UDC 004.9
FORECASTING MODULE FRAMEWORK ARCHITECTURE IN SOCIOLOGICAL RESEARCH INFORMATION-ANALYTICAL SYSTEM
A. M. Kuznetsov, graduate student, TSTU, Tambov, Russia;
orcid.org/0000-0003-2640-3417, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
This article presents the framework architecture for the forecasting module in the sociological research information-analytical system (IAS). The integration of modern approaches and predictive analytics methods for analyzing and forecasting social processes is considered, including linear and logistic regression, time series models (ARIMA, SARIMA, SARIMAX), machine learning methods, and neural networks (LSTM, BERT). The module provides good forecast quality, flexibility and adaptability of analysis taking into account complex dependencies in the data.
Key words: : Information-analytical system (IAS), sociological research, framework, forecasting, neural networks, LSTM, BERT, machine learning, time series, regression analysis, SARIMAX.