INTELLIGENT CRYPTO MARKET FORECASTING USING ARTIFICIAL INTELLIGENCE AND DISTRIBUTED DEEP LEARNING

The significance of the research proposed in this paper lies in the fact that the results of the research provide significant contributions in the field of cryptocurrency market prediction through the implementation of a federated framework of LSTM neural networks and attention. The results of the research demonstrate that the application of a federated framework for implementing a framework of LSTM neural networks and attention could be used to produce results that enhance the cryptocurrency market prediction function. The research results demonstrate the applicability of a federated framework of LSTM neural networks and attention in producing results for the improvement of the functionality of the cryptocurrency market prediction. Therefore, the research proposal has proven its significance.

[1]  S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780,1997. [2]  H. Li, Z. Zhang et al., “A federated learning-based financial forecasting system for cryptocurrency markets,” IEEE Access, vol. 10, pp. 13556–13569, 2022. [3]  L. Deng and D. Yu, “Deep Learning: Methods and Applications,” Found. Trends Signal Process., vol. 7, no. 3–4, pp. 197–387, 2014. [4]   M. Kaastra and M. Boyd, “Designing a neural network for forecasting financial time series,” Neurocomputing, vol. 10, pp. 215–236, 1996. [5]    H. Wang and J. Lee, “Attention-based neural networks for stock movement prediction,” Proc. AAAI,pp. 1807–1813, 2018. [6] X. Zhang and Y. Liu, “Hybrid deep learning approach for cryptocurrency volatility forecasting,” Expert Syst. Appl., vol. 149, art. no. 113248, 2020. [7]     J. Konečný et al., “Federated Optimization: Distributed Machine Learning for On-Device Intelligence,” arXiv:1610.02527, 2016. [8]  G. Kar and M. Stringhini, “Security and privacy in federated learning: A survey,” Comput. Secur., vol. 124, art. no. 102904, 2022. [9] Y. Chen and S. Liu, “Decentralized deep learning for financial prediction,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 7, pp. 2951–2963, 2023. [10]  Z. Wu and X. Bai, “Bitcoin price prediction using LSTM and attention mechanism,” Sensors, vol. 21, no. 4, art. no. 1476, 2021.