Open AccessAPPLICATION OF ARTIFICIAL INTELLIGENCE TO BITCOIN COURSE MODELLING
Author(s) -
Olena Liashenko,
Tetyana Kravets,
Y. Repetskiyi
Publication year - 2020
Publication title -
vìsnik. ekonomìka/vìsnik kiïvsʹkogo nacìonalʹnogo unìversitetu ìmenì tarasa ševčenka. serìâ ekonomìka
Language(s) - English
Resource type - Journals
eISSN - 2079-908X
pISSN - 1728-2667
DOI - 10.17721/1728-2667.2020/209-2/2
Subject(s) - artificial neural network , dependency (uml) , computer science , artificial intelligence , standard deviation , course (navigation) , term (time) , series (stratigraphy) , nonlinear system , time series , radial basis function , machine learning , basis (linear algebra) , function (biology) , algorithm , mathematics , statistics , engineering , paleontology , physics , quantum mechanics , biology , aerospace engineering , geometry , evolutionary biology
Artificial neural networks are modern methods suitable for solving the problem of nonlinear dependency approximation, which is successfully applied in many fields. This paper compares the predictive capabilities of Back Propagation, Radial Basis Function, Extreme Learning Machine, and Long-Short Term Memory neural networks to determine which artificial intelligence algorithm is best for modeling the price of Bitcoin opening. The criterion for comparing network performance was the standard deviation, the mean absolute deviation, and the accuracy of predicting the direction of change of course. At the same time, in the study of time series, it is recommended to perform a comprehensive data analysis using appropriate networks, depending on the length of the series and the specificity of the database.