Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

USING RECURRENT NEURAL NETWORKS FOR TIME SERIES FORECASTING

Perepelkin Vadim   (graduate student, Moscow State University of Technology and Management)

Neural networks are widely used in various fields, including medicine, finance, manufacturing and science. They are already successfully used for solving problems of classification, computer vision, video image processing, natural language processing, data and image generation, and many others. In the work under study, the problematic aspects of using recurrent neural networks for forecasting time series are considered. Time series are ubiquitous in the world around us, industry and science. It represents collected historical data, such as the number of people living in a territory, production volumes, fuel consumption volumes, etc. The prediction of future values of time series is an important task in order to be able to prepare in advance for upcoming changes. The construction of a model for predicting the incidence of the COVID-19 virus based on recurrent neural networks is also considered as an example.

Keywords:forecasting, time series, neural networks, models
 

Read the full article …

Citation link:
Perepelkin V. USING RECURRENT NEURAL NETWORKS FOR TIME SERIES FORECASTING // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2023. -№07/2. -С. 80-82 DOI 10.37882/2223-2966.2023.7-2.20
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences