Translation. Region: Russian Federal
Source: State University of Management – Official website of the State –
A scientific team of scientists from the State University of Management, headed by Doctor of Technical Sciences, Professor Alexey Terentyev, has developed unique predictive models designed for intelligent data analysis. Their use allows forecasting future events in the interaction of complex commercial and production structures with the external environment. For example, for the distribution of resources between system objects for its effective development.
A special feature of the developed models is the ability to find solutions aimed at the effective development of multi-level systems and independent of the subjectivity characteristic of methods based on expert assessments.
The uniqueness of the methodology – the analytical determination of weighting coefficients and, as a result, obtaining a more objective solution – is critically important for systems with contradictory goal setting, which includes transport and logistics production.
Today, the models are used in research by SMU scientists in the field of logistics in the development of a rating system for transport and logistics enterprises, which has made it possible to increase system efficiency compared to the Laplace criteria and Fishburne estimates by 16% and 26%, respectively.
“The predictive modeling methodology developed at the State University of Management also formed the basis for the methodology for assessing the quality of passenger service in the logistics system of interaction between modes of transport. This allows us to solve the problems of determining the vector assessment of increasing the efficiency of the system based on a significant set of indicators of the quality of public transport services,” notes Maxim Pletnev, Head of the Department for Coordination of Scientific Research at the State University of Management.
The above advantages allow the developed models to be used not only in logistics, but also in other areas of scientific research, including machine learning technologies and neural network modeling methods. This enables researchers to obtain the most accurate scenarios and forecasts of the states of the systems under study in conditions of uncertainty in the external environment.
Please note: This information is raw content directly from the source of the information. It is exactly what the source states and does not reflect the position of MIL-OSI or its clients.