Open AccessComparison Between Conventional Methods, Neural Network, and Support Vector Regression in Forecasting Foreign Tourists in Indonesia
Author(s) -
Purwati Purwati,
Donny Montreano,
Alina Cynthia Dewi
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1125/1/012056
Subject(s) - backpropagation , artificial neural network , support vector machine , computer science , tourism , regression , promotion (chess) , value (mathematics) , regression analysis , data mining , artificial intelligence , machine learning , statistics , mathematics , geography , archaeology , politics , political science , law
Tourism is one of the important sectors in the growth of Indonesia’s economy. To be able to achieve the target and increase foreign tourist visits to Indonesia it is necessary to plan appropriate promotion and sustainable development that must be in line with the development of foreign tourists to be in target, effective and efficient. In this study forecasting to the level of foreign tourists visiting Indonesia in order to obtain accurate data. Forecasting is done by comparing 3 forecast methods, viz. traditional method, Support Vector Regression (SVR), and Backpropagation Neural Network (BPNN) method. In this research, there are 36 monthly visit data from 2017 to 2020 that are used to forecast. The result of this research indicates that the best forecasting is done by the Support Vector Regression (SVR) method with a MAPE value is 2.5614 % whereas, Backpropagation Neural Network (BPNN) has a MAPE value 31.3777%.