Fuzzy cognitive map and mean square method in empirical modeling: Application in economics

Abstract

This article offers a Fuzzy Cognitive Map (FCM) - based method of empirical modeling which can be considered as an alternative to multivariate regression analysis for the input–output relationship extraction from experimental data. Vertices of the FCM graph are interpreted as input–output variables of the empirical model, and the weights of arcs are unknown parameters that are estimated in two stages. The first stage consists of the arcs weights estimating based on the proximity of the columns’ values in the input–output observation data table. At the second stage, the observation table is used for the offline weights adjustment using the least squares method and the optimization procedure by genetic algorithm. The method is illustrated by the example of the World Bank data testing the relations between Gross Domestic Product per Capita vs demographic, educational, economic, technological and other factors. The novelty of the method in comparison to the Soft Regression technique lies in the utilization of the FCM arcs weights adjustment according to the least squares criterion.