Modeling of time series data for forecasting the number of foreign tourists in east Kalimantan using fuzzy inference system based on ARX model

Abstract

The government agencies require accurate tourism demand forecasts to plan the required tourism infrastructure, such as accommodation location planning and transportation development. Tourism demand forecasts can be viewed from various factors, one of which is the number of tourists per period. Without ignoring the number of domestic tourists, the increasing number of foreign tourists is prioritized by the government to increase the country's foreign exchange. Usually, a tourist destination is to visit some tour objects and need some accommodation and hotel sites to rest. With this consideration, the forecasting number of foreign tourists can be done by using data on the number of tour objects, accommodation and hotel sites, foreign and domestic tourists from the previous period. Data on the number of domestic tourists used to measure the tendency of foreign tourists compared with domestic tourists to all existing tour objects. All data history can be viewed as time series data. Conventionally, many researchers have employed traditional methods of time series analysis, modeling, and forecasting such as ARX (Autoregressive with exogenous input) model. FIS (Fuzzy Inference System) is a system that processes the input mapping formulation provided to produce output using Fuzzy Logic. The aim of this study is to forecast the number of foreign tourists by using FIS through a training process conducted by adapting the number of linguistic variables. All the training data are modeled by using the ARX model.