Building an AI-empowered system for the detection and persecution of illicit trade
Illicit trade is a problem of massive scale. Smuggling, counterfeiting, misinvoicing and money laundering deprives states and societies of taxes, infringes on product and brand rights, compromises product safety – and finances crime. Global Financial Integrity found a gap of US$8.7 trillion in reported trade that ultimately flow into criminal ventures, yet the detection rate is near zero.
Currently there are very few tools available to detect complex, large scale illicit trade and its perpetrators. Investigations are time- and cost intensive. Law enforcement often relies on tip-offs while customs has to do random checks. Globally we are lacking a science-based understanding of how illicit transactions can be detected, what patterns they are following and how the networks behind them can be traced and persecuted.
The ATTENTION! project will analyse the largest trade database of imports and exports available globally together with extensive Web content- and metadata. ATTENTION! will develop Machine Learning models to understand and detect patterns of illicit trade activity and to expose the perpetrators and their support systems.
The trade activity of over forty countries over six years will be analysed comprehensively to ensure that all known smuggling methods such as co-mingling are included in the AI and ML models. The Web will be scanned for identified patterns to find new cases and detect the networks of perpetrators and their ecosystems integrating a vast array of 3rd party data sources.
Ultimately, the result of ATTENTION! will be the MVP for a cloud software system that will empower companies and authorities to better detect illicit trade and proceed against its agents.