Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels

Zhang, Zhuorui; Dai, Hong-Ning; Zhou, Junhao; Mondal, Subrota Kumar; García, Miguel Martínez; Wang, Hao

doi:10.1016/j.eswa.2021.115378

Cited by 65 publications

(24 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An optimization algorithm's tuning parameter that determines the step size for each iteration as it approaches the minimum of the loss function [4].…”

Section: Learning Ratementioning

confidence: 99%

See 1 more Smart Citation

Cryptocurrency price forecasting method using long short-term memory with time-varying parameters

Boongasame¹,

Songram

2023

IJEECS

View full text Add to dashboard Cite

Numerous research have been done to predict cryptocurrency prices since cryptocurrency prices affect global economic and monetary systems. However, investigations using linear connection approaches and technical analysis indicators frequently fall short of providing an explanation for changes in the pattern of BitCoin pricing. This paper is proposed to study time-varying parameters with long short-term memory (LSTM). The study is investigated on a dataset retrieved from Binance from March 2022 to April 2022. The proposed LSTM used a variety of hyperparameter settings, particularly time parameters, to predict the cryptocurrency price (BTC/USDT) on the dataset. Additionally, it is evaluated in terms of mean absolute percentage error (MAPE) in comparison to smooth moving average (SMA), weighted moving average (WMA), and exponential moving averages (EMA). From the investigation, using the previous 3 days for prediction gives the lowest of the MAPE values and the proposed LSTM outperformed the other models. When considering the last three days' value of pricing, the indicated LSTM offers the best accurate prediction, with a MAPE percentage of 0.0927%.

show abstract

“…An optimization algorithm's tuning parameter that determines the step size for each iteration as it approaches the minimum of the loss function [4].…”

Section: Learning Ratementioning

confidence: 99%

“…Understanding the fluctuation of cryptocurrencies is the first and most significant step in comprehending their risk attributes. It is also a key component of risk management, market making, portfolio optimization and selection, derivative pricing and hedging, and a number of other activities [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Cryptocurrency price forecasting method using long short-term memory with time-varying parameters

Boongasame¹,

Songram

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…Literature [18] is proposed using the Markov switching model window effect of abnormal to virtual cryptocurrency trading to predict warning, by comprehensive research samples within the coefficient and the outside influence on the sample, using the window effect of Markov switching models to predict early warning, and verified in some specific window on the tail that can better realize the precision of forecasting warning. Literature [19] proposed a weighted and pay attention to the memory channel convolution neural network to predict abnormal virtual cryptocurrency trading early warning method, based on the strong correlation between different virtual cryptocurrencies and using the technology of deep learning implementation with a weighted and pay attention to the memory channel convolution neural network model to forecast daily virtual cryptocurrency trading.…”

Section: Research Status Of Virtual Cryptocurrencymentioning

confidence: 99%

Fast Popularity Value Calculation of Virtual Cryptocurrency Trading Stage Based on Machine Learning

et al. 2022

View full text Add to dashboard Cite

This paper proposes a new definition method of currency, which further divides the current hot digital currency according to its legitimacy, encryption, centralization, and other characteristics. Among these, we are mainly interested in virtual cryptocurrencies. Virtual cryptocurrency is one of the application directions of blockchain technology. Its essence is a distributed shared ledger database, which generally has the characteristics of decentralization and non-tampering. The technologies supporting the practical application of virtual cryptocurrencies involve multiple scientific and technological fields such as mathematical algorithms, cryptography, Internet communication, and computer software. Since the launch of the first virtual cryptocurrency bitcoin in 2009, it has developed rapidly worldwide. As of August 1, 2021, more than 11,570 virtual cryptocurrencies have been publicly issued and traded globally, with a total value of over $1.68 trillion. This paper proposes the virtual cryptocurrency trading popularity value system as a standardized index for quantitative analysis of virtual cryptocurrency trading, and the virtual cryptocurrency trading index system as a barometer of the virtual cryptocurrency trading market. It has contributed schemes to the analysis of the market rules of virtual cryptocurrency transactions and the realization and early warning of abnormal virtual cryptocurrency transactions, which are the two main hot research directions of virtual cryptocurrency. To be specific, the popularity value of virtual cryptocurrency transactions provides parameters for analyzing individual virtual cryptocurrencies, and the popularity index of virtual cryptocurrency transactions provides parameters for analyzing the virtual cryptocurrency trading market, so as to prevent major risks of virtual cryptocurrency transactions.

show abstract

“…With the development of information technology, time series data is being produced in almost every application field in real life at an amazing speed [1]. The futures price is considered as an authoritative indicator that can reflect the market situation.…”

Section: Introductionmentioning

confidence: 99%

Research on the Application of Time Convolution Series in Futures Price Forecasting

Yang¹

2022

BCPBM

View full text Add to dashboard Cite

Aiming at the problem of anomaly detection of time series data with unbalanced distribution among classes, a detection method based on depth convolution neural network is proposed. With the increasing trading scale of the futures market, it covers more and more economic and financial fields, and the volatility of the futures market is more and more intense, which constantly presents many complex phenomena that cannot be explained by other classical financial theories. Investors predict stock prices based on statistical analysis or simple machine learning methods, but because the stock market is a complex nonlinear dynamic system, these methods have huge limitations. By using the existing data and the chart obtained by the game master software for prediction analysis, the advantages of several technical indicators have been effectively complemented, and the accuracy of prediction has been improved. On the basis of the concept of attribute set and attribute measure, aiming at the problem of pattern recognition, this paper proposes a recognition method, establishes an attribute mathematical model, and combines it with other methods, which has been gradually applied to artificial intelligence, neural network and other fields. It has been successfully applied in the prediction of futures price trend. Building a futures price forecasting model to reveal the inherent law implied in futures market price index and show its evolution mechanism can improve the control ability to deal with economic and financial risks, and provide an objective and rigorous basis for regulatory authorities to formulate relevant policies, which is also the significance of this study.

show abstract

Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels

Cited by 65 publications

References 38 publications

Cryptocurrency price forecasting method using long short-term memory with time-varying parameters

Cryptocurrency price forecasting method using long short-term memory with time-varying parameters

Fast Popularity Value Calculation of Virtual Cryptocurrency Trading Stage Based on Machine Learning

Research on the Application of Time Convolution Series in Futures Price Forecasting

Contact Info

Product

Resources

About