REGIME CHANGE AND TREND PREDICTION FOR BITCOIN TIME SERIES DATA

Osamu Kodama; Lukáš Pichl; Taisei Kaizoji

doi:10.12955/cbup.v5.954

Osamu Kodama International Christian University, Mitaka, Tokyo, Japan
Lukáš Pichl International Christian University, Mitaka, Tokyo, Japan
Taisei Kaizoji International Christian University, Mitaka, Tokyo, Japan

DOI: https://doi.org/10.12955/cbup.v5.954

Keywords: Bitcoin, BTC, Elman model, Hidden Markov Model, HMM, recurrent neural network

Abstract

Bitcoin time series dataset recording individual transactions denominated in Euro at the COINBASE market between April 23, 2015 and August 15, 2016 is analyzed. Markov switching model is applied to classify the regions of varying volatility represented by three hidden state regimes using univariate autoregressive model and dependent mixture model. Causality extraction and price prediction of daily BTCEUR exchange rates is performed by means of a recurrent neural network using the standard Elman model. Strong correlations is found between the normalized mean squared error of the Elman network (out-of-sample 5-day-ahead prediction) and the realized volatility (sum of minute returns squared throughout the trading day). The present approach is calibrated using simulated regime change in standard econometric models. Our results clearly demonstrate the applicability of recurrent neural networks to causality extraction even in the case of highly volatile cryptocurrency exchange rate time series data.

References

Akansu, A. N., Kulkarni, S. R. & Malioutov, D. M. (Eds.) (2016), Financial Signal Processing and Machine Learning, Wiley-IEEE Press.

Böhme, R., Christin, N., Edelman, B., & Moore, T. (2015) Bitcoin: Economics, Technology, and Governance, Journal of Economic Perspectives vol. 29, No. 2, pp. 213–238.

CoinDesk (2017) Bitcoin – Market Capitalization, http://www.coindesk.com/data/bitcoin-market-capitalization/, Accessed 2017/03/03.

Cortes, C. Vapnik, V. (1995) Support-vector networks, Machine Learning vol. 20, No. 3, pp. 273–297.

Elman, J. L. (1990) Finding Structure in Time, Cognitive Science vol. 14 No. 2, pp. 179–211.

Extance, A. (2015) Bitcoin and beyond, Nature vol. 526, Issue 7571, pp. 21-23.

Franzke, C. (2012) Predictability of extreme events in a nonlinear stochastic-dynamical model, Physical Review E vol. 85, article ID 031134.

Gyorfi, L., Ottucsak G. & Walk, H. (Eds.) (2012), Machine Learning For Financial Engineering (Advances in Computer Science and Engineering: Texts), Imperial College Press.

Hallerberg, S., Bröcker, J. & Kantz, H. (2008), Prediction of Extreme Events, in Nonlinear Time Series Analysis in the Geosciences, Lecture Notes in Earth Sciences vol. 112, pp. 35-59.

Houey, N. (2016) The Bitcoin mining game, Ledger, The Journal of Cryptocurrency and Blockchain Technology Research, vol. 1, pp. 53-68.

Kim Y. B., Kim J. G,. Kim W., Im J. H et al. (2016) Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies. PLoS ONE vol. 11, No. 8, e0161197.

Kirikos, D. G. (2000) Forecasting exchange rates out of sample: random walk vs Markov Switching Regimes. Applied Economics Letters vol. 7, pp. 133-136.

Kristoufek L. (2013) BitCoin meets Google Trends and Wikipedia: Quantifying the relationship between phenomena of the Internet era. Scientific reports vol. 3, 3415.

Lahmiri, S. (2011) A comparison of PNN and SVM for stock market trend prediction using economic and technical information. International Journal of Computer Applications vol. 29, No. 3, pp. 24–30.

Ron D, Shamir A. (2013) Quantitative analysis of the full bitcoin transaction graph. Financial Cryptography and Data Security: Springer, pp. 6–24.