Support Vector Machine Predictive Analysis Implementation: Case Study of Tax Revenue in Government of South Lampung

Abstract

Tax is potential revenue that is used by the government as a source of funding to run the government. One of the conditions needed to implement decentralization is the availability of sources of local revenue. Some local revenue sources are hotel and restaurant taxes. Issues raised in this research are that the number of hotel and restaurant visitors changes every year, resulting in fluctuations in the amount of tax. On the other hand, the Government of South Lampung had difficulty in predicting the target of hotel and restaurant tax revenue when arranging a revenue budget. This is due to the absence of formula to calculate the potential tax revenue accurately, resulting in a lack of strategic management for local revenue improvement. Now, Business Intelligence is becoming a trend. Many sectors use Business Intelligence to analyze and prepare new strategies and improve performance. Thus, it is necessary to use Business Intelligence to predict the potential of hotel and restaurant tax revenue so that the Government of South Lampung can develop appropriate strategies to improve local tax revenue and minimize tax reduction. The method used is a predictive analysis using the Support Vector Machine (SVM).  The result of this study is expected to be taken into consideration for South Lampung Local Government Revenue Service, in particular for the determination of the target of the hotel and restaurant tax sector in the coming year.