Forecasting cryptocurrency prices time series using machine learning approach

dc.contributor.authorDerbentsev, Vasily
dc.contributor.authorДербенцев, Василь Джоржович
dc.contributor.authorDatsenko, Natalia
dc.contributor.authorДаценко, Наталія Володимирівна
dc.contributor.authorStepanenko, Olga
dc.contributor.authorСтепаненко, Ольга Петрівна
dc.contributor.authorBezkorovainyi, Vitaly
dc.contributor.authorБезкоровайний, Віталій Сергійович
dc.date.accessioned2021-10-12T12:14:32Z
dc.date.available2021-10-12T12:14:32Z
dc.date.issued2019-05
dc.description.abstractThis paper describes the construction of the short-term forecasting model of cryptocurrencies’ prices using machine learning approach. The modified model of Binary Auto Regressive Tree (BART) is adapted from the standard models of regression trees and the data of the time series. BART combines the classic algorithm classification and regression trees (C&RT) and autoregressive models ARIMA. Using the BART model, we made a short-term forecast (from 5 to 30 days) for the 3 most capitalized cryptocurrencies: Bitcoin, Ethereum and Ripple. We found that the proposed approach was more accurate than the ARIMA-ARFIMA models in forecasting cryptocurrencies time series both in the periods of slow rising (falling) and in the periods of transition dynamics (change of trend).uk_UA
dc.identifier.citationForecasting cryptocurrency prices time series using machine learning approach [Electronic resource] / Vasily Derbentsev, Natalia Datsenko, Olga Stepanenko, Vitaly Bezkorovainyi1 // SHS Web of Conferences : the 8th International Conference on Monitoring, Modeling & Management of Emergent Economy (M3E2 2019), Odessa, Ukraine, May 22–24, 2019 / [ed. board: S. Semerikov et al.]. – Electronic text data. – Odessa, 2019. – Vol. 65. – Mode of access: https://doi.org/10.1051/shsconf/20196502001. – Title from screen.uk_UA
dc.identifier.issn2261-2424
dc.identifier.urihttps://ir.kneu.edu.ua:443/handle/2010/36616
dc.language.isoenuk_UA
dc.publisherEDP Sciencesuk_UA
dc.titleForecasting cryptocurrency prices time series using machine learning approachuk_UA
dc.typeArticleuk_UA
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2-shswoc65.pdf
Size:
831.13 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: