Models for forecasting indicators based on neural network, regression analysis, and big data

Andrey A. Tuskov, Ivan Efimov, Botagoz S. Saparova, Altynai A. Saparova, Aigul A. Saparova

2023

Closed access Metadata (CSL-JSON)
DOI 10.1117/12.2669452
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The article discusses an approach to the analysis of static information based on the use of neural network technologies and regression models. The forecast for the neural network was made on the basis of official statistics, data on the development of advanced technologies, and also taking into account the current situation in the dynamics of the incidence in Russia for the period from 2003 to 2020. As a result, forecasts for the next 5 years were determined. Growth is expected to continue, but at a slower pace. At this stage, the incidence and the introduction of quarantine measures adversely affect the situation and lead to a reduction in consumption. It is worth noting that the trends in the production of innovative technologies will continue, despite the negative consequences of the pandemic. This is evidenced by forecast data.