Machine learning approaches for financial time series forecasting
| dc.contributor.author | Derbentsev, Vasyl | |
| dc.contributor.author | Дербенцев, Василь Джоржович | |
| dc.contributor.author | Дербенцев, Василий Джорджевич | |
| dc.contributor.author | Matviichuk, Andrii | |
| dc.contributor.author | Матвійчук, Андрій Вікторович | |
| dc.contributor.author | Матвийчук, Андрей Викторович | |
| dc.contributor.author | Datsenko, Nataliia | |
| dc.contributor.author | Даценко, Наталія Володимирівна | |
| dc.contributor.author | Даценко, Наталья Владимировна | |
| dc.contributor.author | Bezkorovainyi, Vitalii | |
| dc.contributor.author | Безкоровайний, Віталій Сергійович | |
| dc.contributor.author | Безкоровайный, Виталий Сергеевич | |
| dc.contributor.author | Azaryan, Albert | |
| dc.date.accessioned | 2023-12-15T11:56:13Z | |
| dc.date.available | 2023-12-15T11:56:13Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | This paper is discusses the problems of the short-term forecasting of financial time series using supervised machine learning (ML) approach. For this goal, we applied several the most powerful methods including Support Vector Machine (SVM), Multilayer Perceptron (MLP), Random Forests (RF) and Stochastic Gradient Boosting Machine (SGBM). As dataset were selected the daily close prices of two stock index: SP 500 and NASDAQ, two the most capitalized cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), and exchange rate of EUR-USD. As features we used only the past price information. To check the efficiency of these models we made out-of-sample forecast for selected time series by using one step ahead technique. The accuracy rates of the forecasted prices by using ML models were calculated. The results verify the applicability of the ML approach for the forecasting of financial time series. The best out of sample accuracy of short-term prediction daily close prices for selected time series obtained by SGBM and MLP in terms of Mean Absolute Percentage Error (MAPE) was within 0.46-3.71 %. Our results are comparable with accuracy obtained by Deep learning approaches. | |
| dc.identifier.citation | Machine learning approaches for financial time series forecasting [Electronic resource] / Vasily Derbentsev, Andriy Matviychuk, Nataliia Datsenko [et al.] // Monitoring, Modeling & Management of Emergent Economy (M3E2–MLPEED 2020) : proceedings of the selected papers of the special edition of international conference, Odessa, Ukraine, July 13–18, 2020 / [ed.: A. Kiv]. – Electronic text data. – Odessa, 2020. – Vol. 2713 : Machine Learning for Prediction of Emergent Economy Dynamics. – P. 434–450. – Mode of access: https://ceur-ws.org/Vol-2713/paper47.pdf. – Title from screen. | |
| dc.identifier.issn | 1613-0073 | |
| dc.identifier.uri | https://ir.kneu.edu.ua/handle/2010/41675 | |
| dc.language.iso | en | |
| dc.publisher | CEUR Workshop Proceedings | |
| dc.subject | financial time series | |
| dc.subject | short-term forecasting | |
| dc.subject | machine learning | |
| dc.subject | support vector machine | |
| dc.subject | random forest | |
| dc.subject | gradient boosting | |
| dc.subject | multilayer perceptron | |
| dc.title | Machine learning approaches for financial time series forecasting | |
| dc.type | Article |