A New Forecasting Framework for Bitcoin Price with LSTM

Wu, Chih-Hung; Lu, Chih-Chiang; Ma, Yongkui; Lu, Ruei-Shan

doi:10.1109/icdmw.2018.00032

Cited by 131 publications

(62 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various techniques like neural network (Jang and Lee 2017), neuro-fuzzy (Atsalakis 2019), machine learning (Mallqui andFernandes 2019), deep learning (McNally et al 2018;Wu et al 2018), and deep neural network (Nakano et al 2018), deep learning chaotic neural networks (Lahmiri and Bekiros 2019) predict the directional predictive modeling of daily prices of Bitcoin. These techniques produce superior predictive performances over their traditional counterparts and are more useful for nonlinear and chaotic financial markets.…”

Section: Previous Researchmentioning

confidence: 99%

A differential evolution-based regression framework for forecasting Bitcoin price

2021

View full text Add to dashboard Cite

This research proposes a differential evolution-based regression framework for forecasting one day ahead price of Bitcoin. The maximal overlap discrete wavelet transformation first decomposes the original series into granular linear and nonlinear components. We then fit polynomial regression with interaction (PRI) and support vector regression (SVR) on linear and nonlinear components and obtain component-wise projections. The sum of these projections constitutes the final forecast. For accurate predictions, the PRI coefficients and tuning of the hyperparameters of SVR must be precisely estimated. Differential evolution, a metaheuristic optimization technique, helps to achieve these goals. We compare the forecast accuracy of the proposed regression framework with six advanced predictive modeling algorithms-multilayer perceptron neural network, random forest, adaptive neural fuzzy inference system, standalone SVR, multiple adaptive regression spline, and least absolute shrinkage and selection operator. Finally, we perform the numerical experimentation based on-(1) the daily closing prices of Bitcoin for January 10, 2013, to February 23, 2019, and (2) randomly generated surrogate time series through Monte Carlo analysis. The forecast accuracy of the proposed framework is higher than the other predictive modeling algorithms.

show abstract

Section: Previous Researchmentioning

confidence: 99%

A differential evolution-based regression framework for forecasting Bitcoin price

2021

View full text Add to dashboard Cite

show abstract

“…In so, further shortcomings in the documentation render it impossible to reproduce and verify the empirical analyses at all. These include, not explicitly reporting the analyzed time range [41,42], data split [43], or machine learning setup (e.g., layer structure, activation function, loss function, learning function) [44][45][46]. Furthermore, inconsistencies in the reporting prohibit reproducing the empirical tests.…”

Section: Discussionmentioning

confidence: 99%

“…Given these limitations, we find that recurrent neural networks, and in particular long-short term memory neural networks, perform well in the bitcoin pricing problem compared to other methods [33,34,[43][44][45][46]53]. Interestingly, even though long shortterm memory neural networks were published in 1997 already [54], the first paper [53] taking these into account is from 2018.…”

Section: Theoretical Implicationsmentioning

confidence: 99%

“…Based on the finding that complex network architectures such as recurrent neural networks yield promising results [33,34,[43][44][45][46]53], future research should evaluate further sophisticated network architectures for this particular problem. This may include assessing the effectiveness of ordinary convolutional neural networks [55], as well as dilated convolutional neural networks [56].…”

Section: Practical Implicationsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Bitcoin Pricing — A Structured Literature Review

Jaquart¹,

Dann²,

Martin³

2020

WI2020 Zentrale Tracks

View full text Add to dashboard Cite

Bitcoin, as the most popular cryptocurrency, has received increasing attention from both investors and researchers over recent years. One emerging branch of the research on bitcoin focuses on empirical bitcoin pricing. Machine learning methods are well suited for predictive problems, and researchers frequently apply these methods to predict bitcoin prices and returns. In this study, we analyze the existing body of literature on empirical bitcoin pricing via machine learning and structure it according to four different concepts. We show that research on this topic is highly diverse and that the results of several studies can only be compared to a limited extent. We further derive guidelines for future publications in the field to ensure a sufficient level of transparency and reproducibility.

show abstract

“…He et al, (2019) supported this in their finding where LSTM-based models performed significantly better than ARIMA in forecasting precious metal prices. Wu et al, (2018) proposed LSTM forecasting framework in the forecast of Bitcoin volatility concluded that values projected by LSTM are nearer to the actual values on a non-stationary time series data. Furthermore, Baughman et al, (2018) utilised LSTM networks to predict the spot price of Amazon computing instances.…”

Section: Introductionmentioning

confidence: 99%

Predicting the Kijang Emas Bullion Price using LSTM Networks

Ismail¹,

Razak²

2020

J ENTREP BUS

View full text Add to dashboard Cite

This study investigates the potential of Deep Learning techniques, specifically LSTM networks, in forecasting Kijang Emas future value over a long period. Six LSTM models comprising of Simple LSTM, Bidirectional LSTM, and Stacked LSTM architecture were built and trained against a 15-year historical price data for Kijang Emas. The models’ performance was then measured against ARIMA (5,1,0) as a baseline reference and evaluated against the RAE, MSE and RMSE metric. The results revealed that LSTM networks models performed well in forecasting Kijang Emas price based on the test dataset where the average RMSE was between 49.9 to 50.3 while the Bidirectional LSTM was found to exhibit better performance as compared to the other LSTM models.

show abstract

A New Forecasting Framework for Bitcoin Price with LSTM

Cited by 131 publications

References 17 publications

A differential evolution-based regression framework for forecasting Bitcoin price

A differential evolution-based regression framework for forecasting Bitcoin price

Machine Learning for Bitcoin Pricing — A Structured Literature Review

Predicting the Kijang Emas Bullion Price using LSTM Networks

Contact Info

Product

Resources

About