BACUDA: supporting Customs with data analyticsBy the WCO Secretariat
WCO Members asked the Secretariat to place a new focus on the development of guidance and capacity to support the use of data analytics. As one of the responses, a team of experts was put in place under a project called BACUDA. The project’s name is an acronym, which stands for “BAnd of CUstoms Data Analysts.” It is also a Korean word that means “to change.” Indeed, the aim of the project is to help Customs administrations in embracing analytical tools and methodologies, a major move for many.
BACUDA team members are all data experts with whom the Secretariat has been collaborating for some years. They are Customs officials in charge of risk management, statistics and IT systems, as well as professional economists and data scientists with an academic background in computer science. Data scientists of various nationalities from the Institute of Basic Science (IBS), the Korea Advanced Institute of Science and Technology (KAIST), and the National Cheng Kung University (NCKU) are involved in the project and leading the development of state-of-the-art algorithms. However, any qualified data experts working in Customs administrations or in academia may join the BACUDA team.
BACUDA is a collaborative research project between Customs and data scientists whose objective is to develop data analytics methodologies, including algorithms in open-source programming languages (R1 or Python2). Methods and algorithms are explained and shared on the WCO website, where they are presented under “Series3” and categorized by objectives, enabling WCO Members to deploy the algorithms in their administrations in order to analyse their own data.
To develop the algorithms, BACUDA analysts use Customs data at the most disaggregated level, i.e. the transaction level. Such data is collected from Customs administrations wishing to support the project, and is then anonymized to respect the confidentiality of the information that has been provided. Moreover, experts who access the anonymized data have to sign a confidentiality statement, and the preliminary results of any research are first released to the data owners who have to approve it before publication.
The potential success of the project lies with access to a huge amount of data at the transaction level, but BACUDA experts also work with open-source data. This data is not limited to macro-economic or geographical and spatial data sourced from international organizations. It also includes satellite images4 in the public domain published by some spatial and military agencies. In addition, experts also make use of some platforms that enable the movement of means of conveyances, such as planes,5 to be tracked as well as criminal activity or specific events6. Together, this data enables to gain a better understanding of border-related activities and supply chains.
Thanks to text-mining and web scraping tools, unstructured data can be extracted from web pages or social networking sites (SNS), and then analysed. For example, price data on online shopping platforms can be cross-referenced to assess the conformity of the declared value of an item for Customs valuation purposes.
Results and way forward
To develop and test the algorithms that they have designed, BACUDA analysts have at their disposal two powerful computers linked to a cloud server thanks to the generous support of the Korea Customs Service. This facility enables them to work anywhere, at any time, so long as they can connect to the internet.
The project team has already developed basic methods and algorithms presented under “Series3” and categorized by the following objectives: Mirror Data Analysis with R and Shiny, Forecasting Customs Revenue, Revenue Gap Analysis, Web Scraping of Price Data, and Customs Fraud Detection by Machine Learning with Random Forest and Python. Access to this information is restricted and interested readers who do not have a user account for the WCO website are invited to submit an access request to the WCO if they are Customs officials or to contact the WCO Research Unit if they have another public or private function.
In conclusion, it should be stressed that the project team is ready to solve all kinds of puzzles for Customs administrations, not only issues related to enforcement per se. They could, for example, help to develop chatbots to advise importers on how to classify their goods, or how to calculate duties and taxes that apply to their trade operations. Another area where BACUDA experts could be of use is in measuring Customs performance by text-mining comments appearing on SNS, rather than using traditional surveys.
http://www.wcoomd.org/en/topics/research/data-analytics.aspx (Make sure you are logged-in to access the page)
WCO Research team
3 http://www.wcoomd.org/en/topics/research/data-analytics.aspx (Access to this page is restricted, please make sure you are logged-in)
BACUDA is open to officials from all WCO Member Customs administrations, including representatives from other sectors such as academia. Potential team members should be experienced and/or passionate data analysts. Anyone who wishes to join or has a suggestion is invited to contact the WCO Research Unit.