THE ROLE OF CONVOLUTIONAL NEURAL NETWORK (CNN) AND RECURRENT NEURAL NETWORK (RNN) ON LEADERSHIP AND WORKFORCE AGILITY IN UMSU POSTGRADUATE PROGRAMS

Abstract

Convolutional Neural Network (CNN) is a development of Multilayer Perceptron (MLP) designed to process and classify data. Recurrent Neural Network (RNN) is an artificial neural network architecture known for its good performance as it processes input data sequentially. In a study conducted by Sugiharto et al., the Recurrent Neural Network method was found to have an accuracy rate of 65%, with an average macro precision of 0.59, an average macro recall of 0.62, and an average macro F1-score of 0.60. The weighted average precision was 0.67, the weighted average recall was 0.65, and the weighted average F1-score was 0.65. Both Convolutional Neural Network and Recurrent Neural Network can be used for research in organizational management, especially in the postgraduate program at Universitas Muhammadiyah Sumatera Utara. The development of artificial intelligence-based systems can also assist management in providing better services. This research describes the implementation of Convolutional Neural Network (CNN) with Recurrent Neural Network (RNN) to examine the roles of Leadership and Workforce Agility in organizational agility within the postgraduate program at UMSU. The analysis results draw conclusions regarding the best values for accuracy, precision, recall, and F-measure between the Convolutional Neural Network (CNN) and Recurrent Neural Network algorithms