LEVERAGING ON CONTINUAL MACHINE LEARNING FOR REAL TIME TRADING IN FINANCIAL MARKETS

Abstract

In this research paper, a novel neural inspired approach called the Auditory Machine Intelligence (AMI) is proposed for the prediction of cryptocurrency price - the ripple (XRP/USD) trading pair. The AMI is implemented as part of an LUNO API systems app and real-time data generated and captured. Comparisons were also made with a popular method used in cryptocurrency trading called the Non-linear Auto-Regressive Neural Network (NARX-net). The experimental results considering the 40%, 60% and 80% training were reported for the both techniques. From the experimental results, it was clearly seen that on the average, the NeuroAMI will outperform the NARXnet technique at the 60% and 80% input training data levels; however, the NARXnet technique fared better on the average at the 40% input training data level.

Keywords

• Blockchain
• cryptocurrency price
• machine learning
• neural network
• prediction

Leveragıng On Contınual Machıne Learnıng For Real Tıme Tradıng In Fınancıal Markets

Abstract

In this research paper, a novel neural inspired approach called the Auditory Machine Intelligence (AMI) is proposed for the prediction of cryptocurrency price - the ripple (XRP/USD) trading pair. The AMI is implemented as part of an LUNO API systems app and real-time data generated and captured. Comparisons were also made with a popular method used in cryptocurrency trading called the Non-linear Auto-Regressive Neural Network (NARX-net). The experimental results considering the 40%, 60% and 80% training were reported for the both techniques. From the experimental results, it was clearly seen that on the average, the NeuroAMI will outperform the NARXnet technique at the 60% and 80% input training data levels; however, the NARXnet technique fared better on the average at the 40% input training data level.

Keywords

• Blockchain
• cryptocurrency price
• machine learning
• neural network
• prediction

References

1. Anghel, D. G. (2020). A reality check on trading rule performance in the cryptocurrency market:Machine learning vs. technical analysis. Finance Research Letters, 101655.
2. Cui, Y., Ahmad, S., & Hawkins, J. (2016). Continuous online sequence learning with an unsupervised neural network model. Neural computation, 28(11), 2474-2504.
3. Dutta, A., Kumar, S., &Basu, M. (2020). A Gated Recurrent Unit Approach to Bitcoin Price Prediction. Journal of Risk and Financial Management, 13(2), 23.
4. Fayek, H. M. (2017). MatDL: A lightweight deep learning library in MATLAB. Journal of Open Source Software, 2(19), 413.
5. Houssein, E. H., Dirar, M., Hussain, K., & Mohamed, W. M. (2020). Assess deep learning models for Egyptian exchange prediction using nonlinear artificial neural networks. Neural Computing and Applications, 1- 23.
6. Miura, R., Pichl, L., &Kaizoji, T. (2019, July). Artificial Neural Networks for Realized Volatility Prediction in Cryptocurrency Time Series. In International Symposium on Neural Networks (pp. 165-172). Springer, Cham.
7. Osegi, E. N., & Anireh, V. (2020). AMI: an auditory machine intelligence algorithm for predicting sensory-like data. Computer Science, 5(2), 71-89.
8. Osegi, E. N. (2021). Design and Implementation of a Web-Based AI Tool for Real Time Trading In Financial Markets. Diploma Thesis. National Open University of Nigeria (NOUN).

9. Osegi, E. N. (2023). Neuronal Auditory Machine Intelligence (Neuro-AMI) In Perspective. http://dx.doi.org/10.13140/RG.2.2.10131.45605.
10. Omane-Adjepong, M., Alagidede, P., & Akosah, N. K. (2019). Wavelet time-scale persistence analysis of cryptocurrency market returns and volatility. Physica A: Statistical Mechanics and its Applications, 514, 105-120.
11. Shintate, T., & Pichl, L. (2019). Trend prediction classification for high frequency bitcoin time series with deep learning. Journal of risk and Financial management, 12(1), 17.