ANALIZANDO LA EFICACIA DE LOS ALGORITMOS DE PREDICCIÓN DE WEKA PARA LA PREDICCIÓN DEL COMPORTAMIENTO DEL BITCOIN
Visualizações: 12DOI:
https://doi.org/10.56579/rei.v8i2.2629Palabras clave:
BTC, Algoritmos, Series Temporales, WEKA, CriptomonedaResumen
Este estudio investigó el rendimiento predictivo del software WEKA en la predicción de series temporales de Bitcoin (BTC), comparando sus resultados con los obtenidos mediante R, utilizando datos históricos desde mayo de 2013 hasta diciembre de 2024 (4.254 observaciones). El análisis empleó múltiples algoritmos de aprendizaje automático evaluados mediante las métricas MAPE, RMSE y MAE. Los resultados revelaron que, aunque R obtuvo un rendimiento superior en la mayoría de los modelos, especialmente en términos de reducción del error, WEKA presentó un rendimiento competitivo y, en algunos casos, superior en modelos específicos: M5Rules alcanzó un MAPE de 2,25% y un RMSE de $1.449,49, mientras que SMOreg obtuvo un MAPE de 2,40% y un RMSE de $1.450,25 en la pestaña Forecast. Los modelos basados en reglas, M5Rules y M5P, mostraron un rendimiento significativamente superior en R, con un MAPE de 3,79% y un RMSE de $2.112,25, en contraste con los resultados modestos en WEKA, donde presentaron una correlación cercana a cero en la pestaña Classify. La prueba KPSS confirmó la no estacionariedad de la serie (valor p = 0,01), y la prueba de causalidad de Granger identificó una dependencia temporal significativa en el rezago 5 (valor p = 8,7e-06). Los hallazgos indican que, aunque WEKA ofrece una funcionalidad adecuada para modelos específicos en tareas de predicción secuencial, presenta inestabilidades y limitaciones en la modelización temporal integral, lo que convierte a R en una alternativa más robusta para aplicaciones financieras complejas.
Descargas
Citas
ALI, A. et al. Network intrusion detection leveraging machine learning and feature selection. In: IEEE. 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET), 2020, [S.l.]. Anais [...]. Piscataway: IEEE, 2020. p. 49–53. DOI: https://doi.org/10.1109/HONET50430.2020.9322813
BEHNOOD, A. et al. Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm. Construction and Building Materials, v. 142, p. 199–207, 2017. DOI: https://doi.org/10.1016/j.conbuildmat.2017.03.061
BREIMAN, L. Bagging predictors. Machine Learning, v. 24, p. 123–140, 1996. DOI: https://doi.org/10.1023/A:1018054314350
BREIMAN, L. Random forests. Machine Learning, v. 45, p. 5–32, 2001. DOI: https://doi.org/10.1023/A:1010933404324
CARUANA, R. et al. Ensemble selection from libraries of models. In: Proceedings of the Twenty-First International Conference on Machine Learning, 2004, [S.l.]. Anais [...]. [S.l.]: [s.n.], 2004. p. 18. DOI: https://doi.org/10.1145/1015330.1015432
CHOWDHURY, R. et al. An approach to predict and forecast the price of constituents and index of cryptocurrency using machine learning. Physica A: Statistical Mechanics and its Applications, v. 551, p. 124569, 2020. DOI: https://doi.org/10.1016/j.physa.2020.124569
CONTRERAS, R. C. et al. Genetic algorithm for feature selection applied to financial time series monotonicity prediction: Experimental cases in cryptocurrencies and Brazilian assets. Entropy, v. 26, n. 3, p. 177, 2024. DOI: https://doi.org/10.3390/e26030177
DERBENTSEV, V. et al. Forecasting cryptocurrency prices time series using machine learning approach. In: SHS WEB OF CONFERENCES, 2019, [S.l.]. Anais [...]. [S.l.]: EDP Sciences, 2019. v. 65, p. 02001. DOI: https://doi.org/10.1051/shsconf/20196502001
DERBENTSEV, V.; MATVIYCHUK, A.; SOLOVIEV, V. N. Forecasting of cryptocurrency prices using machine learning. In: Advanced Studies of Financial Technologies and Cryptocurrency Markets. [S.l.]: Springer, 2020. p. 211–231. DOI: https://doi.org/10.1007/978-981-15-4498-9_12
DERBENTSEV, V. et al. Forecasting cryptocurrency prices using ensembles-based machine learning approach. In: IEEE. International Conference on Problems of Infocommunications. Science and Technology (PIC S&T), 2020, [S.l.]. Anais [...]. Piscataway: IEEE, 2020. p. 707–712. DOI: https://doi.org/10.1109/PICST51311.2020.9468090
FANG, Q. et al. Prediction of blast-induced ground vibration in open-pit mines using a new technique based on imperialist competitive algorithm and M5Rules. Natural Resources Research, v. 29, n. 2, p. 791–806, 2020. DOI: https://doi.org/10.1007/s11053-019-09577-3
FRANK, E.; MAYO, M.; KRAMER, S. Alternating model trees. In: Proceedings of the 30th Annual ACM Symposium on Applied Computing, 2015, [S.l.]. Anais [...]. [S.l.]: [s.n.], 2015. p. 871–878. DOI: https://doi.org/10.1145/2695664.2695848
GNANAMBAL, S. et al. Classification algorithms with attribute selection: an evaluation study using WEKA. International Journal of Advanced Networking and Applications, v. 9, n. 6, p. 3640–3644, 2018.
HARYADI, D. et al. Implementation of support vector regression for polkadot cryptocurrency price prediction. JOIV: International Journal on Informatics Visualization, v. 6, n. 1-2, p. 201–207, 2022. DOI: https://doi.org/10.30630/joiv.6.1-2.945
HOROWITZ, J.; KLEMELÄ, J.; MAMMEN, E. Optimal estimation in additive regression models. Bernoulli, v. 12, n. 2, p. 271–298, 2006. DOI: https://doi.org/10.3150/bj/1145993975
KALEKAR, P. S. Time series forecasting using Holt-Winters exponential smoothing. Kanwal Rekhi School of Information Technology, v. 4329008, n. 13, p. 1–13, 2004.
KARGAR, K.; SAFARI, M. J. S.; KHOSRAVI, K. Weighted instances handler wrapper and rotation forest-based hybrid algorithms for sediment transport modeling. Journal of Hydrology, v. 598, p. 126452, 2021. DOI: https://doi.org/10.1016/j.jhydrol.2021.126452
KURNIAWAN, K.; MADELAN, S. Forecasting using time series analysis method in cryptocurrency period 2015–2022. International Journal of Innovative Science and Research Technology, v. 7, p. 1454–1459, 2022.
LV, L.-T.; JI, N.; ZHANG, J.-L. A RBF neural network model for anti-money laundering. In: International Conference on Wavelet Analysis and Pattern Recognition, 2008, [S.l.]. Anais [...]. Piscataway: IEEE, 2008. v. 1, p. 209–215. DOI: https://doi.org/10.1109/ICWAPR.2008.4635778
NEWSON, R. Parameters behind “nonparametric” statistics: Kendall’s tau, Somers’ D and median differences. The Stata Journal, v. 2, n. 1, p. 45–64, 2002. DOI: https://doi.org/10.1177/1536867X0200200103
NIRANJAN, A. et al. ERCR TV: Ensemble of random committee and random tree for efficient anomaly classification using voting. In: Proceedings of the 2018 3rd International Conference for Convergence in Technology (I2CT), 2018, [S.l.]. Anais [...]. Piscataway: IEEE, 2018. p. 1–5. DOI: https://doi.org/10.1109/I2CT.2018.8529797
PAUDEL, N.; BHATTA, J. Mushroom classification using random forest and REP tree classifiers. Nepal Journal of Mathematical Sciences, v. 3, n. 1, p. 111–116, 2022. DOI: https://doi.org/10.3126/njmathsci.v3i1.44130
POYRAZ, İ.; GÜRHANLI, A. Demand forecasting with time series analysis using drug sales data. International Journey of Engineering Research and Applications, v. 10, n. 7, p. 51-54, 2020.
RAMCHOUN, H. et al. Multilayer perceptron: Architecture optimization and training. International Journal of Interactive Multimedia and Artificial Intelligence, v. 4, n. 1, p. 26-30, 2016. DOI: https://doi.org/10.9781/ijimai.2016.415
REDDY, B. H. M.; REDDY, S. V.; SAROJAMMA, B. Data Mining Techniques for estimation of wind speed using WEKA. International Journal of Computer Sciences and Engineering (IJCSE), v. 9, n. 9, p. 49–53, 2021. DOI: https://doi.org/10.26438/ijcse/v9i9.4851
SABANCI, K.; ÜNLERŞEN, M. F.; POLAT, K. Classification of different forest types with machine learning algorithms. Research in Rural Development, v. 1, p. 254–260, 2016.
SAMSON, T. K. Comparative analysis of machine learning algorithms for daily cryptocurrency price prediction. Information Dynamics and Applications, v. 3, n. 1, p. 64–76, 2024. DOI: https://doi.org/10.56578/ida030105
SCHULZ, E.; SPEEKENBRINK, M.; KRAUSE, A. A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. Journal of Mathematical Psychology, v. 85, p. 1–16, 2018. DOI: https://doi.org/10.1016/j.jmp.2018.03.001
SHI, L. et al. Signal prediction based on boosting and decision stump. International Journal of Computational Science and Engineering, v. 16, n. 2, p. 117–122, 2018. DOI: https://doi.org/10.1504/IJCSE.2018.090450
SINGH, P.; AGRAWAL, S. Node localization in wireless sensor networks using the M5P tree and SMOreg algorithms. In: 5th International Conference on Computational Intelligence and Communication Networks, 2013, [S.l.]. Anais [...]. Piscataway: IEEE, 2013. p. 104–104. DOI: https://doi.org/10.1109/CICN.2013.32
SKOWRON, A.; SURAJ, Z. A parallel algorithm for real-time decision making: a rough set approach. Journal of Intelligent Information Systems, v. 7, p. 5–28, 1996. DOI: https://doi.org/10.1007/BF00125520
SU, X.; YAN, X.; TSAI, C.-L. Linear regression. Wiley Interdisciplinary Reviews: Computational Statistics, v. 4, n. 3, p. 275–294, 2012. DOI: https://doi.org/10.1002/wics.1198
SUN, G. Cryptocurrency price prediction based on Xgboost, LightGBM and BNN. Applied and Computational Engineering, v. 49, p. 273–279, 2024. DOI: https://doi.org/10.54254/2755-2721/49/20241414
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 Revista de Estudios Interdisciplinarios

Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
La Revista de Estudios Interdisciplinares adopta la Licencia Creative Commons Atribución 4.0 Internacional (CC BY 4.0), que permite compartir y adaptar el trabajo, incluso con fines comerciales, siempre que se otorgue la atribución adecuada y se reconozca la publicación original en esta revista.










