Development of methods for intelligent assessment of parameters in decision support systems

The object of the study is decision support systems. The subject of the study is the process of evaluating the parameters of decision support systems. The problem addressed in the study is improving the reliability of parameter evaluation in decision support systems while ensuring the required operational efficiency, regardless of the volume of incoming data. The originality of the proposed method lies in the application of additional advanced procedures, which enable the following: – verification of the topology and parameters of decision support systems, taking into account the degree of uncertainty in the initial data, achieved through the use of an improved penguin colony algorithm; – preliminary selection of individuals for configuring an evolving artificial neural network using an improved genetic algorithm, which reduces solution search time and increases the reliability of the obtained results; – adjustment of the weights of the evolving artificial neural network, leading to improved accuracy in parameter evaluation of decision support systems; – implementation of additional mechanisms for tuning the parameters of the evolving artificial neural network through modification of the membership function; – enhancement of the reliability of parameter evaluation in decision support systems via parallel assessment using multiple evaluation methods; – utilization of a hybrid evaluation of decision support system parameters, enabling correct operation in the absence of conditions such as stationarity, homogeneity, normality, and independence. An example of applying the proposed methodology to the evaluation of decision support system parameters has been conducted. The experiment demonstrated an increase in the reliability of parameter evaluation by 17–21% through the use of additional procedures, while maintaining the specified level of operational efficiency