Skip to content
2000
Volume 18, Issue 7
  • ISSN: 2666-2558
  • E-ISSN: 2666-2566

Abstract

Introduction

Cryptocurrency is the new mode of transaction that is slowly replacing the conventional assets of transactions. With the rise and advancement in the technology called blockchain and the volatile nature of the market, cryptocurrencies are showing possibilities of making huge profits. This new trend is slowly becoming accessible to all classes of society in every part of the world while creating a great opportunity for scholars and analysts to conduct new research. However, unlike the stock market, the prices of cryptocurrencies show highly volatile and dynamic behaviour.

Methods

Several research in the past have been performed to predict the nature and other aspects of cryptocurrencies with the aid of machine learning to forecast the future market based on past data. In the proposed work, 6 different machine-learning models have been used for forecasting the prices of cryptocurrencies. The algorithms used are Autoregressive Integrated Moving Average (ARIMA), Gated Regression Unit (GRU), Long Short-Term Memory (LSTM), Bi-LSTM and Vector Autoregression (VAR).

Results

Further, the accuracies of different models are compared and analysed. Furthermore, these models are used to predict the first-order difference between 24 hours of all-time high and low values. This evaluation gives us an idea of where the price band of the currency and where is it most likely to be present during any 24-hour timespan.

Conclusion

This can effectively lead to better decision making in choosing crypto-currency. The GRU model achieved the best performance in cryptocurrency prediction with an RMSE of 0.2242 and MAE of 0.1598 for BTC prices, while the LSTM followed closely with an RMSE of 0.3473 and MAE of 0.2557. Both models outperformed ARIMA, Bi-LSTM, VAR, and FB Prophet, which showed significantly higher error rates.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/rascs/10.2174/0126662558335176241121113056
2024-12-09
2025-09-21

  • From This Site

    /content/journals/rascs/10.2174/0126662558335176241121113056
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. BontempiG. TaiebS. Le BorgneY. Machine learning strategies for time series forecasting.Business IntelligenceBerlin, HeidelbergSpringer AufaureM.A. ZimányiE. 2013627710.1007/978‑3‑642‑36318‑4_3
     [Google Scholar]
  2. MukhopadhyayU. SkjellumA. HamboluO. OakleyJ. YuL. BrooksR. A brief survey of cryptocurrency systems.Proceedings of the 14th Annual Conference on Privacy, Security and Trust (PST)Auckland, New Zealand, 12-14 Dec. 2016, pp. 437-444.10.1109/PST.2016.7907006
     [Google Scholar]
  3. IqbalM. IqbalM. JaskaniF. IqbalK. HassanA. Time-series prediction of cryptocurrency market using machine learning techniques.EAI Endorsed Trans. Creative Technol.202182817028610.4108/eai.7‑7‑2021.170286
     [Google Scholar]
  4. HawarthJ. How Many Cryptocurrencies are There In 2024?2024Available from: https://explodingtopics.com/blog/number-of-cryptocurrencies
  5. HitamN.A. IsmailA.R. Comparative performance of machine learning algorithms for cryptocurrency forecasting.Indones. J. Electr. Eng. Comput. Sci.20181131121112810.11591/ijeecs.v11.i3.pp1121‑1128
     [Google Scholar]
  6. ChanX. P2P crypto exchange script - Create a P2P cryptocurrency exchange.2022Available from: https://www.finextra.com/blogposting/21746/p2p-crypto-exchange-script---create-a-p2p-cryptocurrency-exchange
  7. FrankenfieldJ. Peer-to-peer (virtual currency): Definition and how it works.2024Available from: https://www.investopedia.com/terms/p/ptop.asp
  8. Bitcoin is an innovative payment network and a new kind of money.Available from: https://bitcoin.org/en/
  9. Three trillion dollars worth of crypto.2021Available from: https://www.statista.com/chart/23160/biggest-crypto-currency-market-caps/
  10. HamayelM.J. OwdaA.Y. A novel cryptocurrency price prediction model using GRU, LSTM and bi-LSTM machine learning algorithms.J. Comput. Sci.202117919
     [Google Scholar]
  11. ShahidF. ZameerA. MuneebM. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM.Chaos Solitons Fractals202014011021210.1016/j.chaos.2020.11021232839642
     [Google Scholar]
  12. LiuB. FuC. BielefieldA. LiuY. Forecasting of Chinese primary energy consumption in 2021 with GRU artificial neural network.Energies20171010145310.3390/en10101453
     [Google Scholar]
  13. MaladiR. K. DhairiyaP. Time series analysis of cryptocurrency returns and volatilities.J. Econ. Finan.202145759410.1007/s12197‑020‑09526‑4
     [Google Scholar]
  14. HoS.L. XieM. The use of ARIMA models for reliability forecasting and analysis.Comput. Ind. Eng.1998351-221321610.1016/S0360‑8352(98)00066‑7
     [Google Scholar]
  15. LivierisI.E. PintelasE. StavroyiannisS. PintelasP. Ensemble deep learning models for forecasting cryptocurrency time-series.Algorithms202013512110.3390/a13050121
     [Google Scholar]
  16. WangH. LeiZ. ZhangX. ZhouB. PengJ. A review of deep learning for renewable energy forecasting.Energy Convers. Manage.201919811179910.1016/j.enconman.2019.111799
     [Google Scholar]
  17. PengC. YichaoG. Cryptocurrency price analysis and time series forecasting.2020Available from: https://wiki.smu.edu.sg/1920t2isss608/img_auth.php/2/20/Report_G7_Cryptocurrency.pdf
  18. Siami-NaminiS. TavakoliN. Siami NaminA. A comparison of ARIMA and LSTM in forecasting time series.17th IEEE International Conference on Machine Learning and Applications (ICMLA)Orlando, FL, USA, 17-20 Dec. 2018, pp. 1394-1401.10.1109/ICMLA.2018.00227
     [Google Scholar]
  19. KwonD.-H. KimJ.-B. HeoJ.-S. KimC.-M. HanY.-H. Time series classification of cryptocurrency price trend based on a recurrent LSTM neural network.J. Inf. Process. Syst.201915369470610.3745/JIPS.03.0120
     [Google Scholar]
  20. SimsC.A. Are forecasting models usable for policy analysis?Quart. Rev.198610Win216
     [Google Scholar]
  21. OyedeleA.A. AjayiA.O. OyedeleL.O. BelloS.A. JimohK.O. Performance evaluation of deep learning and boosted trees for cryptocurrency closing price prediction.Expert Syst. Appl.202321311923310.1016/j.eswa.2022.119233
     [Google Scholar]
  22. SeabeP.L. MoutsingaC.R.B. PindzaE. Forecasting cryptocurrency prices using LSTM, GRU, and bi-directional LSTM: A deep learning approach.Fractal and Fractional20237220310.3390/fractalfract7020203
     [Google Scholar]
  23. ToaiT. K. SenkerikR. ZelinkaI. Arima for short-term and lstm for long-term in daily bitcoin price prediction.Artificial Intelligence and Soft ComputingChamSpringer RutkowskiL. SchererR. KorytkowskiM. 202313114310.1007/978‑3‑031‑23492‑7_12
     [Google Scholar]
  24. ZhongC. DuW. XuW. HuangQ. ZhaoY. WangM. LSTM-ReGAT: A network-centric approach for cryptocurrency price trend prediction.Decis. Support Syst.202316911395510.1016/j.dss.2023.113955
     [Google Scholar]
  25. LiG. WangY. Automatic ARIMA modeling-based data aggregation scheme in wireless sensor networks.J. Wireless Com. Network.20132013110.1186/1687‑1499‑2013‑85
     [Google Scholar]
  26. JinB. XuX. Wholesale price forecasts of green grams using the neural network.Asian J. Econ. Bank.202410.1108/AJEB‑01‑2024‑0007
     [Google Scholar]
  27. JinB. XuX. Predictions of steel price indices through machine learning for the regional northeast Chinese market.Neural Comput. Appl.20243633208632088210.1007/s00521‑024‑10270‑7
     [Google Scholar]
  28. BoraN. Understanding ARIMA models for machine learning.2021Available from: https://www.capitalone.com/tech/machine-learning/understanding-arima-models/
  29. Autoregressive Integrated Moving Average (ARIMA).Available from: https://corporatefinanceinstitute.com/resources/knowledge/other/autoregressive-integrated-moving-average-arima/
  30. Vector autoregressive models for multivariate time series.Modeling Financial Time Series with S-PLUSNew York, NYSpringer200638542910.1007/978‑0‑387‑32348‑0_11
     [Google Scholar]
  31. GoledS. Why are people bashing facebook prophet.2021Available from: https://analyticsindiamag.com/why-are-people-bashing-facebook-prophet/
  32. KumarN. SusanS. "COVID-19 pandemic prediction using time series forecasting models",1st International Conference on Computing, Communication and Networking Technologies (ICCCNT)Kharagpur, India, 01-03 July 2020, pp. 1-7.10.1109/ICCCNT49239.2020.9225319
     [Google Scholar]
  33. GersF.A. EckD. SchmidhuberJ. Applying LSTM to time series predictable through time-window approaches.Neural Nets WIRN Vietri-01LondonSpringer TagliaferriR. MarinaroM. 200219320010.1007/978‑1‑4471‑0219‑9_20
     [Google Scholar]
  34. VermaY. Bidirectional LSTM (long-short term memory) with python codes.2024Available from: https://analyticsindiamag.com/complete-guide-to-bidirectional-lstm-with-python-codes/
  35. BahadP. SaxenaP. KamalR. Fake news detection using bi-directional LSTM-recurrent neural network.Procedia Comput. Sci.2019165748210.1016/j.procs.2020.01.072
     [Google Scholar]
  36. VAR1: Schematic of relationships modeled by vector autoregression at a lag of one.Available from: https://www.researchgate.net/figure/VAR1-Schematic-of-relationships-modeled-by-vector-autoregression-at-a-lag-of-one_fig1_343442292
  37. OhriA. Understanding GRU.Available from: https://www.jigsawacademy.com/blogs/data-science/gru/
  38. WangX. XuJ. ShiW. LiuJ. OGRU: An optimised gated neural network.J. Phys. Conf. Ser.20191325101208910.1088/1742‑6596/1325/1/012089
     [Google Scholar]
  39. Gated Recurrent Units (GRUs) for natural language processing.Available from: https://pythonwife.com/gated-recurrent-units-grus-for-natural-language-processing/
  40. Bitcoin historical data.2012Available from: https://www.kaggle.com/datasets/mczielinski/bitcoin-historical-data
/content/journals/rascs/10.2174/0126662558335176241121113056
Loading
Transient Empirical Machine Learning Models based on Bit Coin Price Prediction using High and Low Values
Recent Advances in Computer Science and Communications 18, E26662558335176 (2025); https://doi.org/10.2174/0126662558335176241121113056
/content/journals/rascs/10.2174/0126662558335176241121113056
/content/journals/rascs/10.2174/0126662558335176241121113056
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): ARIMA; Bi-LSTM; cryptocurrencies; FB-Prophet; GRU; LSTM; Time-Series

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test