Implementation of Data Mining on Tourist Visits Patterns on Lombok Island Tourism Objects

Abstract

Foreign tourists entering Indonesia in 2017 and 2018 have increased. From the data obtained on the website of the Ministry of Tourism (Kemenpar) the number of foreign tourists in 2017 was 14,039,799, while in 2018 there were 15,806.1, with a comparison of the number of tourists from the two years, the percentage increase in tourists was 12.58%. The data analysis approach using a classification model is a data analysis approach by studying the data and making predictions with the new data. in the classification model, there are many algorithms that can be applied in data analysis, one of which is the Decision Tree algorithm. This study aims to analyze the pattern of tourist visits based on the objects visited by the number of tourists visiting certain tourist objects. From the modeling using the Decesion Tree C4.5 Algorithm and the scenario of splitting the data into three parts, the highest accuracy value was obtained for splitting data of 80:20 for train and testing data and max depth 7, which obtained an accuracy of 94% for train data and 92% for data. testing. Modeling with the Boostrap Aggregating Method, the accuracy score obtained on training data is 93% and testing data is 92. percent. 3 accuracy results from using bagging reduce the accuracy of the C4.5 algorithm on the data training side from 94% to 93 percent, while the accuracy of testing data is still the same, namely 92%.