Can artificial intelligence enhance the Bitcoin bonanza

Souza, Matheus José Silva de; Almudhaf, Fahad; Henrique, Bruno Miranda; Negredo, Ana Beatriz Silveira; Ramos, Danilo Guimarães Franco; Sobreiro, Vinícius Amorim; Kimura, Herbert

doi:10.1016/j.jfds.2019.01.002

Cited by 30 publications

(19 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Hayes (2017), Jang and Lee (2018), Madan et al, (2015), McNally et al, (2018), Sin and Wang (2017), and Wu, Lu, Ma, and Lu (2018) addressed the prediction of the next‐day trend of bitcoin (up or down) by adopting binary classification models trained on historical data. Various models, such as logistic regression, RF (Attanasio et al, 2019; Sun et al, 2019; Virk, 2017), SVMs (Silva de Souza et al, 2019; Madan et al, 2015), MLPs and genetic algorithms (Sin & Wang, 2017), Bayesian NNs (Jang & Lee, 2018), and LSTM and RNNs (Hashish et al, 2019; Kwon et al, 2019; Li et al, 2019; McNally et al, 2018; Rebane et al, 2018; Wu et al, 2018). Parallel attempts to perform intra‐day price forecasting of bitcoin have also been made (e.g., Shah & Zhang, 2014; Tupinambás et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cryptocurrency price prediction using traditional statistical and machine‐learning techniques: A survey

Khedr

Arif

et al. 2021

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Cryptocurrencies are decentralized electronic counterparts of government-issued money. The first and best-known cryptocurrency example is bitcoin. Cryptocurrencies are used to make transactions anonymously and securely over the internet. The decentralization behavior of a cryptocurrency has radically reduced central control over them, thereby influencing international trade and relations. Wide fluctuations in cryptocurrency prices motivate the urgent requirement for an accurate model to predict its price. Cryptocurrency price prediction is one of the trending areas among researchers. Research work in this field uses traditional statistical and machine-learning techniques, such as Bayesian regression, logistic regression, linear regression, support vector machine, artificial neural network, deep learning, and reinforcement learning. No seasonal effects exist in cryptocurrency, making it hard to predict using a statistical approach. Traditional statistical methods, although simple to implement and interpret, require a lot of statistical assumptions that could be unrealistic, leaving machine learning as the best technology in this field, being capable of predicting price based on experience. This article provides a comprehensive summary of the previous studies in the field of cryptocurrency price prediction from 2010 to 2020. The discussion presented in this article will help researchers to fill the gap in existing studies and gain more future insight.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Silva de Souza, Almudhaf, Henrique, Negredo, Ramos, Sobreiro, and Kimura (2019) showed how an SVM and an ANN could generate abnormal risk-adjusted returns. They showed their approach to bitcoin.…”

Section: Techniques For Cryptocurrency Price Predictionmentioning

confidence: 99%

Cryptocurrency price prediction using traditional statistical and machine‐learning techniques: A survey

Khedr

Arif

et al. 2021

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

show abstract

“…Al respecto, Huang, Huang y Ni (2019) sostienen que la primera criptomoneda descentralizada del mundo es el Bitcoin, que ha llegado a ser la más conocida, utilizada mundialmente, y en consecuencia cuya cotización sirve de referencia a las demás criptomonedas. Silva, et al (2019), comentan que Bitcoin comenzó en enero de 2009 y constituye una moneda digital que elimina la necesidad de un tercero para validar la ejecución de pagos. De acuerdo a Urdaneta, et al (2019a), la criptomoneda minada la producen programadores que cuentan con equipos como los ASIC (Circuito Integrado para Aplicaciones Específicas), con el propósito de resolver las estructuras cada vez más complejas de bloques blockchain.…”

Section: Introductionunclassified

“…Además, entre los atributos más notables que ofrecen las criptomonedas resumidos por Sobhanifard y Sadatfarizani (2019) se encuentran: 1) Las transacciones internacionales a muy bajo costo; 2) alta velocidad de transacción, descentralización de la moneda garantiza su seguridad (Silva, et al, 2019); 3) servicio las veinticuatro horas del día; 4) fuera del control de un gobierno o banco central; 5) el anonimato de los usuarios; 6) lo difícil de su rastreo confiable (Dibrova, 2016); y, 7) para Caporale, Gil-Alana y Plastund (2018), el mercado de Bitcoin es sensible, puesto que reacciona inmediatamente a la llegada de nueva información.…”

Section: Introductionunclassified

Bitcoin y la teoría monetaria de Friedman y Mises. Evidencias estadísticas/ Bitcoin and the monetary theory of Friedman and Mises. Statistic evidence

Montiel

Monsalve

Garcia

2020

RCS

View full text Add to dashboard Cite

Resumen Las criptomonedas, siendo un medio de pago encriptado deberían estar sujeto a alguna de las hipótesis que describen el comportamiento del dinero en la teoría monetaria. Este artículo analiza el desempeño del Bitcoin, desde el punto de vista de Friedman (1956) y Mises (1982). Utilizando datos mensuales de los últimos 67 meses desde enero de 2014 hasta julio de 2019, se desarrolló una investigación de tipo descriptiva Ex - post facto. Los resultados muestran que cuando el aumento marginal de criptomoneda emitidas disminuye, el volumen de transacciones, precios de cierre, capitalización del mercado y velocidad de circulación, aumentan, mostrando evidencias del teorema de la regresión; asimismo, se comprueba la apreciación del Bitcoin por razones de oferta y demanda (minado); y se pudo constatar el incremento constante tanto de la tasa de variación del precio, como de crecimiento de los Bitcoin emitidos. Se concluye que la teoría monetaria aceptada puede contribuir a explicar el comportamiento de las criptomonedas. Abstract Cryptocurrencies, being an encrypted means of payment, should be subject to any of the hypotheses that describe the behavior of money in monetary theory. This article analyzes the performance of Bitcoin, from the point of view of Friedman (1956) and Mises (1982). Using monthly data from the last 67 months from January 2014 to July 2019, a descriptive Ex - post facto investigation was developed. The results show that when the marginal increase in issued cryptocurrencies decreases, the volume of transactions, closing prices, market capitalization and circulation speed increase, showing evidence of the regression theorem; Likewise, the appreciation of Bitcoin is verified for reasons of supply and demand (mined); and the constant increase in both the price variation rate and the growth of the Bitcoin issued could be verified. It is concluded that the accepted monetary theory can contribute to explain the behavior of cryptocurrencies.

show abstract

“…Another emerging technology, blockchain, supports a decentralized architecture providing a secure sharing of data and resources to the various nodes of theIoT. Sing et al (2021) propose integrating an IoT architecture with blockchain and AI to support a practical big data analysis and mitigate the current challenges.DeSouza et al (2019) propose to apply ML to process big data regarding cryptocurrency prices to enable financial operators to optimize their choices. SVMs and ANNs based strategies can generate abnormal risk-adjusted returns when applied to Bitcoin, the most popular decentralized digital currency.…”

mentioning

confidence: 99%

Artificial intelligence techniques in finance and financial markets: A survey of the literature

Milana

Ashta

2021

Strategic Change

View full text Add to dashboard Cite

Both academic and nonacademic literature is evolving following the oscillating development of artificial intelligence (AI) and computing power's evolution in their application to finance and financial markets. The limits to economic growth encountered after the financial crisis and, successively, the recent pandemic bursts have posed new challenges to AI-related technologies. The surveyed publications have given hope in harvesting improved efficiency, new data, information, advisory and management services, risk mitigation, and some unanswered questions regarding negative impacts on sustainable growth and increasing economic welfare.

show abstract

Can artificial intelligence enhance the Bitcoin bonanza

Cited by 30 publications

References 78 publications

Cryptocurrency price prediction using traditional statistical and machine‐learning techniques: A survey

Cryptocurrency price prediction using traditional statistical and machine‐learning techniques: A survey

Bitcoin y la teoría monetaria de Friedman y Mises. Evidencias estadísticas/ Bitcoin and the monetary theory of Friedman and Mises. Statistic evidence

Artificial intelligence techniques in finance and financial markets: A survey of the literature

Contact Info

Product

Resources

About