Handy Darmawan, Cherise Earlene, Eric, Budi Juarto, F. Kurniadi
{"title":"Comparison Several Regression Algorithms for Prediction of Job Satisfaction","authors":"Handy Darmawan, Cherise Earlene, Eric, Budi Juarto, F. Kurniadi","doi":"10.1109/ICISS55894.2022.9915194","DOIUrl":null,"url":null,"abstract":"Job satisfaction is the attitude or feelings of employees towards the pleasant or unpleasant aspects of work that in accordance with the assessment of each employee. There are several factors that affect job satisfaction, such as work environment satisfaction and employees' welfare. With obtained datasets, ‘welfare satisfaction’ and ‘environment satisfaction’ were used as independent variables with project numbers as dependent variables to examine an algorithm indicating the highest accuracy with the lowest RMSE and MAE values and the highest R-Squared values out of four algorithms, namely Linear Regression, Support Vector Regression, AdaBoost Regression, and Random Forest Regression. The results suggested that Random Forest Regression was the most accurate algorithm with MAE and RMSE values of 0.097000 and 0.185068, respectively, and R-Squared values of 0.981878.","PeriodicalId":125054,"journal":{"name":"2022 International Conference on ICT for Smart Society (ICISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on ICT for Smart Society (ICISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICISS55894.2022.9915194","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Job satisfaction is the attitude or feelings of employees towards the pleasant or unpleasant aspects of work that in accordance with the assessment of each employee. There are several factors that affect job satisfaction, such as work environment satisfaction and employees' welfare. With obtained datasets, ‘welfare satisfaction’ and ‘environment satisfaction’ were used as independent variables with project numbers as dependent variables to examine an algorithm indicating the highest accuracy with the lowest RMSE and MAE values and the highest R-Squared values out of four algorithms, namely Linear Regression, Support Vector Regression, AdaBoost Regression, and Random Forest Regression. The results suggested that Random Forest Regression was the most accurate algorithm with MAE and RMSE values of 0.097000 and 0.185068, respectively, and R-Squared values of 0.981878.