Application of Machine Learning Algorithms for Bitcoin Automated Trading

Żbikowski, Kamil

doi:10.1007/978-3-319-30315-4_14

Cited by 25 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The forecastability of cryptocurrencies' price movements and the profitability of trading strategies have also been addressed using Machine Learning tools, such as Binomial Logistic Regressions (Madan et al, 2015), Random Forests (Madan et al, 2015;Vo and Yost-Bremm, 2018;Xiaolei et al, 2018), Decision Trees (Huang et al, 2018;Xiaolei et al, 2018;Alessandretti et al, 2018), Support Vector Machines (Żbikowski, 2016;Xiaolei et al, 2018;de Souza et al, 2019;Mallqui and Fernandes, 2019), and Artificial Neural Networks Liang, 2017, McNally et al, 2018;Jang and Lee, 2018;Nakano et al, 2018;de Souza et al, 2019;Mallqui andFernandes, 2019¸ Lahmiri andBekiros 2019), particularly Long Short-Term Memory Networks (McNally et al, 2018, Alessandretti et al, 2018Lahmiri and Bekiros, 2019). Most of these papers use Bitcoin daily price data, but some of them use high-frequency data or data on other cryptocurrencies.…”

Section: Market Efficiency Predictability and Profitabilitymentioning

confidence: 99%

Cryptocurrencies and blockchain. Overview and future perspectives

Sebasti�ã

N.A.

Cunha

et al. 2021

IJEBR

View full text Add to dashboard Cite

This article presents an overview of the main developments of cryptocurrencies and discusses their future perspectives. First, it briefly reviews the history of cryptocurrencies since the creation of Bitcoin, presents the main market trends, and discusses the key features of cryptocurrencies in the context of blockchain. Second, it analyses current cryptocurrency projects, like the Libra project, and other applications of the blockchain technology. Third, it presents a systematic economics and financial literature review on cryptocurrencies. Fourth, it examines the challenges, benefits, and future perspectives of cryptocurrencies and blockchain technology, with a focus on the environmental issues and central bank digital currencies.

show abstract

Section: Market Efficiency Predictability and Profitabilitymentioning

confidence: 99%

Cryptocurrencies and blockchain. Overview and future perspectives

Sebasti�ã

N.A.

Cunha

et al. 2021

IJEBR

View full text Add to dashboard Cite

show abstract

“…Meanwhile, the ML algorithms have been applied partially to analysis on crypto-currency coins [4], NN-based methods as Bayesian neural network (BNN) [5], long-short term memory (LSTM), and recurrent NN (RNN) [6], and other algorithms. Among these and other concerns, research studies suggest that the NN algorithm provides a better result in predicting Bitcoin price and analysis on the cryptocurrency Market [7]. Hence this proposal practiced the time series analysis on Bitcoin price prediction using NN.…”

Section: Figure 1 Top-10 Crypto-currencies By Market Capitalization mentioning

confidence: 99%

A Bayesian Regularized Neural Network for Analyzing Bitcoin Trends

et al. 2021

View full text Add to dashboard Cite

Bitcoin is a decentralized digital currency without a central bank or single administrator sent from user to user on the peer-to-peer bitcoin blockchain network without intermediaries' need. In this Bitcoin trend analysis work, initial attributes are considered from five sectors based on financial, social, token, network, and that count to thirteen attributes. The thirteen attributes considered are price, volume, market cap, a mean dollar invested age, social volume, social dominance, development activity, transaction volume, token age consumed, token velocity, token circulation, market value to realized value, and realized cap. We apply the attribute selection and trend analysis mapped with potential seven attributes: Price, Volume, Market Cap, Social Dominance, Development Activity, Market Value to Realized Value & Realized Cap. We have conducted Nonlinear Autoregressive with External Input analysis considering seven attributes. The work employed three training algorithms to train a neural network as Levenberg-Marquard, Bayesian Regularization, and Scaled Conjugate Gradient algorithm. The Error histogram and regression plots results indicate that the Bayesian Regularized Neural Network is showing good performance and thus provides a better forecast.

show abstract

“…With the hype around cryptocurrencies and the development of decentralized applications on public blockchains, a straightforward example is the use of machine learning for automated trading of cryptocurrencies [22,23]. Chen et al [24] used machine learning to detect Ponzi schemes on the blockchain using various features of smart contracts and user accounts.…”

Section: Machine Learning and Blockchainsmentioning

confidence: 99%

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

et al. 2018

View full text Add to dashboard Cite

The adoption of machine learning and deep learning is on the rise in the cybersecurity domain where these AI methods help strengthen traditional system monitoring and threat detection solutions. However, adversaries too are becoming more effective in concealing malicious behavior amongst large amounts of benign behavior data. To address the increasing time-to-detection of these stealthy attacks, interconnected and federated learning systems can improve the detection of malicious behavior by joining forces and pooling together monitoring data. The major challenge that we address in this work is that in a federated learning setup, an adversary has many more opportunities to poison one of the local machine learning models with malicious training samples, thereby influencing the outcome of the federated learning and evading detection. We present a solution where contributing parties in federated learning can be held accountable and have their model updates audited. We describe a permissioned blockchain-based federated learning method where incremental updates to an anomaly detection machine learning model are chained together on the distributed ledger. By integrating federated learning with blockchain technology, our solution supports the auditing of machine learning models without the necessity to centralize the training data. Experiments with a realistic intrusion detection use case and an autoencoder for anomaly detection illustrate that the increased complexity caused by blockchain technology has a limited performance impact on the federated learning, varying between 5 and 15%, while providing full transparency over the distributed training process of the neural network. Furthermore, our blockchain-based federated learning solution can be generalized and applied to more sophisticated neural network architectures and other use cases.

show abstract

Application of Machine Learning Algorithms for Bitcoin Automated Trading

Cited by 25 publications

References 5 publications

Cryptocurrencies and blockchain. Overview and future perspectives

Cryptocurrencies and blockchain. Overview and future perspectives

A Bayesian Regularized Neural Network for Analyzing Bitcoin Trends

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

Contact Info

Product

Resources

About