MLP-NARX Bitcoin Price Prediction Model Integrating System Identification Modelling Principles

Muhammad Nazrin Farhan Nasarudin - Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
Ihsan Mohd Yassin - Microwave Research Institute, Universiti Teknologi MARA, Malaysia
Megat Syahirul Amin Megat Ali - Microwave Research Institute, Universiti Teknologi MARA, Malaysia
Mohd Khairil Adzhar Mahmood - Microwave Research Institute, Universiti Teknologi MARA, Malaysia
Rahimi Baharom - Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
Zairi Ismael Rizman - Universiti Teknologi MARA, 23000 Dungun, Terengganu, Malaysia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.6.2.943

Abstract


Bitcoin is a decentralized digital currency that enables people to exchange value without requiring a third-party intermediary. Due to its many advantages, it has received much interest from institutional and individual investors. Despite its meteoric increase, the price of Bitcoin extremely volatile asset class as it purely relies on supply and demand. This presents an interesting opportunity to create a forecasting model. However, many research papers in this area does not analyse the residuals as part of the forecasting resulting in potentially biased models. In this paper, we demonstrate System Identification (SI) residual analysis techniques to the analysis of our forecasting model. The Multi-Layer Perceptron (MLP) Nonlinear Autoregressive with Exogeneous Inputs (NARX) uses historical price data and several technical indicators to predict the future price movements of Bitcoin. The Particle Swarm Optimization (PSO) algorithm was used to find optimal parameters for the model. The model was able to predict one day ahead price in the prediction test. The model has successfully captured the dynamics of the data through the tests performed on residuals. It is also proving the randomness of residuals, albeit some minor violations.

Keywords


Forecasting; modeling; bitcoin; system identification; artificial intelligence.

Full Text:

PDF

References


C. Zhou, L. Xing, and Q. Liu, “Dependability Analysis of Bitcoin subject to Eclipse Attacks,†International Journal of Mathematical, Engineering and Management Sciences, vol. 6, no. 2, pp. 469–479, Apr. 2021, doi: 10.33889/IJMEMS.2021.6.2.028.

Helynda Mulya Arga Retha and Gilberto Daniel Dwi Putra Taslim, “A Forecasting: Bitcoin Price with the ARIMA Method to Help Swing Traders Made Decision,†Internasional Journal of Data Science, Engineering, and Anaylitics, vol. 2, no. 1, pp. 17–24, May 2022, doi: 10.33005/ijdasea.v2i1.19.

A. Ş. Dokuz, A. Ecemiş, and M. Celik, “Hourly, Daily, and Monthly Analysis of Big Dataset of Bitcoin Blocks,†International Conference on Engineering Technologies, pp. 100–104, 2019.

P. Urien, “Towards Secure Bitcoin Fast Trading: Designing Secure Elements for Digital Currency Invited Paper,†vol. 2, no. August, 2016.

A. van Schetsen, “Impact of graph-based features on Bitcoin prices,†Delft University of Technology, Netherlands, 2019.

M. Chen, N. Narwal, and M. Schultz, “Predicting Price Changes in Ethereum,†Stanford, CA, 2017.

S. Van Der Avoird, “Bachelor Computer Science Prediction and technical analysis of the Bitcoin,†2020.

Anonymous, “CryptoCurrency Market Capitalizations.†https://coinmarketcap.com/

F. Adjei, “Determinants of Bitcoin Expected Returns,†Journal of Finance and Economics, vol. 7, no. 1, pp. 42–47, 2019, doi: 10.12691/jfe-7-1-5.

N. Stepura, A. Vasyliuk, and I. Makar, “Software for Projecting Bitcoin Course by Artificial Neural Network Methods,†in Proc. 4th Int Conf. Computational Linguistic and Intelligent Systems, 2020, vol. II, pp. 390–391. doi: 10.15588/1607-3274-2018-4-14.9.

S. A. Alahmari, “Using Machine Learning ARIMA to Predict the Price of Cryptocurrencies,†International Journal of Future Generation Communication and Networking, vol. 13, no. 1, pp. 745–752, 2020.

Z. Shen, Q. Wan, and D. J. Leatham, “Bitcoin Return Volatility Forecasting: A Comparative Study of GARCH Model and Machine Learning Model,†in 2019 Agricultural & Applied Economics Association Annual Meeting, 2019, pp. 1–20.

B. Barry and M. Crane, “Analysis of cryptocurrency commodities with motifs and LSTM,†in CEUR Workshop Proceedings, 2019, vol. 2563, pp. 28–39.

A. Misnik, S. Krutalevich, S. Prakapenka, P. Borovykh, and M. Vasiliev, “Comparison of the predictions of convolutional neural networks with image arguments and long short-term memory neural networks with time-series arguments for cryptocurrency markets,†CEUR Workshop Proceedings, vol. 2475, no. September, pp. 214–222, 2019.

M. McCoy and S. Rahimi, “Towards a Twitter-based Prediction Tool for Digital Currency,†in International Conference of Artificial Intelligence 2019, 2019, pp. 305–311.

Y. Yang, “Whose opinions prevail on Bitcoin pricing?,†University of Helsinki, 2020.

A. A. Maxim, “Prediction of Cryptocurrency Price Movements from Order Book Data Using LSTM Neural Networks,†University College London, UK, 2019.

B. Bashir and F. Aslam, “Comparative Analysis of Traditional and Soft Computing for Trading Signals Prediction,†International Transaction Journal of Engineering Management & Applied Sciences & Technologies, vol. 11, no. 4, pp. 1–16, 2020, doi: 10.14456/ITJEMAST.2020.70.

N. I. Indera, I. M. Yassin, A. Zabidi, and Z. I. Rizman, “Non-linear Autoregressive with Exogeneous input (NARX) bitcoin price prediction model using PSO-optimized parameters and moving average technical indicators,†Journal of Fundamental and Applied Sciences, vol. 9, no. 3S, p. 791, 2018, doi: 10.4314/jfas.v9i3s.61.

A. Chaudhary, A. Agrawal, and V. Kumar, “Bitcoin Price Prediction using Machine Learning,†International Journal of Multidisciplinary Educational Research, vol. 9, no. 5(5), pp. 151–156, 2020.

Anonymous, “Daily Bitcoin Prices,†2021. http://www.coindesk.com (accessed Apr. 03, 2021).

R. J. Hyndman, “Moving Averages,†in International Encyclopedia of Statistical Science, Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 866–869. doi: 10.1007/978-3-642-04898-2_380.

C. Lento, N. Gradojevic, and C. S. Wright, “Investment information content in Bollinger Bands?,†Applied Financial Economics Letters, vol. 3, no. 4, pp. 263–267, Jul. 2007, doi: 10.1080/17446540701206576.

A. Zabidi, N. M. Tahir, I. M. Yassin, and Z. I. Rizman, “The performance of Binary Artificial Bee Colony (BABC) in structure selection of polynomial NARX and NARMAX Models,†International Journal on Advanced Science, Engineering and Information Technology, vol. 7, no. 2, 2017, doi: 10.18517/ijaseit.7.2.1387.

B. A. Amisigo, N. van de Giesen, C. Rogers, W. E. I. Andah, and J. Friesen, “Monthly streamflow prediction in the Volta Basin of West Africa: A SISO NARMAX polynomial modelling,†Physics and Chemistry of the Earth, Parts A/B/C, vol. 33, no. 1–2, pp. 141–150, Jan. 2008, doi: 10.1016/j.pce.2007.04.019.

D. Nguyen and B. Widrow, “Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights,†in 1990 IJCNN International Joint Conference on Neural Networks, 1990, pp. 21–26 vol.3. doi: 10.1109/IJCNN.1990.137819.

F. Wang, H. Zhang, and A. Zhou, “A particle swarm optimization algorithm for mixed-variable optimization problems,†Swarm and Evolutionary Computation, vol. 60, p. 100808, Feb. 2021, doi: 10.1016/j.swevo.2020.100808.

B. A. Amisigo, N. van de Giesen, C. Rogers, W. E. I. Andah, and J. Friesen, “Monthly streamflow prediction in the Volta Basin of West Africa: A SISO NARMAX polynomial modelling,†Physics and Chemistry of the Earth, Parts A/B/C, vol. 33, no. 1–2, pp. 141–150, Jan. 2008, doi: 10.1016/j.pce.2007.04.019.

N. Heckert and J. Filliben, “Chapter 1: Exploratory Data Analysis,†in NIST/SEMATECH e-Handbook of Statistical Methods, 2003.

I. M. Yassin, “Nonlinear Auto-Regressive Model Structure Selection using Binary Particle Swarm Optimization Algorithm,†Universiti Teknologi Mara, 2014.