Exploring the facets of overall job satisfaction through a novel ensemble learning


Abstract


The aim of this work is to understand the relationship between the overall job satisfaction and the facet job satisfaction, using a comprehensive Italian social cooperatives workers dataset. On this issue, recent works have explored how ensemble learning like Random Forest and TreeBoost can be used to assess the importance of potential predictors in the job satisfaction. Taking a similar way, in this study we use a tailored data mining approach for hierarchical data, namely a new algorithm called CRAGGING, shedding some light about the drivers of Job Satisfaction. To do this we use the variable importance measure designed for the CRAGGING and then we grow a synthetic model to relate the overall job satisfaction with corresponding facets, providing sufficient evidence about good accuracy and less complexity of the model leading to simple and direct interpretation.

DOI Code: 10.1285/i20705948v4n1p23

Keywords: CRAGGING; ensemble learning; final model; hierarchical data; job satisfaction; variable importance

References


[1]. Aldag, R.J., Brief, A.P. (1978). Examination of alternative models of job satisfaction. Human Relations, 31, 1, 91-98.


Full Text: PDF
کاغذ a4

Creative Commons License
This work is licensed under a Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia License.