Досліджується проблема прийняття рішень за допомогою моделі стохастичної гри з природою. Розроблено метод адаптивного вибору варіантів рішень на основі заохочувального навчання та застосування розподілу Больцмана. Розроблено алгоритмічне та програмне забезпечення системи прийняття рішень у грі з природою. Отримано та проаналізовано результати комп’ютерного моделювання стохастичного вибору варіантів рішень.
Game model of decision-making in hierarchical systems functioning in the conditions of aprioristic uncertainty it is constructed. The adaptive recurrent method and algorithm of stochastic game solving are developed. Computer modelling of stochastic game of decision-making in hierarchical system with structure of a binary tree is executed. Influence of parameters on convergence of a game method is investigated.
In the Paper modern approaches to mathematical modeling of retail crediting process have been considered. The necessity to construct specialized decision support systems on the basis of system analysis principles in crediting potential clients was recognized. Advantages of such systems are possibilities to implement effective preliminary data processing, use several alternative methods to estimate clients’ status and set of quality criteria on each stage of data analysis.
This article describes an object-oriented approach of DSS modeling. Three-level architecture is suggested and it describes a conceptual model of DSS. The analysis of possible reusable components for various types of structures is analyzed. We describe the principles of building a custom DSS use of multiple components.
This article is devoted the features of quality evaluation of medical decision making. The developed method, which takes into account the requirements of the standard ISO, and helps improve the quality of medical decisions when choosing a treatment strategy by determining the change in value of integrated test of the patient.
This article describes the steps to clear data in the DSS. The ontology concepts of clear data were proposed and described. The analysis of methods and data cleansing technology were carried out at every stage of the process, taking into account its features. Built The ontology of data cleaning techniques for methodological systematization of functional elements in the implementation model of DSS was built.