Estimating Successful Internal Mobility: A Comparison Between Structural Equation Models and Machine Learning Algorithms

• DOI: 10.3389/frai.2022.848015
• Publication Date: 2022-03-29T18:56:44Z
• Authors: Francesco Bossi; Francesco Di Grut...; Antonio Mastrogio...; Sonia D'Arcangelo; Nicola Lattanzi; Andrea P. Malizia; Emiliano Ricciardi
• Keywords: Internal model

Internal mobility often depends on predicting future job satisfaction, for such employees subject to internal programs. In this study, we compared the predictive power of different classes models, i.e., (i) traditional Structural Equation Modeling (SEM), with two families Machine Learning algorithms: (ii) regressors, specifically least absolute shrinkage and selection operator (Lasso) feature (iii) classifiers, Bagging meta-model k -nearest neighbors algorithm ( -NN) as a base estimator. Our aim is investigate which method better predicts satisfaction 348 (with operational duties) 35 supervisors in training set, 79 test all programs large Italian banking group. Results showed average SEM -NN (accuracy between 61 66%; F1 scores 0.51 0.73). Both Lasso algorithms highlighted resistance change orientation relation together other personality motivation variables models. Theoretical implications are discussed using these successful relocation Moreover, results how crucial it compare methods coming from research traditions Human Resources analytics.