Machine learning for intelligence driven customs management
| dc.contributor.author | Kavoya, Job | |
| dc.date.accessioned | 2020-07-27T12:05:21Z | |
| dc.date.accessioned | 2022-06-06T18:55:01Z | |
| dc.date.available | 2020-07-27T12:05:21Z | |
| dc.date.available | 2022-06-06T18:55:01Z | |
| dc.date.issued | 2020 | |
| dc.description | ATCR Journal Article | en_US |
| dc.description.abstract | The growth of big data is evident as organizations’ application of information technology continue to improve and data storage costs continue to fall. The growth of big data presents an opportunity for organizations to better understand their customers, develop strategies that will generate additional revenue, and grounds for business model innovation. However, a very small portion of data collected by organizations gets analyzed. This scenario creates a loophole that may deny established business additional revenues, and threatens their long-term existence if new market entrants explore this weakness. Intelligence-driven organizations analyze data to generate actionable insights that guide decision making. Customs administrations generate huge amount of unstructured data, but what percentage gets analyzed? This paper presents two frameworks that can be customized by customs to develop strategies for intelligence-driven operations. First, is the SCALE framework that defines attributes of intelligence-drive organizations and secondly, the data-value framework that defines how organizes can transform data to value. These frameworks are enhanced by a review of three customs services in the world. In summary, two key lessons are reviewed. First, is the focus on enterprise-wide adoption of analytics and secondly, is the role data in becoming intelligence-driven. The paper concludes by highlighting use cases where customs can leverage machine learning capabilities to enhance operations. | en_US |
| dc.identifier.citation | Kavoya, J. (2020). Machine Learning for Intelligence Driven Customs Management. African Tax and Customs Review, 3(1), p50-58. Retrieved from https://10.10.110.177/ojs/index.php/atcr/article/view/65 | en_US |
| dc.identifier.issn | 2664-9535 | |
| dc.identifier.issn | 2664-9527 | |
| dc.identifier.uri | https://ikesra.kra.go.ke/handle/123456789/809 | |
| dc.identifier.uri | https://atcr.kra.go.ke/index.php/atcr | |
| dc.language.iso | en | en_US |
| dc.subject | Intelligence-driven | en_US |
| dc.subject | Big data | en_US |
| dc.subject | Analytics | en_US |
| dc.subject | Customs | en_US |
| dc.subject | Machine learning | en_US |
| dc.title | Machine learning for intelligence driven customs management | en_US |
| dc.type | Article | en_US |