Category Archives: FICO
In another sign of the growing use of the cloud for fraud protection, EnterCard — one of the leading Scandinavian finance companies — will use the FICO® Falcon® Platform to combat card fraud and communicate with its 1.7 million customers.
EnterCard is upgrading to a cloud-based version of Falcon to protect customers in Sweden, Norway and Denmark from fraud.
“The cloud-based version of Falcon gives us greater flexibility to serve our customers with better fraud protection,” said Yannick Leclerc, head of fraud in EnterCard Group. “We will have greater control over how we communicate with customers when fraud is suspected, which will help us improve the customer journey in a fraud context.”
For more information, read our news release.
Economies of scale is one of my favorite economic principles. It’s especially cool to see how FICO customers can realize associated benefits by using our behavioral analytic technology.
IDC predicts that in 2017, behavioral analytics across compliance, fraud, and cyber detection and prevention will be in place at 15% of banks, helping them to avoid losses, regulatory fines and sanctions.
Banks have already made a big start in the fraud space. FICO introduced behavioral analytics in the early 1990s and we currently analyze two-thirds of the world’s payment card transactions, in real time, for fraud.
Now, FICO’s proven behavioral analytics can be applied by forward-thinking institutions to fight a wide range of financial crimes. In doing so, banks can gain powerful technology economies of scale, too, leveraging mature, market-proven analytic models to benefit new domains within their business.
How do behavioral analytics work?
A quick search may tell you that “behavioral analytics” measure the behavior of consumers on ecommerce platforms, online games, web and mobile applications or Internet of Things (IoT) devices. In fact, “behavioral analytics,” from a pure data science point of view, help us to understand much more:
- what an individual person or device does, and
- what they don’t do, but might in the future.
The first comparison is of the customer or device in the context of their own history of events, where one can determine changes from historical behaviors. A second comparison is done by grouping customers or devices into similar clusters, and then analyzing how much the behaviors of individuals deviate from their associated groups.
Depending on the degree of variance, we can assess how likely the behavior is to be aberrant and thus potentially fraudulent or criminal — or, in the case of a network device, how likely that endpoint is to have been compromised by a cyber attacker.
Power at scale: Enhancing fraud, compliance and cyber security defenses
Behavioral analytics are a mature technology in fraud prevention. Behavioral analytics technology allows us to flag potentially fraudulent transactions with pinpoint accuracy, greatly reducing the volume of “false positives,” or transactions flagged as potentially fraudulent that are, in fact, legitimate. FICO has honed its fraud detection technology to identify the needles in the haystack.
In terms of compliance — particularly anti-money laundering (AML) and terrorism financing — the most prevalent transaction monitoring solutions used to identify illicit activity in these domains are extremely imprecise. The compliance solutions generate tens of thousands of alerts for every genuinely criminal transaction requiring a formal suspicious activity report (SAR). The volume is so great that that compliance officers can only investigate a small fraction of suspected SARs. As a result, illegal transactions slip through, continuing through the global payments system.
It’s the same situation with cybersecurity. In any security operations center, there’s a cacophony of alarms, 24-7. It’s impossible for operators to tell which alarms are calling out truly meaningful intrusions, and which are just noise. That’s why so many cyber attacks go undetected for weeks, months or even years.
Benefits beyond cost savings
As IDC noted, behavioral analytics technology can help financial institutions to avoid regulatory fines and sanctions. The benefits extend farther: in terms of fraud and compliance, behavioral analytics will allow more illicit transactions to be stopped as they occur, saving untold amounts of financial and reputational loss.
With regard to cybersecurity, the ability to pinpoint cyber attacks more quickly greatly reduces the “dwell time” of malware, ransomware and other malicious code that causes data breaches and other damage. Again, this can significantly reduce the costs of remediation that result from breaches, as well as major financial and reputational losses.
Want to know more? Check out my latest FICO Hot Topic Q&A, “Behavioral Analytics: Boosting Protection across Fraud, Compliance and Cybersecurity.” Follow me on Twitter, too, @ScottZoldi to keep up with my latest analytics rants, raves and musings.
More than 70 straight months of US job growth, the official unemployment rate down below 5%, and average hourly earnings growing at a seven-year high of 2.9%. Signs of approaching full employment finally allowed the Fed to see enough stability to inch up rates without being seemingly blown off course by events elsewhere. There will be more rate hikes to come if the economy stays on this course, and in the event the deficits grow, it will pretty much guarantee what we already expect on the interest rate front.
With all this in mind, it’s a good time to ask: Has the US credit cycle reached the bottom? Is it as good as it gets?
Of course, we never know that for sure. This is all opinion (some would say speculation), especially on the economic policy front. But you have to feel that if it isn’t the bottom we are not far off.
Take a look at delinquency stats.
All of these figures are based on a two-year outcome. Thus, the scoring date for the October 2016 figures would be October 2014.
The most interesting observation is the uptick in origination delinquencies, which we see across the board relative to 2013. Compare that to the broader population, where we see the generally benign to improving economic environment continues to push down rates. (Originations here are trades opened within six months of the scoring date.)
Of course, these figures don’t allow us to separate deterioration from laxer credit standards. It’s fair to say that the latter almost certainly is a key contributor.
In the major product categories, the picture is mixed. At least at the top level, the lid still seems to be on the mortgage market, where delinquency rates remain low. In the card and auto worlds, rates are still a long way below the dark days of 2008 but are up among younger borrowers.
Do YOU think today’s credit cycle is as good as it gets? I invite you to make your case in our comments section.
The truth is that we will only know when we look back and say “I told you so!” For now, the signs suggest we are near that point, and we should keep our eye firmly on the horizon to understand which way this is headed.
Which works better for modeling credit risk: traditional scorecards or artificial intelligence and machine learning?
Given the excitement around AI today, this question is inevitable. It’s also a bit silly. While some new market entrants may have a vested interest in pushing AI solutions, the fact is that traditional scorecard methods and AI bring different advantages to credit risk modeling — if you know how to use them together.
Take, for example, our new credit decisioning solution, FICO Origination Manager Essentials – Small Business. It’s designed to help lenders make faster origination decisions without increasing risk. This new FICO product combines our well-established scorecard technology with AI to build better credit risk models.
How FICO Uses AI to Build Better Credit Risk Models
As with our other origination products, Origination Manager Essentials includes credit risk models, and these models are segmented — different types of small business customers and different credit products require different models to assess their credit risk.
In traditional risk modeling, customer segmentation is based on “hard” lines and broad categories, such as new customer vs. existing customer. This doesn’t capture the behavior of certain individual entities or more optimal ways to segment scoring models.
To build the models in Origination Manager Essentials, our data scientists used AI and machine learning algorithms to discover a better way to segment the scorecards. This allows us to apply AI to improve risk prediction without creating “black box” models that don’t give risk managers, customers and regulators the required insights into why individuals score the way they do.
We are now starting to use techniques such as collaborative profiles to reveal entity segmentation based on customer behaviors. We can then group customers into micro-segments based on that similarity, instead of typical segmentation approaches that rely on hard business attributes. For example, collaborative profiles derive behavioral archetype distributions — these could include archetypes that point to credit seekers building credit histories vs. those who have higher risk and covering misuse of credit elsewhere in their history.
The way that we can capture these subtle changes in behavior, and can incorporate them into the credit risk model, presents a distinct advantage for FICO customers. Our approach builds on mature, time-tested analytic models and scorecards, enhancing them with advanced AI technology to drive better segments and feature creation in models.
Another approach is to use AI and machine learning to “train” models to discover maximum predictive power, and find new relationships amongst input features that could produce a stronger model. For example, utilization is always an important feature in a credit model, as is delinquency, but a nonlinear combination of these can produce more optimal results in a machine learning model. You can then drive these new inputs into a traditional scorecard model to ensure explainability.
Improving Results with AI and Machine Learning
The two examples below illustrate how you can achieve better performance and explainability by combining machine learning and scorecard approaches.
When developing a credit card churn model, FICO data scientists used machine learning to discover a powerful interaction between recency and frequency of card usage. The option to include this interaction as a nonlinear input feature in an interpretable fashion into a scorecard led to a substantial improvement (~10%) of the lift measure, used to characterize the performance of attrition models. In addition, another 15% performance improvement was found by applying machine learning with a much larger set of features relating to event-specific recencies and frequencies. These predictive improvements in turn can translate into substantial portfolio profit gains for a much more precisely targeted retention strategy.
In a project to build a home equity portfolio with limited data, the lack of enough “bads” (poor performing loans) in our sample was causing some problems. By building a machine learning score with optimized hyperparameters, we were able to confirm that we were losing a significant amount of signal with a traditional scorecard. Using machine learning led us to change the model performance outcome from a binary outcome to a continuous outcome. By combining this technology with scorecard technology, we created a strong, robust, palatable solution and saw a 20% improvement in model performance (KS) over a traditional scorecard model alone (see below).
A Smarter Way to Use AI
FICO has long been involved with using AI as part of our analytic approach. How long? We recently filed a new explainable AI patent application to improve upon the IP of a FICO explainable AI patent granted in 1998 —that patent already expired.
Years of market experience have validated our approach, which is very different than the “move fast and break things” brashness we see from some AI start-ups in the originations space. They’re focused on using many types of alternative data, such as information gleaned from social media, to deduce credit risk.
Innovation is great, but you don’t want to naively throw in a lot of new data sources ––many of which may not be permissible in credit decision-making, and might be easily manipulated (like social media data) –– into an AI model that comes up with a score that may not be explainable. Why not? First of all, lenders in many markets do need to be able to explain how a customer was scored. Second, you don’t really understand what relationships are being learned from this data, and if these relationships really matter. By contrast, FICO analyzes new data sets along five lines to see if they will add value to credit risk scoring.
That message was part of my talk at the LendIt USA conference a few weeks ago, where I participated in the panel, “The New Frontier: AI, Machine Learning and Advanced Analytics.” You can see the video of the LendIt panel session here.
The Power of Scorecards
Scorecards are a powerful tool because, like AI, you can incorporate non-linearity in the input layer, and you can take advantage of different features that may be predictive in different ways for different subpopulations, by using segmented scorecard ensembles. But unlike some manifestations of AI, scorecards offer transparency and explainability. This is a big theme in any conversation about AI and credit risk––you need to be sure you understand how that decision was made. Most AI technology remains “black box” and can’t provide an answer when a customer asks, “How did I get this score?”
That said, if I can use machine learning to expose powerful and predictive new latent features of credit risk, I can then directly incorporate them into a scorecard model. This preserves transparency while improving prediction.
If you’d like to learn more about FICO scoring concepts, this webinar explores the FICO® Score and alternative data. And check out my Twitter feed, which is always rolling with my latest thoughts on analytics and AI.
Some 500,000 – 600,000 new small businesses emerge each year, according to recent U.S. Census Bureau data, and they supply over 60% of jobs. While we’ve expected that number to grow and fuel the economy, it is starting to decrease according to recent reports by TIME and CNN Money.
Is small business growth slowing due to lack of innovation and initiative? That seems unlikely. According to a survey done by Insureon, 82% of small businesses expect to grow in 2017. Whether buying new equipment or furniture, hiring, moving, or adding products/services, businesses are planning to expand.
So what’s really standing in the way?
FICO’s mid-market bank and credit union clients tell us that it remains difficult for entrepreneurs and small business owners to acquire the credit they need to fuel their growth plans. The reasons for this are two-fold.
First, there is often little traditional commercial credit history available on new businesses and little traditional consumer credit history on the principals of those businesses, especially among new immigrants or young entrepreneurs. Lenders perceive that the investment in these ‘thin-file’ applicants is extremely risky, although it often isn’t as dicey as they think when using the analytic tools and data sources available today.
Second, it’s expensive for all lenders to serve these smaller community businesses. Whether loans are issued for one million dollars to a commercial business or ten thousand to a small business, traditional lenders frequently spend the same amount of resources to originate them. This makes it less profitable to take chances on small businesses.
Since lenders don’t yet see a viable solution to this issue, they choose to focus on mid-size and large corporate customers, taking fewer chances on small business customers. It remains a challenge to increase origination efficiency and make lower-dollar small business loans a profitable and scalable venture.
Mid-market banks and credit unions traditionally lend to many small businesses. They often provide a more personalized financing experience, as well as focus on building and maintaining relationships with community businesses.
There is good news for mid-market banks and credit unions. Small business owners value the personalized relationships and community focus that smaller lenders provide. All things being even, small business owners prefer working with these lenders. In fact, 75% of small businesses that are customers of small banks or credit unions are “highly satisfied” with their lending relationship, according to a survey at the Federal Reserve Bank of Cleveland. By contrast, only 51% are “highly satisfied” with large banks, and only 15% with online lenders.
In the same survey, small business customers listed two main problems with their mid-market bank or credit union relationship: a difficult application process and a long wait time for the credit decision. Both can be attributed to manual processes. FICO sees this as the major roadblock for growth in small business lending, and it’s certainly a notable disadvantage compared to the instantaneous decisions provided by larger lenders and online lenders.
For those with manual origination processes and limited automation, the first step is implementing a decision rules management system. This allows small lenders to improve loan volumes with the same resources. The system should include an intuitive user interface that enables business users to author rules and deploy business strategies quickly, without the need for IT coding. Next, they should look to create scores specific to smaller enterprises, often with a mix of personal information from the founders/owners (like the FICO® Small Business Scoring Service℠ solution).
FICO works with mid-market lenders to solve these manual loan processing challenges in a sophisticated way that meets budget and ease-of-use requirements. Our newest product, FICO® Origination Manager Essentials, targets mid-market lenders to help them make quicker, smarter small business lending decisions. To read more about this solution, visit fico.com/fico-origination-manager-essentials.
The latest fraud news from the FICO® Card Alert Service, which monitors hundreds of thousands of ATMs and other readers in the US, is bad. In fact, it’s doubly bad:
Here’s some more details: About 60% of the compromises were at non-bank ATMs, such as those in convenience stores. The rest took place at bank ATMs or point-of-sale (POS) devices, such as card payment machines at retailers.
The average duration of a compromise continued to fall — on average, an ATM or POS device would be compromised for 11 days, compared to 14 days in 2015. The 2016 average duration is less than a third of the average duration in 2014, 36 days. The average number of cards affected by a single compromise was cut in half.
What’s behind this startling rise, which is a new record high? Better skimming devices in more people’s hands. If you really want to hack an ATM, you can get your hands on the tech pretty easily. That means we’ll continue to see compromises – and card fraud – rise.
I’ve been asked whether EMV transition is playing a role here. I think it is, but not the role you’d expect.
As ATMs aren’t yet required to be chip-card enabled, the EMV adoption that came into force last year isn’t driving fraud down yet. Instead, we may be confusing consumers — we tell them not to use machines that look funny or have tape on them, and then the cashier tells them to use a POS device that looks funny and has tape on it. You know, machines that look like this:
That said, if you are looking for tips for your customers, here’s FICO’s advice:
- If an ATM looks odd, or your card doesn’t enter the machine smoothly, consider going somewhere else for your cash.
- Never approach an ATM if anyone is lingering nearby. Never engage in conversations with others around an ATM. Remain in your automobile until other ATM users have left the ATM.
- If your plastic card is captured inside of an ATM, call your card issuer immediately to report it. Sometimes you may think that your card was captured by the ATM when in reality it was later retrieved by a criminal who staged its capture. Either way, you will need to arrange for a replacement card as soon as possible.
- Ask your card issuer for a new card number if you suspect that your payment card may have been compromised at a merchant, restaurant or ATM. It’s important to change both your card number and your PIN whenever you experience a potential theft of your personal information.
- Check your card transactions frequently, using online banking and your monthly statement.
- Ask your card provider if they offer account alert technology that will deliver SMS text communications or emails to you in the event that fraudulent activity is suspected on your payment card.
- Update your address and cell phone information for every card you have, so that you can be reached if there is ever a critical situation that requires your immediate attention.
We’ll keep an eye on the ATM situation and give another report mid-year. Follow me on Twitter @fraudbird.
On Groundhog Day 2017, I was thinking that the payments industry is a lot like Groundhog Day, the movie. There are an awful lot of repeating themes in the payments world. And in the best case, they can teach us invaluable lessons.
Payments speed is one of those recurring themes. Four years ago, we at FICO started saying it’s time for banks to upgrade fraud protection in their retail banking departments. Otherwise, financial institutions could wake up one day—Groundhog Day?—and realize that it’s too late; fraudsters will have figured out how to hijack funds flowing out of checking accounts.
Today could be that day.
Are banks truly ready for same-day ACH?
Between the Same Day ACH initiative launch on September 23, 2016 and December 31, 2016, there were more than 13 million same-day ACH transactions. A significant 14% were person-to-person (P2P), a pretty astonishing amount for a brand-new payment type. NACHA provides a roundup of interesting statistics:
Consumer demands and expectation will continue to drive the speed of payments faster. In today’s era of Venmo and SnapCash (and soon Zelle), three-day P2P transfers just don’t cut it. However, many P2P payment systems are secured by payment cards, which are protected by very robust and mature anti-fraud technology—the FICO® Falcon® Platform—and the transactions that flow through them are not subject to the same rigor of compliance requirements.
ACH is a different animal. Increasing the rate, pace and volume of these payment types, which exit the customer’s checking account directly, will quickly strain banks’ compliance organizations and processes. Their compliance infrastructure is typically rules-based and relies on human intervention—two ingredients that don’t have the elasticity to scale as much, and as fast, as is required. This exposes banks to fraudsters, who will quickly find and exploit the weakest link. (Remember the ApplePay authentication fiasco?)
How to fight back
There are two ways that banks can effectively shore up their defenses to fight against same-day ACH fraud:
- Use the power of AI: Artificial intelligence and machine learning supercharge the ability of FICO compliance solutions. As a company, we are pioneers in using AI and behavioral analytics to fight fraud. These capabilities are now applied to FICO TONBELLER solutions for anti-money laundering (AML) and know your customer (KYC), both of which factor into compliance monitoring of ACH transfers. (See our recent blog series on AI in AML.)
- Get a more holistic view of the customer: FICO Falcon is well known as a leading solution in the payment card fraud area. As shown below, the Falcon Platform offers equally robust functionality to monitor payments such as payment card authorizations, posting, ACH, wire, person to person, deposit, online payments and bill pay, and mobile banking activity.
When banks use these capabilities to monitor customer activity across all of their financial behaviors, they can get a holistic view of customers on individual and aggregate levels. This lends crystal-clear insight that can transform the efficiency and efficacy of screening same-day ACH transactions.
Consumer demand to fluidly transfer funds between people, instantaneously, will only increase at a faster pace. For example, PayPal’s Venmo is on track to process $ 20 billion in payments per year; the technology was acquired by PayPal only in 2014.
Just a few years ago, if you were building checking fraud models based on historical transactions, checks would have been the only payment mechanism. But now you’ve got people zapping money to businesses and each other directly, through multiple mobile apps, and often directly out of their retail bank accts. That’s why new technologies, like AI and machine learning, and new approaches, like cross-customer views, are essential.
Keep up with my payments views on Groundhog Day, and every day, on my Twitter feed. Follow me @FraudBird.
Great news, FICO was named as a leader in the March 2017 report, The Forrester Wave™: Predictive Analytics and Machine Learning Solutions, Q1 2017. This is an honor, and it underscores for us the value and positive business impact our analytic solutions continue to deliver.
These types of technology evaluations are really useful for organizations needing guidance as they enter into new strategic ventures. With plenty of attention on the promise of advanced analytics and machine learning, this report from Forrester is very timely. The report highlights:
- The Predictive Analytics and Machine Learning (PAML) Solutions market is “hot,” with Forrester forecasting “a 15% compound annual growth rate (CAGR) for the PAML market through 2021.”
- The true essence and core value of predictive analytics, stating “enterprises that can make probabilistic predictions about customers, business processes, and operations will have an edge over enterprises that can’t.”
- Machine learning is fundamental to artificial intelligence.
When you talk to data scientists and business leaders and hear their real-world stories, one begins to comprehend the possibilities that come with advanced analytics or data science. So, to compliment this Forrester Wave report, I thought I would share a few FICO case studies that demonstrate the value and competitive advantage predictive analytics can provide.
Airline Predicts and Solves Problems Before Crews Are Grounded and Customers Are Unhappy
Managing an airline that serves 100 million customers annually – with more than 3,900 daily departures during peak travel season to more than 100 destinations globally – is no small undertaking. And when regular operations become irregular, the task of keeping customers happy, flights on time and crews supported is daunting.
This is why airlines, like Southwest, have extensive contingency plans for irregular operations. Southwest has The Baker, a recovery optimization engine that turned the best practices of its irregular operations (IROPS) team into complex algorithms that solve potential challenges like maintenance problems or volatile weather, while minimizing the impact to passengers and crews.
Southwest can not only react to problems within minutes, but it can also get ahead of potential disruptions hours in advance and evaluate multiple scenarios. The Baker has helped Southwest improve on-time performance and customer satisfaction, while lowering flight diversions, tarmac delays and crew changes.
This is predictive analytics in action, and it has made a significant impact at Southwest, helping the airline gain advantage in a highly aggressive and competitive market.
Meaningful, Personalized Connections with Customers at the Grocery Store
Virtually any customer engagement can be improved with the power to predict. In the case of a major grocery retailer FICO works with, using analytics to deeply understand customers helped the retailer provide a highly personalized experience that encouraged loyalty and increased profitability.
The grocery retailer wanted to predict the propensity of a customer to purchase particular products and then prescribe the best offer. This required a multidimensional understanding of each of its 9 million loyalty program members, as well as taking into consideration business objectives and constraints.
With FICO’s advanced predictive analytics, the grocer was able to take its 380 billion possible offer combinations and deliver 20 tailored, relevant offers to each member every week.
Predictive Analytics Revolutionize the Energy Industry
Another great FICO customer example is SolarCity, a leading solar energy provider working to create an ideal way to store solar energy and then use it when demand is high. Electric demand can vary widely, based on things like changes in the weather, inconsistent supply or seasonal consumer patterns. With advanced predictive analytics, SolarCity is able to track and forecast complex scenarios for selling aggregated energy.
It’s fascinating that the same technology that is helping Southwest minimize flight delays and a grocery retailer deliver highly personalized offers to customers is also helping optimize a solar energy grid. Hopefully these real-world examples add a little perspective as you read the March 2017 Forrester Wave™ for Predictive Analytics and Machine Learning Solutions.
Imagine a scenario where banks offer their services digitally; not as an ad hoc feature but as a fully integrated mobile experience. A digital-only bank that allows customers to do everything on their smartphones, from opening a new account to making payments, settling credit card bills to resolving disputes, all without having to go to a physical branch.
If this vision sounds premature, then perhaps it’s time to update your view of what’s happening worldwide. This was the bold proposition offered by McKinsey & Company’s Sonia Barquin who presented at FICO’s Asia Pacific Chief Risk Officer Forum held this week in Thailand.
Banks worldwide are fighting back against fintech start-ups looking to cut their lunch with low-cost banking offerings. Barquin pointed out that some global banks are developing digital-only offshoots while others are bringing the philosophy and business model to their main bank offering.
Sonia encouraged the participants to be imaginative –and why not? Especially when she says her research shows that more than 80 percent of banking customers in Asia’s developed markets are willing to move part of their holdings to banks with a solid digital-only banking proposition?
While the financial benefits of the model for banks are obvious, the big question is, how do banks approach this massive undertaking? And especially the more traditional banks who have only just started to integrate many aspects of digital into their operations and offerings?
FICO’s decisioning technologies are clearly an advantage for banks considering an all-digital play. FICO has experience helping banks to quickly build digital offering which transform their business. Our experts at the CRO forum openly shared some great insights on how advanced technology can be leveraged in multiple areas of digital banking:
- Instant credit decisions: Consumers expect an ‘instant’ experience on their mobile phones. FICO has been pioneering credit scoring for more than 60 years and now has the technology to assess the vast majority of consumers with some basic credit information. This empowers banks to issue credit cards, personal loans and other credit in the mobile channel with confidence. FICO is also working on solutions for those outside the traditional banking system, who may have a smartphone. As part of its financial inclusion efforts it is employing a range of partnerships and technologies to grant credit based on alternative data.
- Pricing and loan optimization: FICO has been perfecting analytics that enabled banks to identify that sweet spot or optimal pricing for deposits, mortgages, car loans and other products. Finding the right balance between customer satisfaction and profitability needs to happen quickly when applications are happening online. FICO’s optimization algorithms and knowhow allow banks to make a variety of offers based on the customer’s risk profile, long-term value, loan term preferences and more.
- Detecting fraud in real-time: Less exposure to fraud and financial crime when you are identifying customers online and not in person is critical. FICO’s real-time predictive analytics has been used for more than 20 years to help catch credit card fraud. This same technology is now being incorporated into FICO’s cybersecurity and financial crime solutions, so banks can spot out-of-pattern and suspicious behavior.
Ultimately, the digital-only banking model will not only require a behavioral shift among Asian consumers, but the opportunity for banks will require the deep integration of data and analytics into banking operations. The key to eliminating risk in the business model is to enable banks to make consistent, data-backed, and analytically powered decisions, and ultimately make the smartest choices. Once that happens, the digital-only proposition for banks could be a real game-changer in Asia.
For many banks, KYC — Know Your Customer — means asking them how they intend to use a product, where the funds are coming from for their new account, etc. At the same time, the bank will check the customer against sanction lists, PEP (politically exposed persons) lists, and so forth.
It’s not enough.
Some hard evidence that it’s not enough came in 2016, when the so-called Panama Papers leak revealed that thousands of people worldwide owned a shell company in one of the countries covered. This was, needless to say, not something those individuals had disclosed to their banks.
Should banks care? Absolutely. Under the KYC requirements that are part of current regulations, such as the 4th EU Money Laundering Directive and the fifth pillar of the BSA, the bank needs to know the business of their customers. If a customer owns an offshore company, it’s quite possibly so that they can avoid taxes — or, even worse, so they can hide the flow of money, potentially illegal money.
While there are some legitimate reasons for offshore companies, an offshore company by its very nature poses a risk that needs to be investigated. But you can’t investigate something you don’t know about.
Banks that don’t know about their customers’ offshore companies face not only non-compliance, but reputational risk. No one wants to read that their bank is supporting tax avoidance or money laundering by the use of a shell company in an offshore.
How do you check?
Immediately after the leak went public, banks began a hectic operation to find and fix. I know banks that hired teams of expensive external consultants to manually check if any of millions of customers owned a company in Panama.
A manual check has multiple disadvantages:
- It’s costly and slow.
- It might not stand up to an audit — who can reproduce what has been checked?
- Worst of all, it’s a one-time approach. It will need to be repeated regularly, and intensively whenever further leaks are published.
- The data covers nearly 40 years.
- It links to people and companies in more than 200 countries and territories.
- It reveals more than 370,000 names of people and companies behind secret offshore structures.
Here’s how this works in the KYC process. During onboarding we automatically check if the potential client owns a company in an offshore country. If yes, we would raise a red flag and allow the financial institution to decide if they want to accept the customer. If accepted, the customer would be put in the high-risk segment, with enhanced due diligence. The customer would be monitored against very strict scenarios and thresholds.
If a customer doesn’t own an offshore company when they are onboarded but opens one later, our solution’s continuous customer screening against the ICIJ Offshore Leaks Database will automatically detect it and handle the case, following the risk appetite of the financial institution.
People are sneaky — sometimes a customer will open an offshore company and spell their name slightly differently to avoid the high-risk classification. We have an algorithm to catch that.
The Panama Papers and Bahamas Leaks are only the first step. Regulators will be demanding increased transparency into each customer’s business soon. That’s why we set up a future-proof integration — so that our clients can protect their reputations with an audit-secure, low-friction, scalable process.
The Panama Papers leak has strengthened KYC. We made finding out easy.