Abstract
The popularity of cryptocurrencies has been on the rise with the emergence of blockchain technologies. There have been enormous investments in the cryptocurrency market over the past few years. However, the volatile nature and significant price fluctuations in cryptocurrency have resulted in a high investment risk of these assets. In this paper, an improved neural network (NN) ensemble-based approach is proposed with the help of Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (LSTM), i.e., CNN-BiLSTM for long-term price prediction of cryptocurrencies using both live data API and historical data. The CNN learns internal representation of each cryptocurrency independently and extracts useful features. On the other hand, the LSTM layers are used to predict time-series data and recognize the long as well as short-term dependencies efficiently and accurately. The proposed ensemble of CNN-BiLSTM consists of three layers of CNN and two layers of Bi-LSTM to improve the accuracy of the predictions. Moreover, MLP, GRU, CNN and LSTM models are also implemented and compared with the proposed model on the test datasets followed by error evaluation. For evaluating the error of each model, Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) scores are analyzed for four cryptocurrencies Bitcoin, Ethereum, Dogecoin and Litecoin of historical and live data API. It is observed that the proposed CNN-BiLSTM ensemble model has the lowest RMSE score of 0.164 for live data API for Bitcoin and 0.166 for historical dataset for Dogecoin. The MSE score of 0.027 is observed for both Bitcoin and Dogecoin cryptocurrencies for live data API and 0.027 for Dogecoin for historical dataset. Thus, RMSE and MSE scores of the proposed approach are very less as compared to MLP, GRU, CNN and LSTM models for cryptocurrency price prediction for both the datasets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Jiang X (2020) Bitcoin price prediction based on deep learning methods. J Math Finance 10(01):132–139
Gyamerah SA (2022) On forecasting the Intraday bitcoin price using ensemble of variational mode decomposition and generalized additive model. J King Saud Univ - Comput Inf Sci 34(3):1003–1009
Shin MJ, Mohaisen D, Kim J (2021) Bitcoin price forecasting via ensemble-based LSTM Deep Learning Networks. In 2021 International conference on information networking (ICOIN)
Yao Y, Yi J, Zhai S, Lin Y, Kim T, Zhang G, Yoonjae Lee L (2018) Predictive analysis of cryptocurrency price using deep learning. Int J Eng Technol 7(3.27):258
Lu W, Li J, Li Y, Sun A, Wang J (2020) A CNN-LSTM-based model to forecast stock prices. Complexity 2020:10. https://doi.org/10.1155/2020/662292
Cryptocurrency prices, charts and market capitalizations, CoinMarketCap, Available: https://coinmarketcap.com/
Derbentsev V, Babenko V, Khrustalev K, Obruch H, Khrustalova S (2021) Comparative performance of machine learning ensemble algorithms for forecasting cryptocurrency prices. Int J Eng 34(1):140–148
Yahoo Finance: stock market live, quotes, business & finance news. Yahoo! Finance. Available: https://finance.yahoo.com/
Schulte M, Eggert M (2021) Predicting hourly bitcoin prices based on long short-term memory neural networks. In Lecture notes in information systems and organisation, pp 754–769
Cryptocurrency prices, portfolio, forum, rankings. CryptoCompare, Available: https://www.cryptocompare.com/
Bitcoin charts, Bitcoincharts. Available: https://bitcoincharts.com/
Neural networks: what are they and why do they matter?,” What are they and why do they matter? | SAS India, Available: https://www.sas.com/en_in/insights/analytics/neural-networks.html
LSTM RNN in tensorflow: javatpoint. www.javatpoint.com. Available: https://www.javatpoint.com/long-short-term-memory-rnn-in-tensorflow
Alla S (2021) A guide to bidirectional RNNS with keras. Paperspace Blog. Available: https://blog.paperspace.com/bidirectional-rnn-keras
Saha S (2018) A comprehensive guide to convolutional neural networks : the eli5 way. Medium, Available: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53
Techopedia (2018) What is a gated recurrent unit (GRU)?: definition from Techopedia. Techopedia.com, Available: https://www.techopedia.com/definition/33283/gated-recurrent-unit-gru
Multilayer Perceptron Wikipedia, 12-Apr-2022. Available:https://en.wikipedia.org/wiki/Multilayer_perceptron
Zhang F, Li J, Wang Y, Guo L, Wu D, Wu H, Zhao H (2021) Ensemble learning based on policy optimization neural networks for capability assessment. Sensors 21(17):5802
Mean squared error loss function: peltarion platform. Peltarion, Available: https://peltarion.com/knowledge-center/documentation/modeling-view/build-an-ai-model/loss-functions/mean-squared-error
Frost J (2021) Mean squared error (MSE). Statistics By Jim, Available: https://statisticsbyjim.com/regression/mean-squared-error-mse/
Choubey V (2020) How to evaluate the performance of a machine learning model. Medium, Available: https://vijay-choubey.medium.com/how-to-evaluate-the-performance-of-a-machine-learning-model-d12ce920c365
Root-mean-squared error. Root-mean-squared error: an overview/sciencedirect topics. Available: https://www.sciencedirect.com/topics/engineering/root-mean-squared-error
Author information
Authors and Affiliations
Contributions
Authors TS, NG, M and SD wrote the manuscript, and authors NR and AS guided and mentored. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
See Figs.
Bitcoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using live data
15,
Ethereum price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using live data
16,
Dogecoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using live data
17,
Litecoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using live data
18,
Bitcoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using historical data
19,
Ethereum price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using historical data
20,
Dogecoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using historical data
21 and
Litecoin price prediction graphs of (i) CNN, (ii) LSTM, (iii) GRU and (iv) MLP models, respectively, using historical data
22.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Rathee, N., Ankita Singh, Sharda, T. et al. Analysis and price prediction of cryptocurrencies for historical and live data using ensemble-based neural networks. Knowl Inf Syst 65, 4055–4084 (2023). https://doi.org/10.1007/s10115-023-01871-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-01871-0