Cryptocurrency Price Forecasting using LSTM with Short Time Series Data
Abstract views: 95
/ 
PDF downloads: 199
Keywords:
Estimation, Deep Learning, RNN, LSTMAbstract
After the discovery of RNN's lack of long-term memory storage, the LSTM (Long Short-Term
Memory) concept was developed. LSTM's ability to retain past values from further steps within a sequence
or pattern made it a very useful method to analyze past currency values and attempt to estimate their future
values. In this report, this concept is applied to cryptocurrency market to determine if it is indeed possible
to forecast its future values using an LSTM-based deep learning algorithm. In this study, 100
cryptocurrencies will be estimated using short-term, hourly data. When the results obtained are analyzed,
98% accuracy is obtained on average. However, for some cryptocurrencies, performances far above this
rate and for some cryptocurrencies, performances far below this rate were obtained.
Downloads
References
Hamayel, Mohammad J., and Amani Yousef Owda. 2021. "A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms" AI 2, no. 4: 477-496.
https://doi.org/10.3390/ai2040030
Wardak, A. B., & Rasheed, J. (2022). Bitcoin Cryptocurrency Price Prediction Using Long Short-Term Memory Recurrent Neural Network. European Journal of Science and Technology, (38), 47-53.
V. Kumar T, S. Santhi, K. G. Shanthi and G. M, "Cryptocurrency Price Prediction using LSTM and Recurrent Neural Networks," 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India, 2023, pp. 1-5, doi: 10.1109/ICAAIC56838.2023.10141048.
Ravele, T.; Sigauke, C.; Rambevha, V.R. Predicting Closing Price of Cryptocurrency Ethereum. Preprints 2024, 2024021537. https://doi.org/10.20944/preprints202402.1537.v1
Salim Lahmiri, Stelios Bekiros, Cryptocurrency forecasting with deep learning chaotic neural networks, Chaos, Solitons & Fractals, Volume 118, 2019, 35-40, https://doi.org/10.1016/j.chaos.2018.11.014.
U. S. Sumi, R. Akter, K. A. Ahamed, S. Sutradhar, S. Ahamed and T. Elias, "Analysis of Machine Learning and Deep Learning to Forecast Prices on Several Crypto Exchanges," 2023 Fifth International Conference on Electrical, Computer and Communication Technologies (ICECCT), Erode, India, 2023, pp. 1-8, doi: 10.1109/ICECCT56650.2023.10179848.
M. Rafi, Q. A. K. Mirza, M. I. Sohail, M. Aliasghar, A. Aziz and S. Hameed, "Enhancing Cryptocurrency Price Forecasting Accuracy: A Feature Selection and Weighting Approach With Bi-Directional LSTM and Trend-Preserving Model Bias Correction," in IEEE Access, vol. 11, pp. 65700-65710, 2023, doi: 10.1109/ACCESS.2023.3287888.
B. Sonare, S. Patil, R. Pise, S. Bajad, S. Ballal and Y. Chandre, "Analysis of Various Machine Learning and Deep Learning Algorithms for Bitcoin Price Prediction," 2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), Chennai, India, 2023, pp. 1-5, doi: 10.1109/RAEEUCCI57140.2023.10134467.
Shalini Sharma, Angshul Majumdar, Deep state space model for predicting cryptocurrency price, Information Sciences, Volume 618, 2022, 417-433, https://doi.org/10.1016/j.ins.2022.10.129.
Patrick Jaquart, David Dann, Christof Weinhardt, Short-term bitcoin market prediction via machine learning, The Journal of Finance and Data Science, Volume 7, 2021, 45-66,
https://doi.org/10.1016/j.jfds.2021.03.001.
Sivakumar, Santosh, "Machine Learning and the Network Analysis of Ethereum Trading Data" (2022). Dartmouth College Undergraduate Theses. 265.
https://digitalcommons.dartmouth.edu/senior_theses/265
Sebastião, H.; Godinho, P. Forecasting and trading cryptocurrencies with machine learning under changing market conditions. Financial Innovation 7(1): 3. 2021. DOI: 10.1186/s40854-020-00217-x
Patra, G.R., Mohanty, M.N. Price Prediction of Cryptocurrency Using a Multi-Layer Gated Recurrent Unit Network with Multi Features. Comput Econ 62, 1525–1544 (2023). https://doi.org/10.1007/s10614-022-10310-1.
OS Al-butti, OT Altinoz, “Comparison Between PSO-Based and fmincon-Based Approaches of Optimal Power Flow for a Standard IEEE-30 Bus System,” International Symposium on Energy Management and Sustainability, 209-219. 2022.
K Alhashemi, OT Altinoz, “Applied Time Series Regression by Using Random Forest Algorithm for Forecasting of Electricity Consumption on a Daily Basis,” International Symposium on Energy Management and Sustainability, 197-207, 2022.
M Altinoz, OT Altinoz “Systematic initialization approaches for portfolio optimization problems,” IEEE Access 7, 57779-57794, 2019.
