The Data Science of Compliance

If it feels like groundhog day, you’re probably not alone. On May 2, U.S. sanctions on Tehran will again take center stage as waivers on imports of Iranian oil expire. But although on the surface it may seem like we’ve seen it all before – the new rules, new violations and the billions of dollars in fines that can result from them –  this time it is totally different.

On March 29, 2019, OFAC came out with new expectations that require everyone in the maritime supply chain – banks, energy traders, bunker service providers and other parties – to proactively screen the operations of every vessel they are doing business with. This puts the burden of implementing various OFAC sanctions firmly on the back of the business community.

This is a direct consequence of a UN Security Council report published in January 2019 that specifically stated: “Ship-to-ship (STS) transfers involve increasingly advanced evasion techniques. The disguising of vessels through ship identity theft and false Automatic Identification System (AIS) transmissions is not being taken into account by most global and regional commodity trading companies, banks and insurers, whose due diligence efforts fall extremely short”.

So, what does the data tell us? In March of this year, 529 crude oil tankers visited the Arabian Gulf. Of those, 352 tankers (two-thirds of the total) had gaps in their AIS transmissions for more than eight hours – gaps which are defined by OFAC as a red flag for sanctions evasion. Using AI to model STS, dark activity and identity tampering enables us to reduce the list of potential sanctions evaders to 29 vessels, a mere 5%.

Tanker Activity Arabian Gulf

Areas where tankers had AIS transmission gaps – screenshot from Windward system

This kind of deep analysis simply can’t be done manually, at least not in the time required to support real-world businesses. Consider the bunkering provider who has as little as 15 minutes to approve a transaction for one of its traders. Furthermore, compliance officers rightly say they want a method for seamlessly integrating vessel operational behavior data into their existing screening process, so that vessels are automatically flagged whenever behavioral indicators suggest sanctions evasion risk.

We have always believed that piecing together this puzzle requires a fusion of maritime expertise and data science. But for many years, the ability to map what vessels are actually doing and how they’re operated – rather than just understanding vessel ownership –  was only available to governments. Until now.

Today, we launch Windward Compliance, the first AI-driven maritime sanctions compliance solution. It allows energy traders, financial institutions and bunkering service providers to know who it is safe to do business with. It protects these organizations from the punitive costs of retribution from the U.S government for undermining their sanctions. And enables them to continue doing business with vessels that otherwise would be flagged for being at risk of sanctions evasion as defined by OFAC.

Compliance

The cost to any business in the maritime sector of coming up short on sanctions due diligence is potentially huge – in terms of penalties, share price and reputational damage. Getting the right data and recommendations every day is a small price to pay for peace of mind.

Ami Daniel is Co-Founder & CEO of Windward.