PENGGUNAAN DATA MINING DALAM EKSTENSIFIKASI PENELITIAN ULANG
DOI:
https://doi.org/10.31092/jpbc.v5i2.1305Abstract
ABSTRACT
Due to increasing volume of international trade, effect on increasing customs document, Customs play a role so that trade flows run without obstacles, this causes inspection of imported goods to be less than optimal, but on the other hand Customs are required to collect state revenues optimally. This study tries to solve this problem from the post-clearance control side with re-examination by construct an analytical data model to predict the suitable classification. This study uses data on the Notification of Imported Goods during 2020 at the Regional Office of DJBC XXX which using a sample of goods that has similarities but has the potential to be misclassified. This study uses the Cross-industry Standard Process for Data Mining (CRISP-DM) model and the Rapid Miner Studio 9.9.2 application. Based on the model formed, the prediction results obtained according to the appropriate classification according to data mining. It also found the factors that most impact to goods classification, the most impact is the Importer status, whereas the least impact is the goods lane.
ABSTRAK:
Â
Seiring dengan volume perdagangan internasional yang semakin tinggi, jumlah dokumen kepabeanan yang harus diperiksa juga mengalami peningkatan. Hal ini menghambat peran Bea dan Cukai sebagai fasilitator perdagangan yang menyebabkan pemeriksaan barang impor kurang optimal. Di sisi lain, Bea dan Cukai dituntut untuk menghimpun penerimaan negara secara optimum. Penelitian ini mencoba untuk menyelesaikan permasalahan tersebut pada tahap post clearance dengan penelitian ulang, yaitu dengan membangun model data analitik untuk memprediksi klasifikasi barang yang diberitahukan oleh importir sudah sesuai atau belum. Penelitian ini menggunakan data Pemberitahuan Impor Barang selama tahun 2020 pada Kanwil DJBC XXX yang sampel data barangnya memiliki kemiripan tetapi berpotensi salah klasifikasi. Penelitian ini menggunakan model Cross-industry Standard Process for Data Mining (CRISP-DM) dan aplikasi Rapid Miner Studio 9.9.2. Berdasarkan permodelan yang dibentuk, didapatkan hasil prediksi klasifikasi yang sesuai menurut data mining. Didapat pula faktor yang paling memengaruhi kebenaran pemberitahuan klasifikasi barang impor, yaitu status importir, sedangkan yang paling tidak berpengaruh adalah jalur pengeluaran barang impor.
Kata Kunci: Penelitian Ulang, Data Analitik, Penerimaan Negara, Klasifikasi Barang
Â
References
Canrakerta, Achmad N. Z., Yova R., Application of Business Intelligence for Customs Declaration: A Case Study in Indonesia. Jurnal of Physics: Conference Series.
Chapman & Pete. 2000. CRISP-DM v.1.0 Step by Step Data Mining Guide. SPSS Inc.
Direktorat Jenderal Bea dan Cukai (2017). Peraturan Direktur Jenderal Bea dan Cukai Nomor PER-8/BC/2017 tentang Petunjuk Pelaksanaan Penelitian Ulang sebagaimana diubah dengan Peraturan Direktur Jenderal Bea dan Cukai Nomor PER-25/BC/2019. Jakarta: Direktorat Audit Kepabeanan dan Cukai.
Kementerian Keuangan (2017). Buku Tarif Kepabeanan Indonesia Tahun 2017. Jakarta: Direktorat Jenderal Bea dan Cukai.
Pemerintah Republik Indonesia. (2006). Undang-Undang Republik Indonesia Nomor 10 Tahun 1995 Tentang Kepabeanan sebagaimana diubah dengan Undang-Undang Nomor 17 Tahun 2006. Jakarta: Kementerian Hukum dan HAM.
Sri L., Herta A. S., Implementasi Data Mining Dalam Penerbitan Surat Penetapan Tarif dan Nilai Pabean Menggunakan Metode Classification Pada Direktorat Jenderal Bea dan Cukai. CKI On Spot Vol. 11
Turban & E. 2005. Decision Support Systems and Intelligent Systems. Yogyakarta: Andi Offset.
World Customs Organization (2019). Risk Management Compendium Volume 1. Brussel: World Customs Organization.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.