메인메뉴 바로가기
본문으로 바로가기
Korea Customs Service
HOME
SITEMAP
KOREAN
MOBILE MENU
About us
Vision
Greetings from Commissioner
History
2000 - Present
1970 - 2000
Organization Chart
Location
Links
News
News
Video Gallery
Individuals
Travelers
Customs Clearance Guide for Passengers
On-arrival Duty Free Shops
Traveler Declaration Form
Tax Refund
Internet purchases
Customs Clearance Procedures for Overseas Purchases
Customs Duty Refund for Overseas Purchases
Parcel Tracking
Issuance of personal customs clearance code
Clearance procedures for express cargo
Clearance procedures for postal items
Declaration of Foreign Currency
Moving to Korea
Businesses
Export-Import Clearance
Import Declaration Guideline
Export Declaration Guideline
Price Report on Imported Goods
Tax payment report and making payment
Customs duty exemption and ex post facto management of exempted articles
Intellectual property rights protection
Retention of reported and submitted documents
FTA
Free Trade Agreement(FTA)
Certificate of Origin
Approved Exporter
Certificate of Non-Manipulation
Certificate of Non-Manipulation
Search of the Certificate of Non-Manipulation
FAQ & Notice
Supporting Businesses
Bonded Factory Regime
Installment Payment of Customs Duty
Deferred Payment of VAT on Imported Goods
SME Business Support Program
Addressing the Customs Clearance Issues
Postponing Customs Investigations
Taxpayer Support Programs
Revision Scheme of Tax Paid
AEO program
Self-Regulating Examination and Settlement of the Amount of Import Duty
Tax Payment Guidance
Checking Faithful Tax Report
Customs duty investigation
Comprehensive Audit
Marking of origin
Examination of origin
NonFulfillment of Faithful Report
Error in the content of report
false declaration/ reporting
Restriction of issue of corrected import tax invoice
Protecting Duty Payer's Rights
Protecting duty payer's rights at the time of customs duty investigation
Protecting duty payer's rights at the time of FTA origin verification
Information on the remedy for duty payer's rights
Request for pre-taxation review
Information on the procedures for ex post remedies
General counseling on customs duty
KCS Tariff D/B(Inquiry)
Trade Statistics
What is the trade statistics?
Laws & Regulations
Customs Exchange Rate
Other Information
International organizations and the KCS activities
World Trade Organization (WTO)
World Customs Organization (WCO)
Asia Pacific Economic Cooperation (APEC)
Association of Southeast Asian Nations (ASEAN)
Asia-Europe Meeting (ASEM)
International conventions related to the customs administration
About UNI-PASS
Overview
Key Modules
Development process and support services
Around the World
ODA Customs Modernization Consulting Project
Industry 4.0 : Customs Innovation
Q&A / FAQ
Q&A
Smuggling Report
Usage Information
Smuggling Report
Smuggling List
FAQ
FTA
Import(Personal)
Tariff Classification
Import(Business)
News
HOME
News
News
인쇄
공유
URL공유
페이스북
트위터
카카오스토리
WCO BACUDA Project Team develops a neural network model to assist Customs to detect potential fraudulent transactions
WCO BACUDA Project Team develops a neural network model to assist Customs to detect potential fraudulent transactions 상세보기 표 - 로 구성
Poster
KCS
Date
2020.09.28
As part of WCO BACUDA Project, sponsored by Customs Cooperation Fund-Korea (CCF-K), BACUDA experts have developed a Dual-Attentive-Tree-aware-Embedded (DATE) neural network model with the Institute of Basic Science (IBS) and the National Cheng Kung University (NCKU) to assist Customs administration to better detect transactions presenting risks of fraud. The DATE model has been accepted by ACM SIGKDD 2020 (International Conference on Knowledge Discovery and Data Mining) and will be published in the ACM SIGKDD 2020 proceedings as a full paper.
The WCO BACUDA project was launched in September 2019 as a collaborative research platform focused on data analytics. With the participation of Nigeria Customs Service (NCS), BACUDA experts successfully developed the DATE model, and have been implementing a pilot test to verify its performance with real-time import data of the two Nigerian ports in Tin Can (in Lagos) and Onne (in Port-Harcourt) since March 2020.
The model employed a cutting-edge Artificial Intelligence (AI) mechanism called “ATTENTION” that is used as a language translation tool and for self-driving cars. Thanks to this innovative technology, the model has outperformed other traditional machine learning models (such as XGBoost) in detecting potential fraudulent transactions. The model noticeably outperforms even with relatively small-sized training data (from countries with low trade volumes) and low inspection rates (from countries with huge trade volumes).
File
BACUDA DATE Project.jpg [
203222
]
(Download : 691Number)
List
이전 다음 글보기
Next
Korea Customs Service conducts a Training Session on Customs Modernization for Customs Officials from Belarus
Prev
The 16th Korea-ASEAN Customs Consultation