Decission support system for candidates classification in the employment process based on ANFIS method

Abstract

The aim of this work is to create a decision support system based on Adaptive Neuro-Fuzzy Inference System (ANFIS), which will be used for objective classification of employees in the employment process by analyzing available information about the candidates. Information about the candidates is extracted from the relevant documents on one company during the advertising for job in Information Technology (IT) sector. Filtration and normalization of the data were performed after they had been acquired, the decision support system being realized was implemented in the form of hybrid model, made of fuzzy logic synthesis and neural network, as well as presented by acronym ANFIS. The initial ANFIS system is divided into two subsystems as the result of complexity of the very problem, as well as of more attributes. By training and testing (checking) the obtained Fuzzy Inference System (FIS) structures, the one with the lowest error is chosen. The operation of the network has been demonstrated by the valuable simulation model. The successful validation of the resulting system has been made by validation data.