We live in a global society. The rapid changes in technology, infrastructure, and international business have meant that people are able to interact across the planet at a scale never before seen in history. The flow of goods and services around the world has become a vast interconnected web of commerce, allowing markets to operate seamlessly, competitively, across almost any border. Factories in China ship the latest smart phones to consumers in Chicago. Oil refined in Kuwait is turned into plastics and fuels for consumers in Kuala Lumpur. Gas from Siberia heats homes in Slovenia. In turn, these supply chains depend intimately on one another, making it virtually impossible to see where one begins and another ends.
The COVID-19 pandemic has only highlighted the fragility of this web. Like the fabled butterfly effect, restrictions at a factory in China, national stay-at-home orders, and curfews on international travel sends shockwaves all around the world; almost every industry has been significantly disrupted in one way or another. For instance, the dramatic rise in home working and home entertainment has been one factor in a global shortage of high-performance semiconductor chips, the kind found in laptops, game consoles and TVs. This in turn has led to huge production issues in disparate industries like car manufacturing where production lines and entire factories have even had to be shut down.
This complex web however has a darker side. Hidden within the legal and legitimate systems are vast networks of illicit networks of billions of pounds of trade, where criminals, terrorists and rogue states seek to take advantage for their own nefarious goals, which can come at immense cost to human safety, security and wellbeing. The pursuit of limitless cash fuels the worldwide trafficking perhaps as many as 50 million people into the horror of modern slavery. Black markets in exotic wildlife create billions in revenue while devastating our ecological habitats and vastly increases the risk of biological threats like viruses and pandemics.
These unconscionable acts sadly are highly profitable. Money, properly laundered, may fund lavish lifestyles of organised criminal gangs – fast cars, luxury travel and sprawling beachfront mansions. But money can buy more than jewellery, and other nefarious actors have used illicit finance and black market trade to further their own agenda of international terror, proliferation of nuclear weapons, and even to wage war itself.
At their height in 2014, the so-called Islamic State or ISIS which controlled swathes of Iraq and Syria were earning as much as $3 million per day from the sale of oil from the refineries of northern Iraq and Syria. ISIS used the funds and fuel for control and influence, allowing them to maintain a stranglehold on the people of the region, fuel for cars, trucks, factories and even hospitals, as well as to radicalise and recruit those to conduct deadly attacks on civilians in France, Germany, Egypt and the United Kingdom. Inevitably, oil from ISIS-controlled refineries and wells ended up throughout neighbouring countries via middle-men controlling old smuggling routes inherited from the Baathist era government (who used the routes to evade international sanctions) and Al Qeada. While allied air strikes eventually cut off most of this revenue, black market oil that directly funded terrorism would be readily available through places such as Turkey and Syria, who may haven even used state-owned companies to acquire and profit from this illicit resource.
War by other means
To combat these illicit networks and their corrosive effects, worldwide governments acting either independently or through shared governance and agreements in the EU and the United Nations have organised and communicated a series of international sanctions.
The use of such sanctions goes back at least as far as the ancient Greeks, blocking trade between nations could send a powerful political message and compel an adversary into changing their behaviour. But it was not until the 20th century that sanctions became institutionalised within the foreign policy toolkit. In the aftermath of World War I it was easy to think that sanctions (or even the threat of them) may be enough to deter states from another future conflict, but the on-set of World War 2 soon proved otherwise. More targeted efforts were needed and the modern system that focused on smart targeting of individuals and organisations was enshrined in the creation of the United Nations Security Council. Over time these were expanded, and influential governments such as the USA, UK and EU all developed their own lists of criminal and national security threats.
Modern sanction lists consist of highly specific and legally targeted entities – involved in everything from arms trafficking, nuclear proliferation, human trafficking, money laundering, terrorism, narcotics, and now even cyber attacks – which are consolidated and distributed to help organisations enforce them. Without enforcement they are meaningless lists, simply a summary of those who society collectively merely hopes would change in order to create a more peaceful and prosperous world.
Blocking these entities access to finance, energy, fuel, or other commodities is critical if they are to have any kind of coercive power to change. However, this is increasingly difficult, and we see three key challenges for managing the risk of these entities trading within global supply chains:
Complexity and Scale– the increasing complexity of global supply chains means that there is more chance for criminals to bypass control frameworks that are put in place. Companies operating at a global scale may have hundreds of thousands of counterparties involved in millions of transactions in many different jurisdictions. Understanding if any one of these suppliers, or a supplier of their suppliers are involved with an illegitimate entity can only occur with complete mastery of data.
Counterparty Detection – Even with consistent data, matching whether a specific counterparty in a supply chain to a specific entity on a sanctions list can be difficult.Abu Sara Zahrani, a Saudi national based in Syria was a member of ISIS tasked with buying and selling its oil and commanding an entire division of 7 oilfields at their peak. Enforcing sanctions requires not only spotting his name but also any other permutations or variants, Faysal Ahmad Ali al-Zahrani, Abu Sarah al-Saudi or even فيصل احمد بن علي الزهراني. (for more, please see our blog on entity resolution).
Escalating Criminal Risk – Criminals go to great lengths to obfuscate and hide their illegitimate activities within legitimate trades and supply networks. This means sanction lists are often an incomplete view on risk. Data from other sources can help expand the understanding of risk, including that derived from news and open source intelligence (OSINT) to build up a more complete picture. (For more see our blog on exploiting open source news data).
This blog has discussed the ways in which criminals and terrorist groups have exploited supply chains for their own gain and some of the challenges that global organisations have to enforce the international set of sanctions as laid out by the international community.
In order to overcome these challenges and to support leading companies to detect risks more effectively and efficiently within their complex and disparate supply chains, artificial intelligence and smart technologies are playing a significant role in ushering in a new generation of supply chain risk management.
Entity resolution technology developed by Ripjar uses millions of data points to derive more accurate search and matching logic than any other solution on the market. Compared to legacy solutions this reduces false positive matches by between 50-80% and increases accuracy and recall by 100%, meaning risks are more efficiently discovered and less time is consumed researching incorrect matches.
Natural Language Processing (NLP) also promises to expand our understanding of risk. This is a type of artificial intelligence that can read unstructured documents like news reports, documents or emails just like a human. We are using NLP to detect a far wider set of risks from open source news articles to augment watchlist-only matches and increase the ability for corporates to spot criminal activity.
Combined, these technology breakthroughs can scale to ensure that millions of transactions and counterparty dealings every day are screened, and help the teams tasked with preventing criminal abuse of resources, goods or services are able to conduct their investigations in a more efficient manner with overall more effective outcomes.
It was 4:15 on an otherwise unremarkable Sunday afternoon in March 2018, when two people – a man and a woman – were found slouched over a bench in the middle of a crowded street in Salisbury. Drifting in and out of consciousness, the pair were said to be foaming at the mouth, their eyes staring blankly into space. This was not the effect of alcohol or drugs, but something the public would quickly learn to be far more sinister, the targeted release of a lethal chemical weapon on a UK city. Over the following months, the event would soon turn into one of the largest public health emergencies in history, spark an international manhunt and shine a light on the murky world of espionage and a new chapter of worldwide malign influence; hybrid warfare.
The story of Sergei and Yulia Skripal, poisoned by the Russian state with a chemical nerve agent – Novichok – on the streets of a middle-class city in rural England, quickly became international news and even a BBC mini-series. As an ex-Spy himself, Sergei Skripal had risked his life working for British intelligence, MI6, informing on the activities of covert Russian agents all around the world. Like any spy, risk was inherent, but as a double agent – keeping the trust of his Russian spy colleagues while also reporting on them to the British – the stakes were life and death.
After an alleged ten-year career working undercover, something had gone terribly wrong. Perhaps an unusual behaviour of financial activity had sparked attention, perhaps communications had been intercepted, perhaps another double agent had informed on him. Whatever the reason, Skripal’s betrayal had been uncovered, and he was arrested for treason by Russian authorities in 2004. The Russian newspaper Komsomolskaya Pravda remarked that in Soviet times he would have been shot; but instead he was given 13 years in prison for “high treason in the form of espionage”. Less than 6 years later, in another dramatic movie-worthy twist, Skripal’s release from Russia was secured in 2010 in a classic ‘spy swap’ deal after a network of illegal Russian undercover operatives were discovered in the USA, including notables such as Anna Chapman.
In his release, Skripal had settled down with his family in the comfort and anonymity of Salisbury, sheltered by the country that he had helped in secret for so many years. On that fateful Sunday, as he and his daughter ate at the italian restaurant Zizzi’s, little did he know that two assassins from his former employer – the Russian military intelligence department or GRU – had travelled to the UK with the intent to kill him. A message and warning to any others who might defy the Russian state, betrayal will never be forgotten and nowhere, not even a quiet cathedral city in England, can be safe from retribution. After arriving into London from Moscow, the two assassins, travelling under the alias’ identities of Alexander Petrov and Ruslan Borishov, had initially travelled to Salisbury for less than 2 hours likely in order to conduct reconnaissance for their mission. The next day they travelled again to Salisbury, deploying the chemical nerve agent Novichok – hidden in counterfeit Nina Ricci perfume bottle – on the door handle of Skripals suburban residence. The substance, a highly toxic weapon developed in the Soviet-era, is designed to kill by shutting down the body’s nervous system, causing a loss of all critical functions including breathing. Only a few hours later the exposure had left Sergei and Yulia fighting for their life.
CCTV footage released by the police showed the pair walking in a residential area of Salisbury the day of the attack
What is Hybrid Warfare?
The event in Salisbury wasn’t an isolated incident. It was part of a wider coordinated strategy to exert power and influence in a new era of warfare. Often termed ‘hybrid warfare’, the strategy sits outside of the typical rules-based system of traditional foreign policy. It is a doctrine that is highly flexible and adaptive; it uses a variety of covert tools at its disposal to achieve strategic political objectives. From propaganda and ‘fake news’, to cyber-attacks, assassinations, political warfare and even economic and financial effects, these techniques can all be combined to exert a new kind of global influence. By its very nature it is concealed, with the war being fought by journalists, hackers, businesses and politicians – both witting and unwitting combatants in a greater game for power.
Unlike traditional warfare, where uniforms, insignia, and open declarations by politicians mean consequences can be more easily understood, the difficulty of attributing these coordinated activities means retaliation and retribution is more difficult for the national security communities tasked to defend against it. This completely upends the traditional ‘tit for tat’ mentality which has long been a bastion of international equilibrium. Therefore, it is a highly asymmetric threat, where the power no longer lies with shock and awe, but with networks, coordinated goals, and hidden agendas.
Russia’s fondness for coordinated subterfuge may go back decades, but it wasn’t until 2013 when Russia’s Chief of the General Staff, General Valery Gerasimov outlined what most would come to recognise as the modern codification of hybrid warfare. To wit, non-military techniques aren’t just ways of augmenting the traditional forms of war but are now the main form of influence in an increasingly connected and digital world. It is a war that is fought not only on the ground, but also in the digital networks of cyber space and in the psychological domain of people and cultures. The goal being not in singular military victories, but to keep adversaries in a perpetual state of competition and confrontation.
These techniques include:
Assassinations – While the attempt made on the life Sergei Skripal was ultimately unsuccessful, political assassinations send a powerful message; there is no place to hide and nowhere will be safe. The method of deadly nerve agent is also important, enemies will not be safe even with bodyguards, security or bullet-proof vests. Alexander Litvenko, another ex-spy targeted for revenge in 2006 was murdered after drinking a cup of tea laced with radioactive polonium in a busy 5-star hotel in the heart of Mayfair, London.
Cyber Attacks – hybrid warfare makes extensive use of digital techniques to achieve its aims. Hacking into computer systems provides valuable intelligence which can be used as part of a leak desired to inflame or exacerbate political weakness (as was seen throughout the 2016 US presidential campaign). Shortly after the Salsibury poisonings, local authorities in the area were hit with ‘well coordinated’ cyber attacks likely as part of the same operation. Cyber attacks can fuel other parts of the hybrid operation, collecting information from which to use later or as a platform for disruption – with the potential for damaging vital computer systems in order to leverage influence such as the “NotPetya” attack that while ostensibly targeted Ukraine, wrought worldwide damage to thousands of victims worldwide.
In a remarkable interviewed aired on RT, the pair expressed their passion for gothic architecture and the 123 metre spire of Salisbury Cathedral
Disinformation – Much has been made of the rise of “fake news” that can be pushed out in order to sow distrust in official statements, and counter the narrative. While online social media and automated ‘bots’ often garner attention, fake news has more impact when delivered through mainstream and official channels. Throughout the Salisbury investigation numerous false statements appeared via channels controlled by the Russian state including a claim by the Russian ambassador Alexandar Yakovenko accusing the UK of “destroying all possible evidence” “classifying all remaining materials and making a transparent investigation impossible.” and perhaps most infamously the eventual appearance of the assassins “Borishov” and “Petrov” on Russia Today as two fitness instructors with more than a strong interest in the gothic spire of Salisbury Cathedral.
Espionage – The use of undercover operatives has always been crucial to warfare, but when combined with other levers of power it can have powerful effects to amplify these clandestine goals. The Salisbury assassins were allegedly met in London by another high ranking GRU officer Denis Sergeev, travelling under the alias of Sergey Fedotov who likely gave them their final orders to proceed. These networks of spies, with access to infrastructure, and local connections allow more specialised operations to take place. Throughout 2018 after the Skripal poisoning, Russian agents attempted to access laboratory facilities and networks across Europe including in Switzerland and the Netherlands where material relating to the attack was being analysed. Combining traditional human intelligence techniques, technical surveillance and on-the-ground cyber attacks – undercover teams can be a formidable asset, accessing vital information that could not be gathered any other way.
What can be done to counter Hybrid Warfare?
Just as hybrid warfare uses a holistic blend of techniques to achieve its goals, countering it must also seek to break down barriers between traditionally separate capabilities. Understanding the networks and infrastructure that enable adversaries to coordinate espionage, cyber-attacks, disinformation, and assassinations can help decision makers devise strategies that can create resilience in society and counteract the subversive effects of instability.
Data fusion for analysis and intelligence – Sound intelligence is fundamental to countering hybrid threats, but being able to see the complete picture relies on the fusion of data from all sources; joining the dots between data of different types is critical to unpicking the threads of deception. From the moment that the Salisbury assassins entered the UK, they generated data that investigators and analysts could use to understand their movements and intentions. From CCTV at airports, train stations other locations, to mobile phone data and passport information, we all leave digital footprints in an ocean of data that can give clues to our behaviour.
For instance, in September 2018 a major breakthrough in the Skripal case came from investigative journalists working at Bellingcat and The Insider. Piecing together information from publicly available information on the internet and leaked information on the dark web, Bellingcat showed the world how careful examination of data could uncover the real life identities of the assassins as GRU officer Colonel Anatoliy Chepiga and Dr. Alexander Mishkin. Critical to these breakthroughs was the ability to fuse data from database records, passport scans, images, news articles, websites and documents – linking alias names, addresses, dates of birth and key events to resolve their real life identities (see also our guide on “Entity Resolution” here).
Sanctions and Expulsions – On the27th March 2018, less than three weeks after the attack at Salisbury, an international community of 27 countries including the United States, Ukraine, Canada, Germany, France and Poland expelled 142 Russian nationals from their countries in the largest mass expulsion of diplomats in history. In 2020, the USA, EU and UK went even further, issuing legal sanctions against GRU officers involved in many of these operations, including Aleksei Minin, Aleksei Morenets, Yevgeny Serebriakov, and Oleg Sotnikov who were all accused of taking part in the espionage attempt at the OPCW in the Netherlands where material from Salisbury was being analysed. Such sanctions, effectively deployed within the financial and travel sectors (deployed using technology such as Ripjar’s Name Screening Solution) restrict these individuals’ ability to access basic services and commerce, providing a vital part of the deterrence strategy to send a message to others who may choose to be involved in these types of operations that there are consequences for their actions.
Interagency cooperation and knowledge sharing – No single organisation has a complete picture of all data or is responsible for enacting the strategies to counter hybrid threats. Therefore, effective security strategies to defend against hybrid warfare rely on intelligence sharing and collaboration between government departments, law enforcement, the intelligence services and the private sector. The UK government’s ‘Fusion Doctrine’ published the same month as the Salisbury attack, outlines this whole-of-government approach to collaboration for the purposes of national security, but it must also be underpinned by the technical enablers to do so. From secure communications to data platforms that can share knowledge on threats and intelligence reports, the infrastructure for collaboration must also enable investigations. While police may have access to CCTV data and witness statements, other areas may have specialised data on chemical weapons systems, or the public health emergency developing in the area. Furthermore, banks and other financial institutions will have access to money flows and transfers that all might give a small piece of the puzzle to uncovering the larger pattern of subversion.
Predictive Analytics for Discovery – Finally,countering hybrid threats will not succeed if there exists only a retrospective capability to understand events after the fact – even if that capability does include the heroic forensic detail from sources such as open-source intelligence and the dark web.Therefore, in order to build our defences, data analytics must become forward-looking for discovery of such threats as they emerge. Artificial intelligence and new ways of processing data for behavioural clues will play a vital role in the development of such discovery analytics. Combining all data sources and an understanding of hybrid threats and their characteristics, these advanced forms of data analysis are able spot a clandestine officer arriving from overseas and who they were travelling with, setting up bank accounts or other infrastructure and are able to automatically link known data points of existing threats, to unknown but active data points within the same pool of information. This means threats can be uncovered more quickly, automatically and with more efficient use of resources to help scale against the size of the challenge.
Organised Crime on a Global Scale
Sergei Skirpal and his daughter Yulia ultimately survived the attack. A member of the public Dawn Sturgess, sadly did not. Some may call it hybrid warfare, others simply as murder. The act of criminality, albeit committed by a state actor, does not reduce its culpability, it heightens it. Responsibility for such murder doesn’t just fall to the individual who committed it, but to the entire system that enabled it.
Tackling organised crime on global scale, acts that take place outside of the norms of international behaviour requires a shift in our thinking. Distinguishing between crimes committed by terrorists, gangs or even governments may be difficult, if not impossible without strong attribution of cause and effect. Technology, and new advancements like artificial intelligence and data fusion, deployed within the public and private sectors will accelerate the detection of these hidden networks, and the very connectedness that allows hybrid warfare techniques to succeed will eventually be the same method from which it is successfully defeated.
David Balson Director of Intelligence, Ripjar March 2021
After the Nile, Amazon and Yangtze, the Mississippi ranks as both one of the longest and most evocative rivers in the world. At the heart of the American continent both in location and in stature, the 2320 miles of the Mississippi collects water from a colossal catchment area of over a million square miles, collecting most, if not all the water from 31 US states or 40% of the entire USA, before discharging half a million cubic feet of water every second, into the Gulf of Mexico. It’s story is just as vast as its dimensions, the steamboat-era of the 1930s best captured perhaps by Mark Twain in The Adventures of Huckleberry Finn, has cemented the river’s place in popular culture and imagination.
But it is the river’s economic value that has continually driven its significance. Even the sedentary pace of the 19th century paddle steamers was enough to develop the river as a key route for goods and passengers alike. Today the river transports more than 60% of the US agricultural output and is a critical shipping route for oil and coal throughout the country. The economic value is now estimated at over $400BN, as well as supporting millions of jobs both directly on the river and indirectly in the businesses that have come to rely on it.
It was not always like this. The meandering flow created by nature – the “Father of Waters” as the native Anishinabe people called it – did not lend itself well to its use as a shipping route. The 19th and early 20th century saw substantial attempts to shape, chisel and file off inconvenient curves, bends and other features less conducive to commerce; canals were dug to bypass impassable rapids, dams and levees were built to control flooding, and dredging meant the river could accommodate bigger and heavier ships.
These early attempts would prove disastrous in the long run. Throughout 1926 the rain had been unusually heavy, saturating the basin that fed the river for months. The rain however, did not stop. The spring of 1927 brought catastrophe. The river broke out of its banks in 145 places, and inundated 27,000 square miles to depths of more than 30 feet (9m). The flood left an estimated 750,000 people without food or shelter and created a humanitarian disaster the effects of which can still be seen today.
Those interventions – the attempts to tame the river – had not only had failed, but spectacularly backfired. Straight waterways channel water more efficiently. Deeper water flows more quickly and in greater volume. Levees and dams restrict the natural flow and increase the elevation of the water line. All combined to worsen the resultant flooding.
After the floods, the US Army Corp of Engineers were tasked to build the largest system of flood defences in the world. Taking over from the previous local and piecemeal approaches to flood defence, the Corps took a holistic approach looking at the entire region. Starting in 1928, in one of the largest public civil engineering projects ever devised, dozens of canals, locks and levees would be built to ensure the river could stay navigable for commerce, while allowing nature to take its course whenever the rains came. While new flooding has continued to refine the system, nothing like on the scale of 1927 has ever happened again.
The New Flood
While the Army Engineers were ushering in a revolution in how the great river Mississippi was managed, the 1920s also saw a different revolution in America. As a wave of prosperity surged through middle classes after WW1, new forms of entertainment in the form of tabloids, magazines, radio and motion pictures all captured the public appetite for modernity. These new forms of media ushered in profound cultural changes as new ideas could now freely proliferate, changing the very fabric of society. Time Magazine, Readers Digest, Amos and Andy, Charlie Chaplain; the 1920s set out the template for what would become billion-dollar media empires, movie studios and the liberal flow of knowledge and ideas.
For over 70 years these forms of media grew in popularity and influence, until a new flood occurred. This wasn’t a flood of water, but of information. The internet created an entire new way that media could be created and consumed. In 1996 the internet passed 100,000 websites and by 2000 there were more than 20 million websites; today there are well over a billion. Social media, which empowers anyone to become a publisher of information has created data orders of magnitude larger, with hundreds of millions of posts per day being broadcast on the top platforms.
Reducing the Noise
This blog has already talked about the value of intelligence gathering from open-source media (see Deciphering Risk from Adverse Media Reports) and the ways in which small pieces of information can even reveal information valuable to national security and countering financial crime. Technology has optimised the flow of information to create the most value for people sharing the latest news, but – just like the waters of the Mississippi – it has also created the pre-conditions for a flood.
When on-boarding clients within a financial services context, the flood becomes particularly tricky to navigate.
Using traditional search engines, an analyst may be looking for news articles, something in their history that betrays a risk, criminal activity or other potential regulatory issue. Typing in that client’s name into a search engine could result in a huge number of search results which can easily total many hundreds if not thousands of pages. Perhaps an interesting article detailing their involvement in bribery scandal appears on Page 27 of these search results. How many pages are you able and willing to scroll through to spot the risk? Perhaps, the client shares the same name as a famous sports or pop star and it is difficult to ascertain if the client is among the results at all. Perhaps the results return an article that indeed mentions the prospective clients name, but in the context of a family matter or unrelated business announcement.
This deluge of poor quality and irrelevant data often means that analysts neither have the time nor patience to wade through and find any potential risks. This has typically meant so-called adverse media or negative news searches are time consuming and rarely result in actionable intelligence as part of the on-boarding process.
Rudimentary approaches to solving this problem are widespread in the financial services industry. For instance, by adding the word “bribery” after their clients name “Acme Inc.” may help hone the results somewhat. Adding other words like “corruption”, “crime”, or “human trafficking” might expand the potential for discovering risk, but it is extremely limited as a crude attempt to shape and file off the rough corners of the mountain of data returned.
Simply, these keyword-based searches could never hope to match the range of nuance and variety in the language of news articles, webpages and other open-source data that might inform the intelligence picture around a client’s behaviour. Furthermore, limiting such keyword searches to a single language such as English reduces the likelihood of finding articles in any one of the global languages that make up the media landscape all over the world.
NLP: A Next Generation Approach to reducing Data Floods
Just like the new generations of levees and dams that were built on the Mississippi throughout the 20th century ushered in an entirely new, holistic approach to managing America’s greatest waterway, new technology is now doing the same for managing the flood of information that is inundating compliance analysts conducing adverse media checks.
Natural Language Processing (NLP) is an application of machine intelligence which can automatically read and understand unstructured text such news articles, documents, or any written material. Like many other techniques within the field of AI, this works by training an algorithm to recognise what a news article is about at a conceptual level, allowing to the machine to understand what ‘bribery and corruption’ looks like, in multiple languages and from multiple news sources. In fact, in order to train up a classifier for adverse news, we typically look for 10,000 examples to train the system to spot future, similar articles about that topic. Once trained, these algorithms can spot, instantaneously, the features of an article about bribery and corruption in dozens of languages over millions of articles of news.
Applying this within the context of adverse media searching means NLP has the following benefits:
News Articles are automatically grouped into topics of interest – Over 3 million news articles are published every day from news outlets all over the world. Properly trained NLP can group all of these into different categories before a human has even arrived at their desk. Articles about predicate crimes such as human trafficking, embezzlement, or narcotics can all be pre-selected by the system for searches and alerting without the need for elaborate sets of keywords and query terms.
Irrelevant or Useless articles are automatically removed from review – the overwhelming majority of news articles published every day are not relevant to making informed decisions about client risk. Specifically, we estimate that of the millions of articles published every day, less than 0.8% have any value for on-boarding or periodic review. NLP removes over 99% of the noise from adverse media searches meaning that results returned are more relevant and likely to be of value.
Duplication is reduced and similar news is grouped into stories – similar articles are published every day by multiple outlets. Some are even syndicated, word-for-word copies flood news desks on multiple publications. NLP cuts through this noise, automatically discounting identical articles, and grouping similar articles about the same story into an easy to review collection. This further reduces the analyst burden.
News articles can be grouped not just by keywords, but by phrases and complex combinations of linguistic patterns – going beyond simple keyword monitoring, NLP looks more deeply at the structure and patterns within news articles. This means groupings of topics are more accurate, resulting in better quality searches and data.
Articles in other languages are automatically searched for, identified, and translated – NLP topic classification can be done in any language, provided there is sufficient source of ground truth from which to base its decisions on. Training these topic classifiers in over 15 global languages means that risk is identified no matter where the media article has been published.
The Ripjar difference
It is impressive to imagine the engineers who designed the monumental programme of flood defences after the great flood in 1927, who did it all without any advanced modelling and simulation software, let alone a pocket calculator. All they had was their ingenuity and a slide-rule. However, their engineering was able to tame ‘Big Muddy’, and make it safe for those living and working on it, while respecting the natural processes which put it there in the first place.
We have combined state of the art NLP with Entity Resolution (see What is Entity Resolution?) to give intelligence analysts within financial institutions a world-leading adverse news capability. The colossal river of information that flows digitally around the world is measured not in gallons, but in terabytes. This torrent of information can be harnessed for many different purposes, including the effective screening of clients in financial services for risk and NLP is a critical tool in reducing the volume of this torrent to make it more efficient and effective to help institutions fight financial crime.
If you’d like to learn more about our adverse media or negative news screening capabilities, please read the whitepaper here, or contact us for a demonstration.
