A Combined Approach for Predicting Employees’ Productivity based on Ensemble Machine Learning Methods
Ruba Obiedat, Sara Amjad Toubasi
Abstract
Garment industrial sector is one of the most important business sectors in the world. It presents the lifeblood for many countries’ economy. The demanding of garment merchandise in accretion year over year. There are many key factors affecting the performance of this sector including the employee productivity. This research proposes a hybrid approach which aims to predict the productivity performance of garment employees by combining different classification algorithms such as J48, random forest (RF), Radial Base Function network (RBF), Multilayer Perceptron (MLP), Naïve bayes (NB), and Support vector machine (SVM) with ensemble learning algorithms (Adaboost and bagging) on garment employee productivity dataset. This work monitors three major evaluation metrics including, accuracy, Mean Absolute Error value (MAE) and Root Mean Square Error (RMSE). The results show that RF outperforms the other algorithms with accuracy of 0.983 and MAE of 0097. In addition, the results prove that applying Adaboost ensemble algorithm with J48 enhances the classification performance with accuracy of 0.991 and MAE of 0.0101.