Article: Nonlinear autoregressive with exogeneous input neural network time series model performance: bitcoin price prediction Journal: International Journal of Computational Economics and Econometrics (IJCEE) 2024 Vol.14 No.3 pp.337 - 362 Abstract: There are over 10,000 listed cryptocurrencies, with bitcoin becoming the most used cryptocurrency at present. This research's aim is to establish the different dynamic time series architectures of nonlinear autoregressive having exogenous input (NARX) and nonlinear input output (NIO) to forecast the bitcoin price as well as compare their performance. Furthermore, this study attempts to combine the different number of inputs, hidden nodes, and time delay to assess the social media attribute (X) and bitcoin price (Y) past value impact in each model. The results show that all model architectures NARX and NIO with Levenberg-Marquardt backpropagation training algorithm have a significant relationship between inputs and output. This means social dominance, social volume, and weighted social sentiment have a relationship and effect on price except for model 3 with architecture NIO-1-5-1 (d = 1) and NIO 1-10-1 (d = 2). This research is significant because the results of this study will help traders and investors reduce risk and increase returns. Inderscience Publishers - linking academia, business and industry through research

Title: Nonlinear autoregressive with exogeneous input neural network time series model performance: bitcoin price prediction

Authors: Nurazlina Abdul Rashid; Mohd Tahir Ismail

Addresses: School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia; College of Computing, Informatics and Mathematics, Universiti Teknologi Mara (UiTM) Cawangan Kedah, 08400 Merbok Kedah, Malaysia ' School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia

Abstract: There are over 10,000 listed cryptocurrencies, with bitcoin becoming the most used cryptocurrency at present. This research's aim is to establish the different dynamic time series architectures of nonlinear autoregressive having exogenous input (NARX) and nonlinear input output (NIO) to forecast the bitcoin price as well as compare their performance. Furthermore, this study attempts to combine the different number of inputs, hidden nodes, and time delay to assess the social media attribute (X) and bitcoin price (Y) past value impact in each model. The results show that all model architectures NARX and NIO with Levenberg-Marquardt backpropagation training algorithm have a significant relationship between inputs and output. This means social dominance, social volume, and weighted social sentiment have a relationship and effect on price except for model 3 with architecture NIO-1-5-1 (d = 1) and NIO 1-10-1 (d = 2). This research is significant because the results of this study will help traders and investors reduce risk and increase returns.

Keywords: bitcoin; cryptocurrency; price prediction; nonlinear autoregressive with exogeneous input; NARX; neural network time series; dynamic nonlinear; social media; social dominance.

DOI: 10.1504/IJCEE.2024.139764

International Journal of Computational Economics and Econometrics, 2024 Vol.14 No.3, pp.337 - 362

Accepted: 20 Jan 2024
Published online: 05 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Nonlinear autoregressive with exogeneous input neural network time series model performance: bitcoin price prediction

Keep up-to-date