IMPORT PRICE ANOMALY DETECTION AUTOMATIC DATA PROCESSING MACHINES: A PUBLIC DATA-BASED MACHINE LEARNING STRATEGY
DOI:
https://doi.org/10.31092/jpbc.v10i1.3879Keywords:
Anomaly Detection, Fraud Triangle, Gradient Boosting, Isolation Forest, Machine Learning, Public DataAbstract
The practice of international trade price manipulation has come under scrutiny in Indonesia. However, the confidentiality of internal customs data hinders external researchers from detecting import price manipulation. This research offers novelty by developing a machine learning model prototype that exclusively utilizes public data from the Indonesian Central Bureau of Statistics. This research method applies a quantitative case study on the import of automatic data processing machines (HS Code 8471) from 2022 to 2025 by constructing a "Unit Value" (price/kg) proxy as a macro-risk indicator. The training data was labeled using Isolation Forest (contamination=5%) to train several classification models. The 20-fold stratified CV evaluation results showed Gradient Boosting as the best-performing model (F1-Score 0.904), with Country and HS Code as the strongest predictors. This model identified 51 anomalies (4.76%) in the 2025 data. A key finding was the detection asymmetry: a dominance of 26 cases of over-invoicing and only 2 cases of under-invoicing. This research contribution not only proved the feasibility of using public BPS data as an early warning system capable of detecting structural anomalies, but also confirmed the capability of machine learning in reducing information asymmetry and closing the "opportunity" gap within the Fraud Triangle Theory.
References
Abdullahi, R., & Mansor, N. (2015). Fraud Triangle Theory and Fraud Diamond Theory. Understanding the Convergent and Divergent For Future Research. International Journal of Academic Research in Accounting, Finance and Management Sciences, 5(4). https://doi.org/10.6007/IJARAFMS/v5-i4/1823
Abioye, O. A., Evwiekpaefe, A., Odion, P., & Awujoola, O. J. (2025). Improving Parkinson’s Diagnosis: A Stacked Ensemble Learning with Vocal Biomarkers and Data Balancing. Journal Research and Development (ITJRD), 10(1). https://doi.org/10.25299/itjrd.2025.22310
Adeline, M., Mutoharoh, L., Khaliza, R. N., Azis, M. N., & Triwardhani, D. (2024). Kajian tentang Dampak Penyelenggaraan G20 pada Pemulihan Perekonomian Indonesia Pasca Pandemi. Accounting Student Research Journal, 3(1), 72–84. https://doi.org/10.62108/asrj.v3i1.7615
Australian Government. (n.d.). Indonesia-Australia Comprehensive Economic Partnership Agreement. https://www.dfat.gov.au/trade/agreements/in-force/iacepa/indonesia-australia-comprehensive-economic-partnership-agreement
Badan Pusat Statistik. (2024). Nilai Impor Nonmigas Bulanan Menurut Negara Asal (Ribu US$), 2024. https://www.bps.go.id/id/statistics-table/2/MjM4OSMy/nilai-impor-nonmigas-bulanan-menurut-negara-asal--ribu-us--.html
Badan Pusat Statistik. (2025a). Data Ekspor Impor Nasional. https://www.bps.go.id/id/exim
Badan Pusat Statistik. (2025b, October). Berita Resmi Statistik: Perkembangan Ekspor dan Impor Indonesia Agustus 2025. https://www.bps.go.id/id/pressrelease/2025/10/01/2463/ekspor-dan-impor-indonesia-agustus-2025-masing-masing-tercatat-usd-24-96-miliar-dan-usd-19-47-miliar.html
Boateng, E. Y., & Abaye, D. A. (2019). A Review of the Logistic Regression Model with Emphasis on Medical Research. Journal of Data Analysis and Information Processing, 07(04), 190–207. https://doi.org/10.4236/jdaip.2019.74012
Brandt, K. (2023). Illicit financial flows and developing countries: A review of methods and evidence. Journal of Economic Surveys, 37(3), 789–820. https://doi.org/10.1111/joes.12518
Canrakerta, Nizar Hidayanto, A., & Ruldeviyani, Y. (2020). Application of Business Intelligence for Customs Declaration: A Case Study in Indonesia. Journal of Physics: Conference Series, 1444(1). https://doi.org/10.1088/1742-6596/1444/1/012028
Dangsawang, B., & Nuchitprasitchai, S. (2024). A machine learning approach for detecting customs fraud through unstructured data analysis in social media. Decision Analytics Journal, 10. https://doi.org/10.1016/j.dajour.2024.100408
DHL. (2025, August 4). Why Thailand’s computer part exports are surging and how your business can capitalize. https://www.dhl.com/discover/en-th/small-business-advice/business-innovation-trends/export-computer-parts-thailand
Farizi, W. S. Al, Hidayah, I., & Rizal, M. N. (2021). Isolation Forest Based Anomaly Detection: A Systematic Literature Review. 2021 8th International Conference on Information Technology, Computer and Electrical Engineering (ICITACEE), 118–122. https://doi.org/10.1109/ICITACEE53184.2021.9617498
Hanifah, A., Munawaroh, A., Husainah, N., Jamilah, S., Hartinah, S., Harun, S. H., & Annas, M. (2025). Pengantar Ilmu Statistik. Duta Sains Indonesia.
Laksmana, R. T. (2013). Under dan Over Invoicing: Permainan Jungkat Jungkit Nilai Pabean. Surabaya: Kantor Pengawasan dan Pelayanan Bea dan Cukai Tipe Madya Pabean Tanjung Perak.
Hardianto, H., Wahyuni, L., Rosnelly, R., Nasution, M. I. A., & Harahap, C. B. (2024). Computer Assembly Training at SMK Tritech Indonesia. Publikasi Pengabdian Masyarakat, 4(2), 173–185. https://doi.org/https://doi.org/10.22303/publidimas.4.2.2024.173-185
Lobb, J. (2025, July 3). Powering Australia’s data centre boom: Navigating energy compliance and opportunity. Dentons. https://www.dentons.com/en/insights/articles/2025/july/3/powering-australias-data-centre-boom
Mulyana, I., & Ulum, M. B. (2025). Application of Machine Learning Models for Fraud Detection in Synthetic Mobile Financial Transactions. JITK (Jurnal Ilmu Pengetahuan Dan Teknologi Komputer), 10(4), 759–769. https://doi.org/10.33480/jitk.v10i4.6420
Ngui, Y. (2025, September 17). Indonesia sovereign wealth fund INA targets data centres, AI in healthcare, renewables. Reuters. https://www.reuters.com/sustainability/climate-energy/indonesia-sovereign-wealth-fund-ina-targets-data-centres-ai-healthcare-2025-09-17/
Novith, D. C., Sembiring, A. R., & Ridho, M. H. (2023). Customs Fraud Detection Using Extremely Boosted Neural Network (XBNet). Jurnal BPPK: Badan Pendidikan Dan Pelatihan Keuangan, 16(1), 67–77. https://doi.org/10.48108/jurnalbppk.v16i1.816
Nugraheny, D. E., & Arief, T. M. V. (2025, October 22). Menkeu Purbaya Sebut 3 Bulan Lagi Bea Cukai Punya AI untuk Deteksi Under Invoicing. Kompas.Com. https://money.kompas.com/read/2025/10/22/124436226/menkeu-purbaya-sebut-3-bulan-lagi-bea-cukai-punya-ai-untuk-deteksi-under
Prastuti, G., Permatasari, I., -, L., Satmoko, Ag. S. A., & Imran, A. (2023). Detecting Cross-Border Transaction Patterns Using Machine Learning: The Case of Indonesia. Jurnal BPPK: Badan Pendidikan Dan Pelatihan Keuangan, 16(1), 132–145. https://doi.org/10.48108/jurnalbppk.v16i1.822
Rasheed, F., Said, J., & Ismail Khan, N. (2023). Evolution of Fraud-Related Theories: A Theoretical Review. Journal of Nusantara Studies (JONUS), 8(3), 322–350. https://doi.org/10.24200/jonus.vol8iss3pp322-350
Rusydi, M. K., Irianto, G., & Achsin, M. (2023). Value Chains and Illicit Financial Flows From Trade Misinvoicing: Indonesia-Singapore. Jurnal Aplikasi Manajemen, 21(2), 478–489. https://doi.org/10.21776/ub.jam.2023.021.02.16
Sa’adah, S. A., & Hartanto, A. (2023). Fraud Detection Using Data Analytics: A Case Study of Under Invoicing Importation Fraud in Indonesia. Jurnal BPPK: Badan Pendidikan Dan Pelatihan Keuangan, 16(1), 146–153. https://doi.org/10.48108/jurnalbppk.v16i1.823
Sánchez-Aguayo, M., Urquiza-Aguiar, L., & Estrada-Jiménez, J. (2021). Fraud Detection Using the Fraud Triangle Theory and Data Mining Techniques: A Literature Review. Computers, 10(10), 121. https://doi.org/10.3390/computers10100121
Seck, D. A. N. (2024). Building Machine Learning Models for Fraud Detection in Customs Declarations in Senegal. WSEAS Transactions on Information Science and Applications, 21, 208–215. https://doi.org/10.37394/23209.2024.21.20
Xu, H., Pang, G., Wang, Y., & Wang, Y. (2023). Deep Isolation Forest for Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12591–12604. https://doi.org/10.1109/TKDE.2023.3270293
Zulfikar, A., Rahmani, F. A., & Azizah, N. (2023). Deteksi Anomali Menggunakan Isolation Forest Belanja Barang Persediaan Konsumsi Pada Satuan Kerja Kepolisian Republik Indonesia. Jurnal Manajemen Perbendaharaan, 4(1), 1–15. https://doi.org/10.33105/jmp.v4i1.435
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.
