Customer Success

Korea Customs Service improves illegal-cargo detection with SAS^®

The Korea Customs Service (KCS) is a government agency established to secure national revenues by controlling imports and exports for the economic development of South Korea and to protect domestic industry through contraband control. It is responsible for the customs clearance of imported goods as well as tax collection at the customs border.

But KCS' portfolio has expanded dramatically. The agency must now be concerned with areas such as social security, health care, environmental protection, and overall control of foreign transactions covering false indication of origin, infringement of intellectual property rights, illegal foreign exchange transactions and money laundering.

To keep up with these increasing demands, KCS uses SAS to implement advanced risk management with a high detection rate, improving the effective inspection of imported goods.

Difficulties in detecting illegal cargo
Over the last decade, Korea's imported goods more than doubled as the size of the KCS work force remained the same. This forced the agency to find a way to thoroughly detect illegal cargo with existing resources without a total inspection of imported goods. KCS tried to promote greater efficiency and the use of selective inspections, but the results fell short of expectations.

In the previous risk management system, the subjects of inspection were selected based on the importers, items or foreign providers of illegal cargo detected in the past. So when illegal importers changed the names, items or foreign providers, KCS was at a disadvantage. Moreover, as the patterns of illegal imports changed, computer experts targeted different kinds of cargo for inspections without taking into account the experience and know-how of customs agents in the field. Consequently, there have been continuous complaints against the customs inspection by the customs staff and the general public.

Implementing advanced data mining
KCS decided to implement an advanced risk management strategy to deal with these complaints. It specified three areas for innovation – the system for sorting out illegal cargo, the actual method of inspection and the expertise of inspection personnel – to achieve total improvement of the inspection process.

The agency employed advanced data mining capabilities in its innovation efforts.

KCS' introduction of data mining techniques is notable in that it attempted qualitative improvement by utilizing a state-of-the-art tool from the private sector. Established data mining techniques have been used by private businesses, such as insurance and credit card companies, to sort out bad customers before. But KCS applied them in risk management of imported cargo, expecting that scientific and objective sorting would be possible.

Yi Don Hyeon, Manager of KCS, explains, "Before, our competent staff collected and analyzed field and historical information to sort out risk patterns. As there may be, however, a blind spot where statistical risks can escape from detection, we felt the necessity of a mining technique to sort them out."

Looking for a software application to develop a data mining model, KCS decided to introduce SAS for fraud detection, based on its widespread use and trustworthy reputation in the data mining field.

20-percent increase in detection rate
Before a full-scale deployment, KCS conducted a pilot project. More than 60 search conditions were developed for model evaluation. Using SAS, the system began to show a significant improvement in detecting contraband trade, tax evasion, imports and exports of adulterated food, and so on. After the successful pilot program, KCS proceeded with full-scale implementation.

With KCS' focus on ensuring objective analysis, it was of the utmost importance to derive a hypothesis based on quality data. Yi Don Hyeon says, "Most of the time was spent deriving a hypothesis. Experts from 47 customhouses in the country were summoned to a number of conferences to identify candidates for the most risky patterns. Customs administration should be fast and accurate, and delayed analysis can cause damage to businesses. So, we worked hard to develop a solid plan because the system might seem less efficient. The SAS solution provided great support for this."

The new system enabled scientific and rational customs services. Presently, more than 400 staff members in the field are using the advanced risk management system. Upon a request for customs service, the personnel in charge of import inspection can immediately decide whether to inspect the cargo. Now they can detect potentially illegal attempts for customs clearance on the spot through KCS' know-how and data mining techniques.

The SAS solution enabled more specific and accurate sorting of illegal cargo. For instance, the number of potentially illegal factors increased from 77 to 163. As a result, the detection rate for important items, as well as the total rate, increased by more than 20 percent.

The SAS solution also enhanced organizational efficiency. A decrease in inspection rates and number of inspections through advanced risk management resulted in lower staffing levels. Furthermore, the number of inspections for normal cargo has been significantly decreased, leading to fewer complaints from import companies, a higher detection rate and a favorable reaction from the trade industry.

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.