BTC illiquidity prediction using high-dimensional features and hybrid CNNRNN

Authors

  • Ehsan Karimi Shahmarvandi Department of Computer Engineering, University of Amsterdam, Amsterdam, Netherlands. https://orcid.org/0009-0002-4210-1830
  • Reza Shoukhcheshm Department of Computer Engineering, Amir Kabir University, Tehran, Iran.
  • Mohammadreza Gheisari Najafabadi Department of Industrial Management, Management and Accounting Faculty, Shahid Beheshti University, Tehran, Iran.
  • Sasan Mazaheri Department of Industrial Management, Management and Accounting Faculty, Shahid Beheshti University, Tehran, Iran.
  • Mohammad Ghadiri Department of Computer Science, Lakehead University, Thunder Bay, Canada.
  • Mahboobeh Shafiei Department of Computer Engineering, Shiraz University, Shiraz, Iran.
  • Ramin Mousa * Department of Computer Engineering, Zanjan University, Zanjan, Iran.

https://doi.org/10.48314/ceti.v2i2.56

Abstract

The ease of converting an asset (such as stock or cryptocurrency) into cash or another asset without incurring a loss is referred to as liquidity, and the relationship between the time scale and the price scale of the investment represents this concept. The opposite of liquidity is illiquidity, which creates challenges in converting assets into cash in bearish markets. This paper examines the illiquidity of Bitcoin (BTC) and presents hybrid approaches based on deep learning. The hybrid model combines spatial features with CNN and temporal features with RNN. Bitcoin hash rate information was collected in 3 different periods to evaluate the combined approaches. Six combined models and seven basic models were considered to evaluate the results. The combined model, based on CNN and Bi-IndRNN, achieved the best results in the MAE evaluation criterion for all three intervals. This approach achieves MAEs of 0.51, 1.18, and 4.97 for intervals I, II, and III, respectively. Additionally, the Pearson correlation analysis has shown that the two tasks of price prediction and illiquidity prediction are independent of each other, indicating that these tasks are completely separate.

Keywords:

Illiquidity prediction, BTC hashrate, Hybrid model, CNNRNN, Cryptocurrency

References

  1. [1] Huberman, G., Leshno, J. D., & Moallemi, C. (2019). An economist’s perspective on the BTC payment system. AEA papers and proceedings, 109, 93–96. https://doi.org/10.1257/pandp.20191019
  2. [2] Sensoy, A. (2019). The inefficiency of BTC revisited: A high-frequency analysis with alternative currencies. Finance research letters, 28, 68–73. https://doi.org/10.1016/j.frl.2018.04.002
  3. [3] Saito, T. (2015). A microeconomic analysis of BTC and illegal activities. In Handbook of digital currency (pp. 231–248). San Diego: Academic Press. https://doi.org/10.1016/B978-0-12-802117-0.00012-6
  4. [4] Huang, J., Mensi, M., Oveisi, E., Mantella, V., & Buonsanti, R. (2019). Structural sensitivities in bimetallic catalysts for electrochemical CO2 reduction revealed by Ag–Cu nanodimers. Journal of the American chemical society. https://pubs.acs.org/doi/abs/10.1021/jacs.8b12381
  5. [5] Kajtazi, A., & Moro, A. (2019). The role of BTC in well diversified portfolios: A comparative global study. International review of financial analysis, 61, 143–157. https://doi.org/10.1016/j.irfa.2018.10.003
  6. [6] Conti, M., Kumar, E. S., Lal, C., & Ruj, S. (2018). A survey on security and privacy issues of BTC. IEEE communications surveys & tutorials, 20(4), 3416–3452. https://doi.org/10.1109/COMST.2018.2842460
  7. [7] Lee, J. H., & Pilkington, M. (2017). How the blockchain revolution will reshape the consumer electronics industry [Future directions]. IEEE consumer electronics magazine, 6(3), 19–23. https://doi.org/10.1109/MCE.2017.2684916
  8. [8] Baur, D. G., Hong, K., & Lee, A. D. (2018). BTC: Medium of exchange or speculative assets? Journal of international financial markets, institutions and money, 54, 177–189. https://doi.org/10.1016/j.intfin.2017.12.004
  9. [9] Chen, B., Zeng, X., Liu, Y., Xiao, F., Huang, M., Bing Tan, K., … & Zhan, G. (2022). Thermal decomposition kinetics of M−BTC (M = Cu, Co, Zn, and Ce) and M−BTC/Pt composites under oxidative and reductive environments. Chemical engineering journal, 450, 138470. https://doi.org/10.1016/j.cej.2022.138470
  10. [10] Dyhrberg, A. H., Foley, S., & Svec, J. (2018). How investible is BTC? Analyzing the liquidity and transaction costs of BTC markets. Economics letters, 171, 140–143. https://doi.org/10.1016/j.econlet.2018.07.032
  11. [11] Wang, B., Long, W., & Wei, X. (2018). Investor attention, market liquidity and stock return: A new perspective. Asian economic and financial review, 8(3), 341. https://doi.org/10.18488/journal.aefr.2018.83.341.352
  12. [12] Będowska-Sójka, B., Hinc, T., & Kliber, A. (2020). Volatility and liquidity in cryptocurrency markets—the causality approach. Contemporary trends and challenges in finance (pp. 31–43). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-43078-8_3
  13. [13] Cortez, K., Rodríguez-García, M. D., & Mongrut, S. (2021). Exchange market liquidity prediction with the k-nearest neighbor approach: Crypto vs. fiat currencies. Mathematics, 9(1). https://doi.org/10.3390/math9010056
  14. [14] Mudassir, M., Bennbaia, S., Unal, D., & Hammoudeh, M. (2025). Time-series forecasting of BTC prices using high-dimensional features: A machine learning approach. Neural computing and applications, 37(28), 22979–22993. https://doi.org/10.1007/s00521-020-05129-6
  15. [15] Liu, F. T., Ting, K. M., & Zhou, Z. H. (2012). Isolation-based anomaly detection. ACM transactions on knowledge discovery, 6(1). https://doi.org/10.1145/2133360.2133363
  16. [16] Hansen, P. R., Kim, C., & Kimbrough, W. (2024). Periodicity in cryptocurrency volatility and liquidity*. Journal of financial econometrics, 22(1), 224–251. https://doi.org/10.1093/jjfinec/nbac034
  17. [17] Marjan, K., Reza, N. M., Mahmood, F., Iman, A., Rouzbeh, N., & H., G. A. (2024). Improving long-term flood forecasting accuracy using ensemble deep learning models and an attention mechanism. Journal of hydrologic engineering, 29(6), 4024042. https://doi.org/10.1061/JHYEFF.HEENG-6262
  18. [18] You, Y. (2025). Research on precision optimization of deep learning method based on vat-lstm and transformer encoder in financial data prediction. 2025 international conference on intelligent systems and computational networks (ICISCN) (pp. 1–6). IEEE. https://doi.org/10.1109/ICISCN64258.2025.10934410
  19. [19] Sharma, A., & Kansal, V. (2024). Comprehensive evaluation of cnn, rnn, and crnn for document retrieval in healthcare systems. 2024 5th international conference on recent trends in computer science and technology (ICRTCST) (pp. 491–496). IEEE. https://doi.org/10.1109/ICRTCST61793.2024.10578433
  20. [20] Kumar, M., Khan, L., & Chang, H. T. (2025). Evolving techniques in sentiment analysis: A comprehensive review. PeerJ computer science, 11, e2592. https://doi.org/10.7717/peerj-cs.2592
  21. [21] Biswas, D., & Gil, J. M. (2024). Design and implementation for research paper classification based on CNN and RNN models. Journal of internet technology, 25(4), 637–645. https://jit.ndhu.edu.tw/article/view/3081/0
  22. [22] Manalu, H. V., & Rifai, A. P. (2024). Detection of human emotions through facial expressions using hybrid convolutional neural network-recurrent neural network algorithm. Intelligent systems with applications, 21, 200339. https://doi.org/10.1016/j.iswa.2024.200339
  23. [23] Yoga, M., Ramyasri, M. M., Bhavatharini, N., Harini, M., & NivethaSri, A. (2024). Unravelling visual narratives with deep learning for image caption generation. 2024 international conference on cognitive robotics and intelligent systems (ICC-ROBINS) (pp. 387-393). IEEE. https://doi.org/10.1109/ICC-ROBINS60238.2024.10533953
  24. [24] Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. ArXiv preprint arxiv:1506.00019, abs/1506.0. https://doi.org/10.48550/arXiv.1506.00019
  25. [25] Li, X., Zhang, W., Ding, Y., Cai, J., & Yan, X. (2025). Rolling bearing degradation stage division and RUL prediction based on recursive exponential slow feature analysis and Bi-LSTM model. Reliability engineering & system safety, 259, 110923. https://doi.org/10.1016/j.ress.2025.110923
  26. [26] Li, S., Li, W., Cook, C., Zhu, C., & Gao, Y. (2018). Independently recurrent neural network (INDRNN): building a longer and deeper {RNN}. 2018 conference on computer vision and pattern recognition, {CVPR} 2018, Salt Lake City, UT, USA (pp. 5457–5466). IEEE. 10.1109/CVPR.2018.00572
  27. [27] Yu, L., Zha, R., Stafylas, D., He, K., & Liu, J. (2020). Dependences and volatility spillovers between the oil and stock markets: New evidence from the copula and VAR-BEKK-GARCH models. International review of financial analysis, 68, 101280. https://doi.org/10.1016/j.irfa.2018.11.007

Downloads

Published

2025-04-10

Issue

Vol. 2 No. 2 (2025): Computational Engineering and Technology Innovations

Section

Articles

How to Cite

Karimi Shahmarvandi, E., Shoukhcheshm, R. ., Gheisari Najafabadi, M. ., Mazaheri, S., Ghadiri, M. ., Shafiei, M. ., & Mousa, R. . (2025). BTC illiquidity prediction using high-dimensional features and hybrid CNNRNN. Computational Engineering and Technology Innovations, 2(2), 62-80. https://doi.org/10.48314/ceti.v2i2.56

Similar Articles

1-10 of 13

You may also start an advanced similarity search for this article.