FICO

Recently, congressional staff requested a briefing from FICO on how our analytics are tackling the opioid epidemic – an issue that, despite pervasive gridlock in Congress, has become a priority for both Democrats and Republicans. Our experts welcomed the opportunity to share their experiences. We believe that the increased use of analytics can play a pivotal role in confronting this challenge. Opioids are a class of drugs that include heroin as well as pain medications such as codeine, oxycodone and morphine. In 2014, according to the Centers for Disease Control, more than 28,000 people died from opioids – a number greater than the deaths from traffic accidents that same year. And the opioid problem is getting worse, with increasingly more deaths involving fentanyl and other synthetic opioids. The House and Senate recently approved a bill addressing the opioid crisis by nearly unanimous votes. Though both parties wanted additional provisions, the compromise bill is a rare showing of bipartisan cooperation during a particularly divisive time on Capitol Hill. The Comprehensive Addiction and Recovery Act of 2016 expands educational resources and strengthens prevention, treatment and recovery efforts by providing medical professionals and law enforcement with more tools to assist people suffering from drug addictions. On July 22, President Obama signed the bill into law. When congressional staff reached out to FICO, their goal was to learn more about how analytics are being used to combat the opioid crisis. FICO introduced behavioral analytics to combat healthcare fraud more than 15 years ago, leveraging learnings from our success in using analytics to significantly shrink fraud losses in the payment card space. As our experts explained to congressional staff, today our analytics identify and score anomalies associated with opioid fraud, waste and abuse among a full range of stakeholders: pharmacies, prescribers, members and even employees. FICO also illustrated how we can leverage our link analysis tool to discover true identities of opioid abusers through social network relationships between people, entities and activities. This is especially helpful in scenarios where an individual is “emergency room” shopping for opioids by using false identities. As our experts imparted, using the right analytics can be a huge part of the solution to this global epidemic. However, there are also disincentives in the system that need to be resolved. For example, payers for self-insured entities, representing 60% of the employer group healthcare market, get compensated for processing transactions, not for identifying fraud, waste and abuse. Clearly, there is more work to be done. As policy leaders continue to identify the most effective methods for combating the growing opioid problem, we expect the use of analytics will receive even greater emphasis as part of an overall solution. The post Using Analytics to Attack Opioid Abuse appeared first on FICO.

Fees are an important and often misunderstood part of checking accounts. Management of checking account fees is often scrutinized by regulatory agencies and the public. A review of the CFPB's Complaint Database and the CFPB’s 2015 Consumer Response Annual Report shows the impact of poorly managed fee programs on consumers and the banking industry. How do you know if you are effectively managing fees? Ask yourself these questions: Are your policies easy to understand and consistently implemented by your front-line personnel? Is your fee waiver approach based on relationship and risk, or do you have a one-size-fits all approach to fee waivers and fee reversals? Are your policies easy to understand and consistently implemented? Let’s discuss the “easy to understand” part of this question first. The fee policies in place must be easy to understand for your customers as well as your staff. Your front-line employees should understand the fees that differentiate your products and how they compare with your competitors. This piece of the equation is easily managed through education and training of all levels of staff. Consistently implementing fee policies is where the challenges often arise. In a perfect world, fee waiver and fee reversal policies would be well-documented with defined qualification criteria based on risk, profitability and other data-driven metrics. Any exceptions to the fee policy would be documented and tracked for future policy management and re-development. Unfortunately, many organizations are not managing in this perfect world. The decision whether or not to waive a fee is often made arbitrarily, and can be based on personal relationships and biases, rather than customer risk, value and the banking relationship. These decisions introduce risks – reputational, regulatory and relationship – to your organization. Risks that need to be mitigated. Although consistent fee management can be challenging, the perfect world is achievable with the introduction of analytically driven strategic decisions – decisions that can be automated for consistent implementation, and still allow for exception processing and tracking. The perfect world – managing the customer holistically and valuing the customer relationship – will lay the foundation for effective and consistently implemented fee management policies. Do you have a one-size-fits-all approach to fee waivers and fee reversals? Let’s start by describing the difference between a fee waiver and a fee reversal program. Fee waiver programs are often product-driven. For example, Checking Account A allows for two overdraft fee waivers annually. In a best-in-class solution, a customer would be notified each time a fee was waived as part of the program, and the fee would not post to the account because it was waived prior to being assessed. A consumer would be educated to understand that any overdraft incurred after the two waived fees would be charged to their account. Fee waivers represent a proactive management of fees. The opposite of this approach is the fee reversal. In a fee reversal, the fee is assessed to the customer and reversed as part of a bank-initiated or customer-initiated request. One of the most common types of fee reversals occur when a customer calls up and requests that a fee be removed, and the organization makes the determination and either reverses the fee or lets it stand. This is a reactive approach to fee management. Developing an approach that is consistent, repeatable and analytically driven can enhance a one-size-fits-all approach across fee waivers and fee reversals. This can be managed in an automated manner and still provide the flexibility needed in today’s environment. Fees are a critical revenue driver for checking accounts. They can also be a major cause of dissatisfaction and attrition. FICO is here to help you balance these conflicting goals and manage fees effectively, read more here on FICO.com. The post Getting Checking Fee Management Rig

Have you got a handle on IFRS 9, CECL and BCBS 239? If not, and it all just sounds like regulatory alphabet soup, it’s time to familiarize yourself with these critical acronyms. All three requirements highlight the need for financial institutions to ensure the quality of their risk data. Aggregation and effective use of this data are becoming key to meeting new compliance challenges, not to mention an opportunity to derive additional business value. So what specifically are all these acronyms? Here’s a quick overview: IFRS 9 – IFRS 9 is a new international accounting standard that was adopted by the International Accounting Standards Board (IASB). In the aftermath of the financial crisis, the IASB believed that the accounting standards in use (specifically IAS 39) failed to highlight the losses that firms would face because they were based on past events. With the adoption of IFRS 9 beginning in 2018, financial institutions will have to model future events and calculate provisions based on expected, rather than current, incurred loss events. My colleague recently wrote a blog post on IFRS 9, if you are interested in more details. CECL – While IFRS 9 began as a joint project with the Financial Accounting Standards Board (FASB), which promulgates accounting standards in the US, the two organizations ultimately developed separate standards. FASB’s Current Expected Credit Loss (CECL) standard adopts a similar approach to IFRS 9. It requires lenders to forecast all potential losses for the expected life of a loan at origination and, based on that, set aside reserves upfront for those losses. However, CECL differs from IFRS 9 in that it requires provisions based on lifetime loss for all impacted assets, not just those that are under-performing or non-performing. The final CECL standard was issued on June 17, 2016. It will be effective in 2020 for Securities and Exchange Commission registrants, and in 2021 for all others. BCBS 239 – Rounding out the alphabet soup is BCBS 239. Another lesson learned from the financial crisis was that bank’s IT and data architecture were inadequate to support the management of broad financial risks. The Basel Committee of Banking Supervision (BCBS) developed BCBS 239 as a set of overarching principles that impact efforts related to the new accounting standards, as well as activities such as stress testing. The primary goal was to ensure that global systematically important banks (G-SIBS) strengthen their risk data aggregation capabilities and internal risk reporting practices. In doing so, these institutions would enhance their risk management and decision-making processes. The regulation required impacted banks to align to a set of principles of effective risk management and governance by January 2016. These new standards, coupled with other compliance requirements such as stress testing, reporting and monitoring, all place an emphasis on effectively collecting and managing risk data from disparate sources in order to meet growing regulatory scrutiny. The resulting challenges were discussed at length during several regulatory compliance sessions in late April at FICO World 2016, our premier client conference. As a senior leader at a large multinational financial institution asserted in his presentation, compliance should not be the only goal in developing a strong risk data aggregation and reporting system. Significant business value can also be derived in the form of: better data quality, reduced costs in data management, enhanced operational agility as model complexity is reduced and better-architected applications for analytics. Of course, FICO subject matter experts were quick to assure FICO World attendees that we have comprehensive solutions that will enable them to address these challenges, whether it is loss forecasting models, impairment calculation tools, stress testing capabilities, or risk data aggregation and reporting. The big takeaway, however, remains that compliance is becoming more

Last month the President of the San Francisco Federal Reserve Bank addressed the LendIt USA conference here in San Francisco. He talked about “unintended consequences” and the role regulators play in protecting wider economic interests. “I am excited for the changes to come, and I see the potency of the possible,” said John C. Williams. “But for fintech’s potential to be met, we need to make sure we don’t reinvent or exacerbate shortcomings that have plagued our financial system thus far. In that regard, well-designed regulation protects consumers, fosters inclusionary rather than exclusionary practices and enhances fairness and resilience of the financial system should help rather than hinder fintech’s contribution.” Since that speech, trouble with marketplace lenders such as Lending Club has led many in the industry to say the fintech bubble is bursting. Whether or not that turns out to be the case, it’s worth exploring this issue: What are the unintended consequences that could arise from new ways of assessing risk? A large body of regulation has built up in the US that provides protections to consumers around use of data, underwriting criteria and marketing practices. Fintech business models that evade this regulation could well have unintended consequences — negative impacts on consumers and the overall health of the financial system. While fintech compliance with regulations is important, poorly designed or misapplied risk models can have significant unintended consequences. In the lending industry, poor risk models lead to poor decisions that lead to poor business results — and poor treatment of customers. Is there something more at work than selection bias when we see delinquency rates in China for P2P lenders in the 25% range relative to card rates at the banks in the 3-5% range? At the very least it would indicate the need for some new risk tools to guide underwriting policy because costs of this sort are not sustainable. When you have a decision to make about whether to lend money, getting that decision right is important for the borrower, the lender and its shareholders or investors, as well as for the economy at large. The decision must be sound, and so must the risk model guiding it. Data scientists have ways of ensuring that the models they build have integrity. What does that mean? Integrity means it was “done right”. In the analytics world, we often use the words stability and robustness, meaning the model was built right so it performs well over time. Something that needs a lot of rebuilding lacks integrity – just like a bridge! Ideally, models need five key attributes, predictive power, coverage, fairness, transparency and the ability for the consumer to dispute the answer. (This is to avoid the classic “computer says no” situation familiar to anyone who watched Little Britain!) It isn’t always possible to achieve all these things at once or to the same degree as is possible with conventional application and bureau data. It will be doubly hard to achieve this standard if your models have opaque variables, relying heavily on variables that could be easily gamed or are otherwise non-robust (thus necessitating frequent model fixes) or are so complex that you can’t explain them or diagnose what has gone wrong. And that is the danger with many of the scoring models being touted by fintech companies. Transparency is a little harder to address, because that really does become part of the regulatory framework as well as the maturing of the market. Here in the US we have long had rules that enforce transparency in credit scoring, beginning with score reason codes, and we have a vibrant direct-to-consumer market that has raised people’s awareness even further. At FICO we launched the FICO Score Open Access program that gives 150 million consumers access to their FICO Score through their billing statement or online banking site. Transparency is something we should strive for in most credit markets, although we have to

Last week at FICO® World 2016, the Decisions Conference, IT leaders such as CISCO, attended, participated and sponsored our event.  After deploying Cisco technology, we realized that our customers could benefit from knowing that our technology works well together. When business and IT are aligned, outcomes improve. Cisco knows IT and Cisco Unified Computing System (UCS) servers are installed in more than 75 percent of the Fortune 500 companies. To that end, the FICO® Decision Management Suite (DMS) is now certified on Cisco UCS and available in the Cisco Marketplace. FICO and Cisco want to help organizations of all sizes tackle IT complexity by delivering a tested and validated solution to our joint customers. FICO uses Cisco UCS, Cisco has validated the FICO Decision Management Suite on its servers and now you can deploy it on Cisco UCS with confidence. Learn more about the FICO Decision Management Suite on Cisco UCS solution here. You can also visit the Cisco partner page on our Partner Portal here. The post Tackle IT Complexity with FICO and Cisco appeared first on FICO.

Artificial Intelligence is one of today’s hottest topics, in academia and in business. Here’s how the two worlds can intersect. One of the most refreshing parts of my job involves keeping up with data science developments at leading universities. Occasionally I have the opportunity to “parachute in” to see faculty and student projects first hand, and talk with the researchers behind them. This is exactly what I did last week in New York City at Columbia University’s Data Science Day, a one-day jam that featured “lightning talks” (short, TED-like presentations) from Columbia professors, as well as dozens of student exhibits. One of my favorite presentations at Data Science Day was by Professor Julia Hirschberg, chair of Columbia’s Data Science Department and an alumna of the venerable Bell Labs. Professor Hirschberg’s lightning talk, “Applications for Detecting Emotion in Speech and Text,” was about using AI techniques for sentiment analysis. She noted that, “Identifying the emotional content of written and spoken language is increasingly useful in business, medicine and security…. Large data sets of text and speech can be used to train systems to detect consumer reactions to products and services … to diagnose medical conditions such as depression, and identify deception in a wide variety of … settings.” Professor Hirschberg’s findings were intriguing and well presented. Today, we use speech analysis in FICO Engagement Analyzer, helping organizations collecting debt to maintain compliance and collection effectiveness. Engagement Analyzer uses sophisticated text and speech recognition analytics to index, search, analyze and report content from collector interactions. It is interesting to consider how an additional dimension of analysis, of emotion, could someday enhance products like Engagement Analyzer. Future scientists I was also enthused to see a terrific turnout at Data Science Day. Hundreds of people packed into Roone Arledge Auditorium on the Columbia campus. These young researchers are looking to data science to be the tool that helps solve some of the world’s most complex challenges, to create a better society. The large turnout reminded me of another informal data point I’d recently seen, in an article by analytics guru Gregory Piatetsky. As indicated below, data science and analytics aren’t just hot topics of study at Columbia; programs are springing at universities across the country. Piatetsky’s article listed more than two dozen analytics programs at US universities. Source: KDnuggets These anecdotal data points, along with the spirited conversations I enjoyed at Columbia Data Science Day, made me glad that artificial intelligence study is going strong on campuses everywhere, and part of the common language of hundreds of thousands of future data scientists. I’m now on Twitter. Come follow me @ScottZoldi. The post AI on Campus: The Next Generation of Data Scientists appeared first on FICO.