Prediction of Work From Home Post COVID-19 using Classification Model

This study aims to predict the continuance of the adoption of WFH after COVID-19 and other factors that also influence these preferences. This study was conducted using data mining techniques with the CRISP-DM framework based on the Decision Tree, Naïve Bayes, and Random Forest Algorithms. The dataset was taken based on a questionnaire survey distributed online via Google Forms with a target of 200 respondents and returned from 183 respondents from four divisions. The results of this study indicate the Decision Tree model has the best performance with an accuracy of 85.45%. Based on the prediction and questionnaire results, employees tend to agree to continue implementing WFH after COVID-19 with a Hybrid working model. These preferences influence work improvement, employee performance, and work environment.