Modeling of The Number of Tourists with Autoregressive Integrated Moving Average and Recurrent Artificial Neural Network

Pemodelan Jumlah Wisatawan dengan Autoregressive Integrated Moving Average dan Recurrent Artificial Neural Network

Abstract

Tourism has become a priority area for Indonesia's economic development. Tourism is expected to be one of the main drivers of Indonesia's economic growth through job and business creation, foreign currency earnings and infrastructure development. In addition, tourism can be used to introduce the identity and culture of the community. Therefore, tourism development will continue and increase through the expansion and utilization of national tourism resources and possibilities. In this study, the number of foreign tourist arrivals will be predicted using the ARIMA model and the Elman-RNN model, given that the pattern of tourist arrivals is not always linear. The data used is the data from the survey results of the Central Statistics Agency. The data is divided into two parts, namely in-sample data and out-sample data. Of the two models, the model of the Elman-RNN network is the best model with the smallest MAPE and RSME values.