Expert System for Employee Performance Evaluation Based on HR Analytics Data Using the Certainty Factor Method

Abstract

Employee performance evaluation is one of the important things in human resource management because it can affect the Company's productivity and development. However, the performance appraisal process that is still carried out manually or conventionally often results in subjective and inconsistent appraisals. This makes the results of the evaluation sometimes less effective to be used as a basis for decision-making. This study aims to design an expert system using the Certainty Factor (CF) method to help the process of evaluating employee performance automatically and more objectively by utilizing HR Analytics data. The data used amounted to 791 employees consisting of age, work experience, education level, department, performance score, and performance category. The expert system created has eleven inference rules with five assessment categories, namely Poor, Average, Good, Very Good, and Special. The rules are prepared based on the results of consultation with experienced HR practitioners. The Certainty Factor method is used to determine the level of confidence of the system in classifying employee performance in conditions that have an element of uncertainty. The results showed that the system could produce a combined CF value between 0.46 and 0.84 on several employee profiles. In addition, the system also obtained an accuracy level of 82% in accordance with expert research. Based on these results, the Certainty Factor-based expert system can be used as a decision support in a more structured and data-based employee performance evaluation process.