A Data-driven, Graphical Approach to Dismantling Illicit & Counterfeit Medicine Markets (ICMs)

Date

2022-04-14

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

In the light of the global coronavirus pandemic, the rise of the illicit and counterfeit medicines (ICMs) market has impacted drug and medical supplies, bringing to the surface vulnerabilities in supply chain networks and the coordination of controlled responses. The ICM market thrives in an online context that utilizes affiliate marketing to target vulnerable communities. Currently, there is a lack of tools for aggregating and analyzing network intelligence and limited research on explainable clustering methods relating to ICMs. By creating a multifaceted strategy to develop new solutions and improve upon those currently in place, this work looks to advance the field of machine learning and network science from a distributed machine learning approach. Unearthing illicit supply activity requires the development of distributed data mining methods to detect anomalies and inference of coordination and intent. Developing a centralized data lake and subsequent simulations of the data to address the constraints will be the first work to produce a detailed catalog and proposal of how to set up a fully distributed machine learning solution for various industries. The tragic effects of ICMs are a global phenomenon, with the pandemic exacerbating the impact of the problem due to supply chain disruptions and a lack of quality control. Beyond the apparent public health impact, socially disadvantaged, and undeserved communities are more likely to suffer from the negative impact of counterfeit and poor-quality drugs. A cohesive and just society must protect its most vulnerable and this work promises to contribute to that protection.

Description

Keywords

Citation