Scenario Forecasting of University Development Based on a Combined Cognitive Model

Abstract

AbstractA new approach to solving the problem of predicting the performance of a university as a weakly structured system based on an aggregated model, including an ensemble of gray fuzzy cognitive maps (FCM), is proposed. A combination of cognitive modeling, interval mathematics, and causal algebra was used to construct the gray FCM. Aggregation of gray FCM models gives a synergistic effect, in which the disadvantages of some models are compensated by the advantages of other models. The use of the interval approach in describing the relationships between the concepts made it possible to reduce the uncertainty of expert assessments of the strength of the relationship between the concepts of the cognitive map, as well as to increase the efficiency of the forecasting process. The model based on the ensemble of gray FCMs provided an increase in the reliability of the solution using several options for formalizing the knowledge and experience of experts. The novelty of the approach is determined by the use in the construction of a fuzzy cognitive map of special constructions in the form of interval estimates to assess the strength of connections between concepts, providing an adequate cognitive model, as well as the use of a predictive ensemble of gray FCMs, based on which a more accurate result was obtained in comparison with a single FCM and existing ones. Models of classic FCM. The proposed approach provided, under the given constraints, obtaining the most acceptable scenario for planning the increment of the basic indicators of the university's activity to target values by identifying the latent factors affecting them and calculating the aggregate of impulse influences on latent factors to ensure the achievement of the goal.KeywordsScenario predictionGray fuzzy cognitive mapInterval fuzzy set