Contenido principal del artículo

Autores

Debido al alto atractivo de las criptomonedas, los inversionistas y los investigadores han prestado mayor atención en la previsión de los precios de las criptomonedas. Con el desarrollo metodológico del Deep Learning, la previsión de las criptomonedas ha tenido mayor importancia en los últimos años. En este artículo, se evalúan cuatro modelos de Deep Learning: RNN, LSTM, GRU y CNN-LSTM con el objetivo de evaluar el desempeño en el pronóstico del precio de cierre diario de las dos criptomonedas más importantes: Bitcoin y Ethereum. Se utilizaron métricas de análisis de desempeño como MAE, RMSE, MSE y MAPE y como métrica de ajuste, el R2. Cada modelo de Deep Learning fue optimizado a partir de un conjunto de hiperparámetros y para diferentes ventanas de tiempo. Los resultados experimentales mostraron que el algoritmo RNN tuve un rendimiento superior en la predicción del precio de Bitcoin y el algoritmo LSTM en el precio de Ethereum. Incluso, ambos métodos presentaron mejor desempeño con dos modelos de la literatura evaluados. Finalmente, la confiabilidad del pronóstico de cada modelo se evaluó analizando la autocorrelación de los errores y se encontró que los dos modelos más eficientes tienen alto poder de generalización.

Erick Lambis-Alandete, Universidad Nacional de Colombia, Facultad de Minas, Medellín, Colombia

https://orcid.org/0000-0002-5615-5437

1.
Lambis-Alandete E, Jiménez Gómez M, Velásquez-Henao JD. Comparación de algoritmos de Deep Learning para pronósticos en los precios de criptomonedas. inycomp [Internet]. 18 de septiembre de 2023 [citado 8 de mayo de 2024];25(3):e-21312845. Disponible en: https://revistaingenieria.univalle.edu.co/index.php/ingenieria_y_competitividad/article/view/12845

Kang CY, Lee CP, Lim KM. Cryptocurrency Price Prediction with Convolutional Neural Network and Stacked Gated Recurrent Unit. Data. 2022;7(11). https://doi.org/10.3390/data7110149 DOI: https://doi.org/10.3390/data7110149

Fleischer JP, von Laszewski G, Theran C, Bautista YJP. Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory. Algorithms. 2022;15(7). https://doi.org/10.3390/a15070230 DOI: https://doi.org/10.3390/a15070230

Ammer MA, Aldhyani THH. Deep Learning Algorithm to Predict Cryptocurrency Fluctuation Prices: Increasing Investment Awareness. Electron. 2022;11(15). https://doi.org/10.3390/electronics11152349 DOI: https://doi.org/10.3390/electronics11152349

Patel MM, Tanwar S, Gupta R, Kumar N. A Deep Learning-based Cryptocurrency Price Prediction Scheme for Financial Institutions. J Inf Secur Appl. 2020;55. https://doi.org/10.1016/j.jisa.2020.102583 DOI: https://doi.org/10.1016/j.jisa.2020.102583

Lahmiri S, Bekiros S. Cryptocurrency forecasting with deep learning chaotic neural networks. Chaos, Solitons and Fractals. 2019;118:35-40. https://doi.org/10.1016/j.chaos.2018.11.014 DOI: https://doi.org/10.1016/j.chaos.2018.11.014

Wu C-H, Lu C-C, Ma Y-F, Lu R-S. A new forecasting framework for bitcoin price with LSTM. In: IEEE International Conference on Data Mining Workshops, ICDMW. 2019. p. 168-75.https://doi.org/10.1109/ICDMW.2018.00032 DOI: https://doi.org/10.1109/ICDMW.2018.00032

Pintelas E, Livieris IE, Stavroyiannis S, Kotsilieris T, Pintelas P. Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach. Vol. 584 IFIP, IFIP Advances in Information and Communication Technology. 2020. 99-110 p. https://doi.org/10.1007/978-3-030-49186-4_9 DOI: https://doi.org/10.1007/978-3-030-49186-4_9

Awoke T, Rout M, Mohanty L, Satapathy SC. Bitcoin Price Prediction and Analysis Using Deep Learning Models. Vol. 134, Lecture Notes in Networks and Systems. 2021. 631-640 p. https://doi.org/10.1007/978-981-15-5397-4_63 DOI: https://doi.org/10.1007/978-981-15-5397-4_63

Oyedele AA, Ajayi AO, Oyedele LO, Bello SA, Jimoh KO. Performance evaluation of deep learning and boosted trees for cryptocurrency closing price prediction. Expert Syst Appl. 2023;213. https://doi.org/10.1016/j.eswa.2022.119233 DOI: https://doi.org/10.1016/j.eswa.2022.119233

Ferdiansyah, Othman SH, Radzi RZM, Stiawan D, Sutikno T. Hybrid gated recurrent unit bidirectional-long short-term memory model to improve cryptocurrency prediction accuracy. IAES Int J Artif Intell. 2023;12(1):251-61. https://doi.org/10.11591/ijai.v12.i1.pp251-261 DOI: https://doi.org/10.11591/ijai.v12.i1.pp251-261

Nasirtafreshi I. Forecasting cryptocurrency prices using Recurrent Neural Network and Long Short-term Memory. Data Knowl Eng. 2022;139. https://doi.org/10.1016/j.datak.2022.102009 DOI: https://doi.org/10.1016/j.datak.2022.102009

Bao W, Yue J, Rao Y. A deep learning framework for financial time series using stacked autoencoders and longshort term memory. PLoS One. 2017;12(7):1-24. https://doi.org/10.1371/journal.pone.0180944 DOI: https://doi.org/10.1371/journal.pone.0180944

Kim HY, Won CH. Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Syst Appl [Internet]. 2018;103:25-37. Available from: https://doi.org/10.1016/j.eswa.2018.03.002 DOI: https://doi.org/10.1016/j.eswa.2018.03.002

Zha W, Liu Y, Wan Y, Luo R, Li D, Yang S, et al. Forecasting monthly gas field production based on the CNN-LSTM model. Energy [Internet]. 2022;260(August):124889. Available from: https://doi.org/10.1016/j.energy.2022.124889 DOI: https://doi.org/10.1016/j.energy.2022.124889

Luo H, Wang D, Cheng J, Wu Q. Multi-step-ahead copper price forecasting using a two-phase architecture based on an improved LSTM with novel input strategy and error correction. Resour Policy. 2022;79(August). https://doi.org/10.1016/j.resourpol.2022.102962 DOI: https://doi.org/10.1016/j.resourpol.2022.102962

Lawi A, Mesra H, Amir S. Implementation of Long Short-Term Memory and Gated Recurrent Units on grouped time-series data to predict stock prices accurately. J Big Data [Internet]. 2022;9(1). Available from: https://doi.org/10.1186/s40537-022-00597-0 DOI: https://doi.org/10.1186/s40537-022-00597-0

Tang H, Ling X, Li L, Xiong L, Yao Y, Huang X. One-shot pruning of gated recurrent unit neural network by sensitivity for time-series prediction. Neurocomputing [Internet]. 2022;512:15-24. Available from: https://doi.org/10.1016/j.neucom.2022.09.026 DOI: https://doi.org/10.1016/j.neucom.2022.09.026

Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, et al. Recent advances in convolutional neural networks. Pattern Recognit [Internet]. 2018;77:354-77. Available from: https://doi.org/10.1016/j.patcog.2017.10.013 DOI: https://doi.org/10.1016/j.patcog.2017.10.013

Ghimire S, Deo RC, Casillas-Pérez D, Salcedo-Sanz S, Sharma E, Ali M. Deep learning CNN-LSTM-MLP hybrid fusion model for feature optimizations and daily solar radiation prediction. Meas J Int Meas Confed [Internet]. 2022;202(August):111759. Available from: https://doi.org/10.1016/j.measurement.2022.111759 DOI: https://doi.org/10.1016/j.measurement.2022.111759

Livieris IE, Stavroyiannis S, Pintelas E, Pintelas P. A novel validation framework to enhance deep learning models in time-series forecasting. Neural Comput Appl. 2020;32(23):17149-67. https://doi.org/10.1007/s00521-020-05169-y DOI: https://doi.org/10.1007/s00521-020-05169-y

Recibido 2023-03-06
Aceptado 2023-09-18
Publicado 2023-09-18