Neuro-Fuzzy Employee Ranking System in the Public Sector

Abstract

One of the biggest problems the public sector faces is the proper utilization of human resources. Within a particular combination of practices, dynamic resource allocation management aims to increase employee productivity. The question that arises is how to match the abilities of employees on a measurable scale through their connection with the logic of neuro-fuzzy systems. Productivity and efficiency are two sides of the same coin and are directly related to the deployment of tasks. In this context, the new era of digital transformation along with the automation of processes allows the direct measurement of the workload status at any time. After the deployment of numerous experiments we verify that skill management is linked to performance measurement. Hard skills are selected since there is no direction of how to quantify soft skills and especially when applied to employees of a public body. ANFIS neuro-fuzzy system was selected since it uses the learning algorithm derived from neural network theory along with human criteria. Therefore the proposed system is based on two distinct factors, Skill management and Neuro-Fuzzy Inference System. The model initialization is system-data driven, which enhances the accuracy compared to traditional HR systems and secures a non-subjective procedure on employee management applied to the public sector.