Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations
A holistic occupational and economy-wide framework for salary prediction is developed and tested using statistical machine learning (ML). Predictive models are developed based on occupational features and organizational characteristics. Five different supervised ML algorithms are trained using surve...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/13/10/495 |
| _version_ | 1797431539735199744 |
|---|---|
| author | Yasser T. Matbouli Suliman M. Alghamdi |
| author_facet | Yasser T. Matbouli Suliman M. Alghamdi |
| author_sort | Yasser T. Matbouli |
| collection | DOAJ |
| description | A holistic occupational and economy-wide framework for salary prediction is developed and tested using statistical machine learning (ML). Predictive models are developed based on occupational features and organizational characteristics. Five different supervised ML algorithms are trained using survey data from the Saudi Arabian labor market to estimate mean annual salary across economic activities and major occupational groups. In predicting the mean salary over economic activities, the Bayesian Gaussian process regression ML showed a marked improvement in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> over multiple linear regression (from 0.50 to 0.98). Moreover, lower error levels were obtained: root-mean-square error was reduced by 80% and mean absolute error was reduced by almost 90% compared to multiple linear regression. However, the salary prediction over major occupational groups resulted in artificial neural networks performing the best in terms of both <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>, with an improvement from 0.62 in multiple linear regression to 0.94 and errors were reduced by approximately 60%. The proposed framework can help estimate annual salary levels across different types of economic activities and organization sizes, as well as different occupations. |
| first_indexed | 2024-03-09T09:45:31Z |
| format | Article |
| id | doaj.art-26ca22e9b8504221bc2a92a8b99cdaf5 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T09:45:31Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-26ca22e9b8504221bc2a92a8b99cdaf52023-12-02T00:33:06ZengMDPI AGInformation2078-24892022-10-01131049510.3390/info13100495Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and OccupationsYasser T. Matbouli0Suliman M. Alghamdi1Department of Industrial Engineering, Faculty of Engineering-Rabigh Branch, King Abdulaziz University, Jeddah 21589, Saudi ArabiaAdvanced Resources for Information Technology Co., Riyadh 13524, Saudi ArabiaA holistic occupational and economy-wide framework for salary prediction is developed and tested using statistical machine learning (ML). Predictive models are developed based on occupational features and organizational characteristics. Five different supervised ML algorithms are trained using survey data from the Saudi Arabian labor market to estimate mean annual salary across economic activities and major occupational groups. In predicting the mean salary over economic activities, the Bayesian Gaussian process regression ML showed a marked improvement in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> over multiple linear regression (from 0.50 to 0.98). Moreover, lower error levels were obtained: root-mean-square error was reduced by 80% and mean absolute error was reduced by almost 90% compared to multiple linear regression. However, the salary prediction over major occupational groups resulted in artificial neural networks performing the best in terms of both <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>, with an improvement from 0.62 in multiple linear regression to 0.94 and errors were reduced by approximately 60%. The proposed framework can help estimate annual salary levels across different types of economic activities and organization sizes, as well as different occupations.https://www.mdpi.com/2078-2489/13/10/495machine learning regressionsalary predictiongaussian process regressionartificial neural networkseconomic activitiesoccupational groups |
| spellingShingle | Yasser T. Matbouli Suliman M. Alghamdi Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations Information machine learning regression salary prediction gaussian process regression artificial neural networks economic activities occupational groups |
| title | Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations |
| title_full | Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations |
| title_fullStr | Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations |
| title_full_unstemmed | Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations |
| title_short | Statistical Machine Learning Regression Models for Salary Prediction Featuring Economy Wide Activities and Occupations |
| title_sort | statistical machine learning regression models for salary prediction featuring economy wide activities and occupations |
| topic | machine learning regression salary prediction gaussian process regression artificial neural networks economic activities occupational groups |
| url | https://www.mdpi.com/2078-2489/13/10/495 |
| work_keys_str_mv | AT yassertmatbouli statisticalmachinelearningregressionmodelsforsalarypredictionfeaturingeconomywideactivitiesandoccupations AT sulimanmalghamdi statisticalmachinelearningregressionmodelsforsalarypredictionfeaturingeconomywideactivitiesandoccupations |