![]() ![]() The basis of the whole set of methods of socio-economic forecasting is traditionally made up of statistical methods used to build appropriate models of time series. This task ultimately acts as an objective condition for the implementation of an effective economic policy. In this regard, the development of tools to justify the values of forecast economic parameters, which allows us to achieve planned control figures with a high degree of reliability, is an important scientific task. This means that the basis for future development for the most part lies in the indicators of past periods obtained with a significant delay, if we take into account the real situation with the publication of official statistics. To date, the management of the region is carried out through monitoring by adjusting the planned values in accordance with those actually achieved. Management of the development of social and economic systems is mainly based on documents containing the planned values of indicators on a particular topic (strategy, concept, forecast, etc.). (2020) Transfer learning and domain adaptation based on modeling of socio-economic systems. Key words: transfer learning domain adaptation, simulation modeling decision support systems socio-economic development of regions.Ĭitation: Kazakov O.D., Mikheenko O.V. Transfer learning and domain adaptation based on modeling of socio-economic systemsĮ-mail: State Technological University of Engineering Address: 3, Stanke Dimitrov Avenue, Bryansk 241037, Russia The suggested approach makes it possible to expand the possibilities of complex application of simulation methods for building a neural network in order to justify the parameters of the development of the socio-economic system and allows us to get information about its future state. The original LSTM training was realized with the help of TensorFlow, an open source software library for machine learning. To achieve this goal, a simulation model was developed by combining notations of system dynamics with agent-based modeling in the AnyLogic system, which allows us to investigate the influence of a combination of factors on the key parameters of the efficiency of the socio-economic system. ![]() ![]() The authors have implemented training of the original recurrent neural network on synthetic data obtained as a result of simulation, followed by transfer training and domain adaptation. In particular, in the context of applying machine learning algorithms, one of the problems is the limited number of marked data. Review of existing approaches in this area allows us to draw a conclusion about the need to solve a number of practical issues of improving the quality of predictive analytics for preparing forecasts of the development of socio-economic systems. This article deals with the application of transfer learning methods and domain adaptation in a recurrent neural network based on the long short-term memory architecture (LSTM) to improve the efficiency of management decisions and state economic policy. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |