Bitcoin price prediction using LSTM autoencoder regularized by false nearest neighbor loss
Abstract
We implement deep learning for predicting bitcoin closing prices. Identifying two new determiners, we propose a novel LSTM Autoencoder using Mean Squared Error (MSE) loss which is regularized by False Nearest Neighbor (FNN) algorithm. The method results in reduced error rates when compared to traditional forecasting algorithms and is statistically validated. This research contributes by developing a robust algorithm that accurately determines the fluctuation directions in bitcoin prices and results in values closer to the actual prices.
References
[1]
Abarbanel HD, Brown R, Sidorowich JJ, and Tsimring LS The analysis of observed chaotic data in physical systems Rev Mod Phys 1993 65 4 1331
[2]
Ahmed S, Hassan SU, Aljohani NR, and Nawaz R FLF-LSTM: a novel prediction system using Forex loss function Appl Soft Comput 2020 97 106780
[3]
Antulov-Fantulin N, Guo T, and Lillo F Temporal mixture ensemble models for probabilistic forecasting of intraday cryptocurrency volume Decisions Econ Finan 2021 44 2 905-940
[4]
Cao L, Mees A, and Judd K Dynamics from multivariate time series Physica D 1997 121 1–2 75-88
[5]
Cavalli S and Amoretti M CNN-based multivariate data analysis for bitcoin trend prediction Appl Soft Comput 2021 101 107065
[6]
Chen Z, Li C, and Sun W Bitcoin price prediction using machine learning: an approach to sample dimension engineering J Comput Appl Math 2020 365 112395
[7]
Chen L, Pelger M, and Zhu J Deep learning in asset pricing Manage Sci 2024 70 2 714-750
[8]
CoinDesk (2021) CoinDesk: Bitcoin, Ethereum, Crypto News and Price Data https://www.coindesk.com/ (accessed on 2-Nov-2021)
[9]
Cretarola A, Figà-Talamanca G, and Patacca M Market attention and Bitcoin price modeling: theory, estimation and option pricing Decisions Econ Finan 2020 43 1 187-228
[10]
De Angelis P, De Marchis R, Marino M, Martire AL, Oliva I (2021) Betting on bitcoin: a profitable trading between directional and shielding strategies. Decisions Econ Finan, 1–21
[11]
Demir E, Gozgor G, Lau CKM, and Vigne SA Does economic policy uncertainty predict the Bitcoin returns? An empirical investigation Finance Res Lett 2018 26 145-149
[12]
Ding G and Qin L Study on the prediction of stock price based on the associated network model of LSTM Int J Mach Learn Cybernet 2020 11 6 1307-1317
[13]
Dyhrberg AH Bitcoin, gold and the dollar–A GARCH volatility analysis Finance Res Lett 2016 16 85-92
[14]
Figa-Talamanca G and Patacca M Does market attention affect Bitcoin returns and volatility? Decisions Econ Finan 2019 42 1 135-155
[15]
Fraser AM and Swinney HL Independent coordinates for strange attractors from mutual information Phys Rev A 1986 33 2 1134
[16]
Gandal N, Hamrick JT, Moore T, and Vasek M The rise and fall of cryptocurrency coins and tokens Decisions Econ Finan 2021 44 2 981-1014
[17]
Ghorbel A and Jeribi A Investigating the relationship between volatilities of cryptocurrencies and other financial assets Decisions Econ Finan 2021 44 2 817-843
[18]
Gilpin W Deep reconstruction of strange attractors from time series Adv Neural Inf Process Syst 2020 33 204-216
[19]
Grassberger P, Procaccia I (1983) Measuring the strangeness of strange attractors. Physica D: nonlinear phenomena 9(1-2):189–208.
[20]
Kantz H, Schreiber T (2004) Nonlinear Time Series Analysis. Cambridge University Press
[21]
Katsiampa P Volatility estimation for Bitcoin: a comparison of GARCH models Econom Lett 2017 158 36
[22]
Kennel MB, Brown R, and Abarbanel HD Determining embedding dimension for phase-space reconstruction using a geometrical construction Phys Rev A 1992 45 6 3403
[23]
Liu M, Li G, Li J, Zhu X, and Yao Y Forecasting the price of Bitcoin using deep learning Finance Res Lett 2021 40 101755
[24]
Lux T Inference for systems of stochastic differential equations from discretely sampled data: a numerical maximum likelihood approach Ann Finance 2013 9 2 217-248
[25]
Madan DB Asset pricing theory for two price economies Ann Finance 2015 11 1 1-35
[26]
Maknickienė N, Maknickas A (2012), May Application of neural network for forecasting of exchange rates and forex trading. In The 7th international scientific conference Business and Management (pp. 10–11)
[27]
Mari C and Mari E Gaussian clustering and jump-diffusion models of electricity prices: a deep learning analysis Decisions Econ Finan 2021 44 2 1039-1062
[28]
McNally S, Roche J, Caton S (2018), March Predicting the price of bitcoin using machine learning. In 2018 26th euromicro international conference on parallel, distributed and network-based processing (PDP) (pp. 339–343). IEEE
[29]
Na H and Kim S Predicting stock prices based on informed traders’ activities using deep neural networks Econ Lett 2021 204 109917
[30]
Nakamoto S, Bitcoin A (2008) A peer-to-peer electronic cash system. Bitcoin.–URL: https://bitcoin.org/bitcoin. pdf, 4(2), 15
[31]
Nelson DM, Pereira AC, De Oliveira RA (2017), May Stock market’s price movement prediction with LSTM neural networks. In 2017 International joint conference on neural networks (IJCNN) (pp. 1419–1426). IEEE
[32]
Phillips RC, Gorse D (2018), June Mutual-excitation of cryptocurrency market returns and social media topics. In Proceedings of the 4th international conference on frontiers of educational technologies (pp. 80–86)
[33]
Rezaei H, Faaljou H, and Mansourfar G Stock price prediction using deep learning and frequency decomposition Expert Syst Appl 2021 169 114332
[34]
Sauer T, Yorke JA, and Casdagli M Embedology J Stat Phys 1991 65 3–4 579-616
[35]
Segnon M and Bekiros S Forecasting volatility in bitcoin market Ann Finance 2020 16 435-462
[36]
Shahi TB, Shrestha A, Neupane A, and Guo W Stock Price forecasting with deep learning: a comparative study Mathematics 2020 8 9 1441
[37]
Sugihara G and May RM Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series Nature 1990 344 6268 734-741
[38]
Zanc R, Cioara T, Anghel I (2019), September Forecasting Financial Markets using Deep Learning. In 2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP) (pp. 459–466). IEEE
Index Terms
- Bitcoin price prediction using LSTM autoencoder regularized by false nearest neighbor loss
Index terms have been assigned to the content through auto-classification.
Recommendations
A Hybrid Approach for Predicting Bitcoin Price Using Bi-LSTM and Bi-RNN Based Neural Network
Intelligent Data Engineering and Automated Learning – IDEAL 2021AbstractBitcoin is an electronic or digital currency. However, unlike government-issued currencies, there is no single entity that issues bitcoin or is in charge of processing transactions. That’s why bitcoin has become popular in the recent era. As ...
The effects of individual-level espoused national cultural values on the willingness to use Bitcoin-like blockchain currencies
AbstractSome have called bitcoin a real bubble, while, according to others, it is the most radical invention of the twenty-first century. Nevertheless, there is a consensus regarding the disruptive potential of blockchain technology, which is ...
Highlights- Espoused national cultural values affect the use of blockchain currencies.
- ...
K-Nearest Neighbor Finding Using MaxNearestDist
Similarity searching often reduces to finding the k nearest neighbors to a query object. Finding the k nearest neighbors is achieved by applying either a depth- first or a best-first algorithm to the search hierarchy containing the data. These ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 19 November 2024
Accepted: 27 August 2024
Author Tags
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Jan 2025