Open AccessFACTORS AFFECTING THE CUSTOMS CLEARANCE TIME AT PRIME CUSTOMS OFFICE TYPE A OF TANJUNG PRIOK
Author(s) -
Khamami Herusantoso,
Ardyanto Dwi Saputra
Publication year - 2020
Publication title -
customs research and applications journal
Language(s) - English
Resource type - Journals
ISSN - 2715-338X
DOI - 10.31092/craj.v2i2.56
Subject(s) - c4.5 algorithm , business , pruning , process (computing) , computer science , decision tree , data mining , artificial intelligence , naive bayes classifier , support vector machine , agronomy , biology , operating system
In the dwell-time, the customs clearance is considered as the most complex phase, even though its portion is the shortest among other phases, such as pre-clearance and post clearance. In order to improve the efficiency and effectiveness on the services performed in the customs clearance process, the customs authorities must start considering the help of database analysis in identifying obstacles instead of depending on the personal analysis. Useful information is hidden among the importation data set and it is extractable through data mining techniques. This study explores the customs clearance process of import cargo whose document is declared through the red channel at Prime Customs Office Type A of Tanjung Priok (PCO Tanjung Priok), and applies a specific data mining classifier called the decision tree with J48 algorithm to evaluate the process. There are 11 classification models developed using unpruned, online pruning, and post-pruning features. One best model is chosen to extract the hidden knowledge that describes factors affecting the customs clearance process and allows the customs authorities to improve their services performed in the future.