Regardless of the industry vertical in which they operate, financial services institutions stand to make -- or lose -- a lot of money based on their ability to analyze past occurrences to predict future events. Traditionally, firms attempted this through planning exercises. They'd collect data, study trends and make one-time presentations to company executives.
But as data volumes continue to rise, firms are adopting increasingly complex predictive analytics models to analyze the large data streams and anticipate future behavior and events. And, instead of using these models on a year-to-year basis, companies are employing them day to day or, in the case of Wall Street, in real time. The increased prominence of these sophisticated tools and systems across the financial services industry suggests that predictive analytics have become "the next big thing" -- a hot technology with the potential to transform the business.
By leveraging predictive analytics and pattern analysis technologies, financial services firms are able to understand their customers, their operations and their markets in greater detail. Perhaps more important, they are able to identify and react to trends as they emerge, staying ahead of the curve -- and the competition.
A Customer Focus
In insurance and banking, predictive analytics often are used to segment valuable customers and anticipate the types of products and services that will attract their new business or increase their loyalty. "I see predictive analytics becoming more pervasive around the operations of financial services companies, beginning with customer focus -- as we go from a product-based industry to a customer-focused industry and from a product profitability standpoint to a customer lifetime value ambition," says Marty Ellingsworth, president of innovative analytics at ISO (Jersey City, N.J.).
At Branchville, N.J.-based Selective Insurance ($4.8 billion in total assets), predictive analytics are leveraged to improve pricing and identify and retain the most valuable customers, according to Daniel Bravo, SVP of Selective's strategic operations group. "The models aid the decision-making process in the field to get to the right pricing granularity for the right risks," he says. "That translates into both new business and renewal."
Selective began working on predictive models in early 2005 and was leveraging predictive analytics in business decisions by 2006, Bravo continues. The carrier worked closely with Deloitte Consultingon the initiative, with much of the development occurring in-house, he adds, declining to name Selective's other technology partners.
Bravo explains that the insurer has underwriters positioned in the field -- inside the offices of independent agent partners -- who make decisions around the business the company will and will not take on. "Through the use of predictive analytics, we are helping them make decisions with even better information," he says, adding that Selective employs predictive models to analyze data collected via policy applications to determine the quality of a given risk and how it likely will perform for the life of that customer's account.
A key part of the success of Selective's predictive analytics effort, according to Bravo, was the complete integration of predictive analytics with personal and commercial lines operations, rather than launching predictive analytics as an isolated, bolt-on solution. "One of the advantages that Selective has is our ability to bring [predictive analytics] into the regular insurance operations of the company and not disrupt those operations while still taking full advantage of the guidance and granularity the models provide," he says.
Bravo adds that ensuring that employees embraced the technology was the most important part of the transformation. Use predictive analytics to "offer guidance," he advises. "Present it as a tool and [implement] it in a way that people can take advantage of it without being Ph.D.s in anything."
Immersing the company in predictive analytics, rather than stapling the concept to the side of the enterprise, also was a key to success at Wachovia ($720 billion in assets). In part to facilitate the use of predictive analytics in building new customer relationships, the Charlotte, N.C.-based bank realigned its marketing group to include several other divisions, such as insight and innovation, e-commerce, and customer loyalty and satisfaction.
"We are aligning under more predictive analytics with more thought and resources dedicated toward it," relates Dan Thorpe, SVP of statistics and modeling at Wachovia. "We've put together all the groups that circle around that into one division."
Creating a Lifetime of Value
According to Thorpe, Wachovia has developed customer acquisition and target models, as well as models for attrition, using the SAS Analytics solution from the Cary, N.C.-based vendor. By combining those predictive models, the bank creates what it calls a customer lifetime value model, which helps it decide for which geographies and channels it should increase or decrease advertising spend.
"We're looking at long-term value to the bank rather than just pure acquisition," Thorpe says of the lifetime value concept. "We've worked really hard to develop the infrastructure to really be fact-based, quantitative-based and predictive analytics-based to understand return on our investment."
Wachovia also uses predictive analytics to increase the value of its existing customer relationships, having applied its models to develop customer lifetime values for the 13 million households in its retail bank, according to Thorpe. Rather than simply recommend new products to those households in a blanket fashion, Wachovia determines which households are most likely to respond to specific offers and which products offer the greatest profit opportunities. "We're taking that customer lifetime value knowledge into how we actually touch a customer," Thorpe relates.
Because predictive analytics enable institutions such as Wachovia to tailor products to specific customers' needs, similar innovations will become increasingly important in differentiating financial services firms as competition increases, according to John Lucker, a Hartford-based principal and national practice leader for advanced quantitative solutions with Deloitte Consulting. "It's not a one-size-fits-all world anymore," he says. "People demand customization." Further, Lucker adds, in the chase for higher investment returns, customers are more likely than ever to move their money from one institution to another, making identifying and retaining the most profitable customers more challenging and more important than in the past.
"Once you find these people, you have to do something to make them stay. It's not just finding them; it's reacting to their needs," Lucker comments. "Predictive analytics ties into finding the people and then using more traditional marketing efforts to get at, from a segmentation perspective, what it is they want and then catering to those needs."
While predictive analytics can be used to identify the most-desired customers, the technology may be equally valuable when used to identify the least-desired customers -- those likely to commit fraud.
For insurers, predictive analytics can be leveraged during the claims process by finding commonalities among new, incoming claims and historical claims that may indicate fraud. When those common elements are uncovered, a carrier's special investigations unit (SIU) can trigger an investigation.
Wachovia's Thorpe says there's an opportunity to identify bank fraud using predictive analytics and pattern analysis as well. But particularly in banking, it's vital that fraud is identified immediately. "It has to be very dynamic," Thorpe explains, pointing out that someone with a stolen debit card will try it once to see if it works. If successful, they'll make as many transactions as quickly as possible to max out the card. "We have to be able to catch it the first time to prevent those repetitive ones. You have to be that quick," Thorpe continues. "To identify fraud, you have to do it instantaneously to prevent it from happening elsewhere."
While pattern analysis, or anomaly detection, has been used to detect fraud in the credit card industry for some time, lately it also has been garnering increased attention on Wall Street. Hacking against financial firms is at an all-time high, and perpetrators increasingly are hijacking customers' accounts to buy and sell stocks fraudulently online. According to security experts, pattern analysis can be a big help in detecting such anomalies.
The method involves running server-based processes in the background that authenticate users based on what types of transactions they are executing and/or from where they are logging on. The information is then compared with a profile of what is expected of each user. If an individual's behavior is out of range with what is expected, the transaction can be immediately flagged.
"If constantly kept running in the background, these systems can be highly effective at keeping criminals out," says Gartner VP and distinguished analyst Avivah Litan. "They are not intrusive to legitimate users unless the user's activity is suspect."
One firm that reportedly is planning to adopt pattern analysis technology to protect its network from unauthorized access is JPMorgan Chase. The bank already has been using the technology in its retail banking services to track credit card fraud. But, according to industry insiders, it is now preparing to use the technology for its securities services, too. JPMorgan Chase declined to comment.
Securities regulators also are implementing pattern analysis technology, particularly under its most evolved form, complex event processing (CEP), to help stop insider trading. CEP uses analytic techniques such as event streams processing, event correlation and abstraction to detect complex patterns among many events and relationships between events, such as causality and timing.
"Regulators might be looking at stored historical data and real-time data," explains Bill Hobbib, VP of marketing at CEP provider Streambase. "Then you can compute all the real-time trades taking place. As you're monitoring each trade you might be looking at the names [and] times of month with respect to quiet periods when people are not allowed to trade."
The U.K.'s FSA started using Progress Apama's (London and New York) Event Processing Platform to monitor transactions and detect insider trading and other market abuses. Previously, the U.K. watchdog monitored hundreds of scenarios that could indicate trading abuses but was forced to analyze the data after the fact. But by the time abuses were uncovered, the market had long been moved by them. Now the FSA can detect abuses virtually in real time.
Analytics and Compliance
Financial firms' compliance officers also are tapping CEP to assess potential trade events and check them against compliance requirements with the aim of avoiding costly fines. "The interest is particularly around smart order routing and monitoring order routing to show compliance in real time," explains Joe Rosen, currently president of RKA, a New York-based management consulting firm that advises on the use of technology in the global capital markets, and the former managing director of trading technology/head of technology marketing at the New York Stock Exchange.
Meanwhile, with the capital markets becoming increasingly electronic, and multi-asset and multi-geographic trading now the norm, the biggest demand for CEP technology currently is around algorithmic trading. Since CEP streams large flows of data from disparate sources and analyzes it in real time, firms that use the technology are able to trade faster than ever before. "A lot of people are overwhelmed by the speed of data coming out, particularly in equities and options," explains Brad Bailey, senior analyst with Boston-based Aite Group. "That is putting a tremendous amount of strain on infrastructure."
In the midst of today's global liquidity crunch and constantly evolving markets, investment banks are using CEP technology for real-time liquidity management. Until now, most banks managed liquidity manually on an intraday basis in the middle office but were unable to readily determine the actual positions of the bank at any given time during the day, according to Jeff Wootton, VP, product strategy, at Chicago-based Aleri, a provider of event streaming processing technology for financial institutions.
With CEP, however, they can see exact positions down to the transaction level and across the bank, as well as apply predictive analytics based on historical data, Wootton says. "This provides banks with a fast and accurate way to determine how much liquidity they need to borrow, if any, ultimately reducing the costs."
Aleri just released LMS 5, the latest version of its Liquidity Management System, as well as a new Collateral Management Module (CMM). The CMM provides up-to-date enterprise inventory liquidity-centric views of liquid assets positions for day-to-day and crisis liquidity management purposes, and can trigger actions to mobilize these liquid assets, according to Wootton. CMM also provides detailed stock information for use in liquidity risk reporting.
Among those using Aleri's platform for liquidity management is Brussels-based Dexia Bank Belgium. "To calculate the consolidated liquidity ratios, we need to be able to collect important data, such as the liquidity and securities positions, from the different Dexia entities into one central system," explains Johan Evenepoel, global head of repo, cash and liquidity, Dexia Group.
Aleri's clients also include London-based Barclays Bank, and Commerzbank Corporates and Markets (CBCM), which has leveraged CEP for automated pricing and market making, taking in market exchange rates, applying the bank's proprietary algorithms and then calculating prices in real time.
Overall, Aite estimates that revenues for CEP-related products will quadruple in the next two years, reaching $460 million by 2010. The broader event processing (EP) category -- which comprises a range of applications that facilitates the aggregation and processing of event data -- will reach $1 billion, Aite says.
"[CEP] is the next big thing," contends RKA's Rosen. "In the capital markets where you have need for lots of data, you have to have this kind of technology."