|
advertisement |
|
|
|
|
|
|
Industrial Automatic Control Systems and Controllers Annotation << Back
Method of Automated Short-term Forecasting of Time Series in Online Mode |
V.S. Tormozov, E.A. Kulpeys, K.K. Smagulova, E.F. Amirova, P.K. Korotkov, M.R. Bogdanov, S.V. Vygovskiy
The article considers the development of a software system for informing and forecasting the time series, using the example of the exchange rate on the Forex stock exchange using a mathematical apparatus of artifi cial neural networks. The problem of predicting future values of the characteristics of a complex system has been and remains today. Along with traditional methods for predicting time series, the theory of artifi cial neural networks is currently actively used, which has proven itself in the fi eld of control, where the use of human intelligence was previously necessary, in particular in solving prediction problems. Using the currency quotation value prediction model, you can make fairly reliable short-term forecasts. For most sample samples for testing, the forecast showed the correct direction of short-term change in the study quotation. Using the currency quotation value prediction model, you can make fairly reliable short-term forecasts. For most sample samples for testing, the forecast showed the correct direction of short-term change in the study quotation. With the help of the constructed forecasting model, you can make fairly reliable short-term forecasts.
Keywords: software system; forecasting; time series, Forex; currency quotes.
DOI: 10.25791/asu.7.2021.1296
Pp. 32-40. |
|
|
|
Last news:
Выставки по автоматизации и электронике «ПТА-Урал 2018» и «Электроника-Урал 2018» состоятся в Екатеринбурге Открыта электронная регистрация на выставку Дефектоскопия / NDT St. Petersburg Открыта регистрация на 9-ю Международную научно-практическую конференцию «Строительство и ремонт скважин — 2018» ExpoElectronica и ElectronTechExpo 2018: рост площади экспозиции на 19% и новые формы контент-программы Тематика и состав экспозиции РЭП на выставке "ChipEXPO - 2018" |