Predicting The Number of Tourists Based on Backpropagation Algorithm

Predicting The Number of Tourists Based on Backpropagation Algorithm

Artificial Neural Networks, BackpropagationAlgorithm, Prediction, Tourist

The number of tourists always fluctuates every month, as happened in Kaliadem Merapi, Sleman. The purpose of this research is to develop a prediction system for the number of tourists based on artificial neural networks. This study uses an artificial neural network for data processing methods with the backpropagation algorithm. This study carried out two processes, namely the training process and the testing process with stages consisting of: (1) Collecting input and target data, (2) Normalizinginput and target data, (3) Creating artificial neural network architecture by utilizing GUI (Graphical UserInterface)Matlabfacilities. (4) Conducting training and testing processes, (5) Normalizing predictive data, (6) Analysis of predictive data. In the data analysis, the MSE (Mean Squared Error) value in the training process is 0.0091528 and in the testingprocess is0.0051424. Besides, the validity value of predictive accuracy in the testing process is around 91.32%. The resulting MSE (Mean Squared Error) value is relatively small,and the validity value of prediction accuracy is relatively high, so this system can be used to predict the number of tourists in Kaliadem Merapi, Sleman

Dwi Marlina1, Fatchul Arifin2

https://jurnal.iaii.or.id/index.php/RESTI/issue/view/23

Yogyakarta State University

20 juni 2021

Fajar bagus W

PDF

Indonesia

Text