A Gated Recurrent Unit Approach to Bitcoin Price Prediction

In today's era of big data, deep learning and artificial intelligence have formed the backbone for cryptocurrency portfolio optimization. Researchers have investigated various state of the art machine learning models to predict Bitcoin price and volatility. Machine learning models like recurrent neural network (RNN) and long short-term memory (LSTM) have been shown to perform better than traditional time series models in cryptocurrency price prediction. However, very few studies have applied sequence models with robust feature engineering to predict future pricing. in this study, we investigate a framework with a set of advanced machine learning methods with a fixed set of exogenous and endogenous factors to predict daily Bitcoin prices. We study and compare different approaches using the root mean squared error (RMSE). Experimental results show that gated recurring unit (GRU) model with recurrent dropout performs better better than popular existing models. We also show that simple trading strategies, when implemented with our proposed GRU model and with proper learning, can lead to financial gain.

[1]  Taisei Kaizoji,et al.  Volatility Analysis of Bitcoin Price Time Series , 2017 .

[2]  Jaewook Lee,et al.  An Empirical Study on Modeling and Prediction of Bitcoin Prices With Bayesian Neural Networks Based on Blockchain Information , 2018, IEEE Access.

[3]  Obryan Poyser Exploring the determinants of Bitcoin's price: an application of Bayesian Structural Time Series , 2017, 1706.01437.

[4]  Albert Bifet,et al.  Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[5]  Andrea Baronchelli,et al.  The emergence of consensus: a primer , 2017, Royal Society Open Science.

[6]  Morten L. Bech,et al.  Central Bank Cryptocurrencies , 2017 .

[7]  L. Leemis Applied Linear Regression Models , 1991 .

[8]  Lawrence H. White,et al.  The Market for Cryptocurrencies , 2014 .

[9]  Eng-Tuck Cheah,et al.  Speculative bubbles in Bitcoin markets? An empirical investigation into the fundamental value of Bitcoin , 2015 .

[10]  Ladislav Kristoufek,et al.  What Are the Main Drivers of the Bitcoin Price? Evidence from Wavelet Coherence Analysis , 2014, PloS one.

[11]  Luke Tredinnick Cryptocurrencies and the blockchain , 2019, Business Information Review.

[12]  Akbar Siami Namin,et al.  Forecasting Economics and Financial Time Series: ARIMA vs. LSTM , 2018, ArXiv.

[13]  Sheila Dow,et al.  Monetary Reform, Central Banks, and Digital Currencies , 2019, International Journal of Political Economy.

[14]  Richard Socher,et al.  Regularizing and Optimizing LSTM Language Models , 2017, ICLR.

[15]  Rifat Hacioglu,et al.  Prediction of Bitcoin prices with machine learning methods using time series data , 2018, 2018 26th Signal Processing and Communications Applications Conference (SIU).

[16]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[17]  Wenpeng Yin,et al.  Comparative Study of CNN and RNN for Natural Language Processing , 2017, ArXiv.

[18]  A. Fumagalli,et al.  Cryptocurrencies, Monetary Policy, and New Forms of Monetary Sovereignty , 2019, International Journal of Political Economy.

[19]  Nino Antulov-Fantulin,et al.  Predicting short-term Bitcoin price fluctuations from buy and sell orders , 2018, ArXiv.

[20]  Paraskevi Katsiampa Volatility estimation for Bitcoin: A comparison of GARCH models , 2017 .

[21]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[22]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[23]  Hossam Faris,et al.  A Comparison between Regression, Artificial Neural Networks and Support Vector Machines for Predicting Stock Market Index , 2015 .

[24]  Jamal Bouoiyour,et al.  Is Bitcoin a hedge, a safe haven or a diversifier for oil price movements? A comparison with gold , 2018 .

[25]  Kin Keung Lai,et al.  A Bias-Variance-Complexity Trade-Off Framework for Complex System Modeling , 2006, ICCSA.

[26]  Pei-Chann Chang,et al.  An Ensemble of Neural Networks for Stock Trading Decision Making , 2009, ICIC.

[27]  John Barrdear,et al.  The Macroeconomics of Central Bank Issued Digital Currencies , 2016 .

[28]  Shouyang Wang,et al.  Forecasting stock market movement direction with support vector machine , 2005, Comput. Oper. Res..

[29]  ChongEunsuk,et al.  Deep learning networks for stock market analysis and prediction , 2017 .

[30]  L. Kaiser Seasonality in cryptocurrencies , 2019 .

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[33]  L. Fantacci Cryptocurrencies and the Denationalization of Money , 2019, International Journal of Political Economy.

[34]  M. Peat,et al.  Bitcoin Futures - What Use are They? , 2018, Economics Letters.

[35]  A. H. Dyhrberg Bitcoin, gold and the dollar – A GARCH volatility analysis , 2016 .

[36]  Neil Gandal,et al.  Can We Predict the Winner in a Market with Network Effects? Competition in Cryptocurrency Market , 2016, Games.

[37]  Qiang Qu,et al.  Renovating blockchain with distributed databases: An open source system , 2019, Future Gener. Comput. Syst..

[38]  Yhlas Sovbetov Factors Influencing Cryptocurrency Prices: Evidence from Bitcoin, Ethereum, Dash, Litcoin, and Monero , 2018 .

[39]  Donald W. Marquaridt Generalized Inverses, Ridge Regression, Biased Linear Estimation, and Nonlinear Estimation , 1970 .

[40]  M. Elbeck,et al.  Bitcoins as an investment or speculative vehicle? A first look , 2015 .

[41]  Chulwoo Han,et al.  Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies , 2017, Expert Syst. Appl..

[42]  Tao Chen,et al.  Back propagation neural network with adaptive differential evolution algorithm for time series forecasting , 2015, Expert Syst. Appl..

[43]  Kazumitsu Nawata,et al.  Estimation of sample selection bias models , 1996 .

[44]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[45]  C. Spearman The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[46]  Peter E. Kennedy A Guide to Econometrics , 1979 .

[47]  P. Ciaian,et al.  The economics of BitCoin price formation , 2014, 1405.4498.

[48]  Tetsuya Takiguchi,et al.  Can We Forecast Daily Oil Futures Prices? Experimental Evidence from Convolutional Neural Networks , 2019, Journal of Risk and Financial Management.

[49]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[50]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[51]  Benjamin M. Blau Price dynamics and speculative trading in bitcoin , 2017 .

[52]  Satoshi Nakamoto Bitcoin : A Peer-to-Peer Electronic Cash System , 2009 .

[53]  Caroline Granier,et al.  Cryptocurrencies and Blockchain: Opportunities and Limits of a New Monetary Regime , 2019, International Journal of Political Economy.

[54]  E. C. Cagli Explosive behavior in the prices of Bitcoin and altcoins , 2019, Finance Research Letters.

[55]  G. Dwyer The Economics of Bitcoin and Similar Private Digital Currencies , 2014 .

[56]  Simon Caton,et al.  Predicting the Price of Bitcoin Using Machine Learning , 2018, 2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP).

[57]  David Enke,et al.  The use of data mining and neural networks for forecasting stock market returns , 2005, Expert Syst. Appl..

[58]  Lars Ivar Hagfors,et al.  On the Hedge and Safe Haven Properties of Bitcoin: Is it Really More than a Diversifier? , 2016 .

[59]  Angela Rogojanu,et al.  The issue of competing currencies. Case study – Bitcoin , 2014 .

[60]  Young Bin Kim,et al.  Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies , 2016, PloS one.

[61]  Primavera De Filippi,et al.  Bitcoin: A Regulatory Nightmare to a Libertarian Dream , 2014 .

[62]  Marcel C. Minutolo,et al.  Does Bitcoin exhibit the same asymmetric multifractal cross-correlations with crude oil, gold and DJIA as the Euro, Great British Pound and Yen? , 2018 .

[63]  Aaron Yelowitz,et al.  Characteristics of Bitcoin users: an analysis of Google search data , 2014 .

[64]  Lukasz Kaiser,et al.  Neural GPUs Learn Algorithms , 2015, ICLR.

[65]  T. Moore,et al.  Bitcoin: Economics, Technology, and Governance , 2014 .

[66]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[67]  A. Blundell-Wignall The Bitcoin Question , 2014 .

[68]  José Neves,et al.  Evolving Time Series Forecasting ARMA Models , 2004, J. Heuristics.

[69]  Andrea Baronchelli,et al.  Evolutionary dynamics of the cryptocurrency market , 2017, Royal Society Open Science.

[70]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[71]  A. Szafarz,et al.  Virtual currency, tangible return: Portfolio diversification with bitcoin , 2015 .

[72]  Zheshi Chen,et al.  Bitcoin price prediction using machine learning: An approach to sample dimension engineering , 2020, J. Comput. Appl. Math..

[73]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[74]  Ah Chung Tsoi,et al.  Lessons in Neural Network Training: Overfitting May be Harder than Expected , 1997, AAAI/IAAI.

[75]  Nino Antulov-Fantulin,et al.  An experimental study of Bitcoin fluctuation using machine learning methods , 2018 .

[76]  Michael A. Cusumano The Bitcoin ecosystem , 2014, Commun. ACM.

[77]  Nicolas Huck,et al.  Pairs trading and outranking: The multi-step-ahead forecasting case , 2010, Eur. J. Oper. Res..

[78]  Alex 'Sandy' Pentland,et al.  An Experimental Study of Cryptocurrency Market Dynamics , 2018, CHI.

[79]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[80]  Isaac Madan Automated Bitcoin Trading via Machine Learning Algorithms , 2014 .

[81]  R. Axelrod,et al.  Evolutionary Dynamics , 2004 .