Predictive Analysis of Cryptocurrency Price Using Deep Learning
The decentralization of cryptocurrencies has greatly reduced the level of central control over them, impacting international relations and trade. Further, wide fluctuations in cryptocurrency price indicate an urgent need for an accurate way to forecast this price. This paper proposes a novel method to predict cryptocurrency price by considering various factors such as market cap, volume, circulating supply, and maximum supply based on deep learning techniques such as the recurrent neural network (RNN) and the long short-term memory (LSTM),which are effective learning models for training data, with the LSTM being better at recognizing longer-term associations. The proposed approach is implemented in Python and validated for benchmark datasets. The results verify the applicability of the proposed approach for the accurate prediction of cryptocurrency price.
 Kaastra I & Boyd M, â€œDesigning a neural network for forecasting financial and economic time seriesâ€, Neurocomputing, Vol.10, No.3, (1996), pp.215-236.
 White H, â€œEconomic prediction using neural networks: The case of IBM daily stock returnsâ€, IEEE International Conference on Neural Networks, (1988), pp.451-458.
 Briere M, Oosterlinck K & Szafarz A, â€œVirtual currency, tangible return: Portfolio diversification with bitcoinâ€, Journal of Asset Management, Vol.16, No.6), (2015), pp.365-373.
 Chatfield C & Yar M, â€œHolt-Winters forecasting: some practical issuesâ€, The Statistician, (1988), 129-140..
 Karpathy A, â€œThe unreasonable effectiveness of recurrent neural networksâ€, Andrej Karpathy blog, (2015).
 Elman JL, â€œFinding structure in timeâ€, Cognitive science, Vol.14, No.2, (1990), pp.179-211.
 Gers FA, Eck D & Schmidhuber J, â€œApplying lstm to time series predictable through time-window approachesâ€, Neural Nets WIRN Vietri-01, (2001), pp.669-676.
 Bengio Y, Simard P & Frasconi P, â€œLearning long-term dependencies with gradient descent is difficultâ€, IEEE transactions on neural networks, Vol.5, No.2, (1994), pp.157-166.
 Bengio Y, â€œLearning deep architectures for AIâ€, Foundations and trendsÂ® in Machine Learning, Vol.2, No.1, (2009), pp.1-127.
 Hochreiter S & Schmidhuber J, â€œLSTM can solve hard long time lag problemsâ€, Advances in neural information processing systems, (1997), pp. 473-479.
 Tschorsch F & Scheuermann B, â€œBitcoin and beyond: A technical survey on decentralized digital currenciesâ€, IEEE Communications Surveys & Tutorials, Vol.18, No.3, (2016), pp.2084-2123.
 Mukhopadhyay U, Skjellum A, Hambolu O, Oakley J, Yu L & Brooks R, â€œA brief survey of cryptocurrency systemsâ€, IEEE 14th Annual Conference on Privacy, Security and Trust (PST), (2016), pp.745-752.
 Phillips RC & Gorse D, â€œPredicting cryptocurrency price bubbles using social media data and epidemic modelingâ€, IEEE Symposium Series on Computational Intelligence (SSCI), (2017), pp.1-7.
 Deng Y, Bao F, Kong Y, Ren Z & Dai Q, â€œDeep direct reinforcement learning for financial signal representation and tradingâ€, IEEE transactions on neural networks and learning systems, Vol.28, No.3, (2017), pp.653-664.
 Zhao Y, Li J & Yu L, â€œA deep learning ensemble approach for crude oil price forecastingâ€, Energy Economics, Vol.66, (2017), pp.9-16.
 Al Shehhi A, Oudah M & Aung Z, â€œInvestigating factors behind choosing a cryptocurrencyâ€, IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), (2014), pp.1443-1447.
 Chen J & Wang D, â€œLong short-term memory for speaker generalization in supervised speech separationâ€, The Journal of the Acoustical Society of America, Vol.141, No.6, (2017), pp.4705-4714.
 Sun L, Jia K, Chen K, Yeung DY, Shi BE & Savarese S, â€œLattice long short-term memory for human action recognitionâ€, IEEE International Conference on Computer Vision, (2017).
 Hyndman RJ & Koehler AB, â€œAnother look at measures of forecast accuracyâ€, International journal of forecasting, Vol.22, No.4, (2006), pp.679-688.
 Willmott CJ & Matsuura K, â€œAdvantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performanceâ€, Climate research, Vol.30, No.1, (2005), pp.79-82.
 G, Abikhanova, A Ahmetbekova, E Bayat, A Donbaeva, G Burkitbay (2018). International motifs and plots in the Kazakh epics in China (on the materials of the Kazakh epics in China), OpciÃ³n, AÃ±o 33, No. 85. 20-43.
 A Mukanbetkaliyev, S Amandykova, Y Zhambayev, Z Duskaziyeva, A Alimbetova (2018). The aspects of legal regulation on staffing of procuratorial authorities of the Russian Federation and the Republic of Kazakhstan OpciÃ³n, AÃ±o 33. 187-216.