Forecasting Model Approach: Investigating Calendar Anomalies and Volatility Patterns in the Cryptocurrency Market

Eficiencia del mercado y anomalías de calendario pos-COVID: perspectivas de bitcoin y ethereum

Contact Info

Product

Resources

About