An intelligent hybrid deep belief network model for predicting students employability

In recent times, the question of employability has become a critical concern not only for degree holders but for educational organizations. Hence, employability prediction models play an important role in analyzing the student’s capability to get employment. In this paper, a hybrid model of deep belief network and soft max regression (DBN-SR) is proposed for student employability prediction. Initially, pre-processing is performed on student’s data for removing irrelevant attributes to achieve data consistency. Further, to enhance the accuracy of the prediction model, the crow search algorithm-based feature selection model is employed to select the optimal subset of features from original features. Then, the selected subset of features is taken as the input of the deep belief network (DBN) for intrinsic feature learning to obtain high-level feature representation. Finally, the soft max regression (SR) is used to predict the class of students as employed or unemployed. The proposed employability prediction model achieves above 98% of accuracy which is comparatively 2.5%, 5% higher than the deep autoencoder and deep neural network-based models. The performance outcomes proved that the proposed DBN-SR model has been well suitable for predicting student’s employability.