The Effect of the Different Data Aggregation Methods and their Detail Levels to the Prediction of Bitcoin's Exchange Rate

Recently a growing interest can be observed in the field of financial forecasting and especially in the field of cryptocurrency market forecasting. This proved to be an outstandingly complex problem because of the many special characteristics of these markets. Making accurate predictions requires the proper usage and fine tuning of the most modern algorithms. The goal of our research was to find the optimal data division method for the LSTM neural network-based prediction of the exchange rate of Bitcoin and fine-tune the model to achieve the lowest mean percentage error possible. To fulfill this goal, two binning methods, namely transaction time-based, and transaction quantity-based binning methods were evaluated from the viewpoint of the Bitcoin exchange rate prediction. We came to the conclusion that time-based binning method outperforms the other tested method and the granularity of the optimal time division was also established. Experimental results show, that the 20-minute and 30-minute prediction interval are the most suitable choices in case of a limited amount of training data and for making more trading decisions. In case of markets with a higher commission, or when more training data are available the 2-hour prediction is recommended. Our results show that on the proper time division-based LSTM prediction method is suitable for developing successful short term trading strategies for Bitcoin markets.

[1]  S. Nadarajah,et al.  Statistical Analysis of the Exchange Rate of Bitcoin , 2015, PloS one.

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

[3]  Nashirah Abu Bakar,et al.  Autoregressive Integrated Moving Average (ARIMA) Model for Forecasting Cryptocurrency Exchange Rate in High Volatility Environment: A New Insight of Bitcoin Transaction , 2017 .

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

[5]  Kai Chen,et al.  A LSTM-based method for stock returns prediction: A case study of China stock market , 2015, 2015 IEEE International Conference on Big Data (Big Data).

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

[7]  Muhammad J. Amjad,et al.  Trading Bitcoin and Online Time Series Prediction , 2016, NIPS Time Series Workshop.

[8]  Nuning Kurniasih,et al.  Forecasting Historical Data of Bitcoin using ARIMA and α-Sutte Indicator , 2018, Journal of Physics: Conference Series.

[9]  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).

[10]  Thomas M. Breuel,et al.  Benchmarking of LSTM Networks , 2015, ArXiv.

[11]  Chris Chatfield,et al.  Holt‐Winters Forecasting: Some Practical Issues , 1988 .

[12]  Leopoldo Catania,et al.  Predicting the Volatility of Cryptocurrency Time–Series , 2018 .

[13]  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.

[14]  Claudio Pizzi,et al.  Mathematical and Statistical Methods for Actuarial Sciences and Finance , 2014 .

[15]  Salim Lahmiri,et al.  Cryptocurrency forecasting with deep learning chaotic neural networks , 2019, Chaos, Solitons & Fractals.

[16]  Akihiko Takahashi,et al.  Bitcoin technical trading with artificial neural network , 2018, Physica A: Statistical Mechanics and its Applications.

[17]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[18]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[19]  Abdul Rahman,et al.  α-Sutte Indicator: a new method for time series forecasting , 2018, Journal of Physics: Conference Series.