September 14, 2012

Optimization Software for Collections

We recently worked with a leading auto lending company to set up FICO Xpress Optimization Suite for their collections needs. Historically, collections has been a very subjective business left in the hands of the individual collector. We’ve seen more analytics being used to pick the right action based on customer behavior and degree of delinquency. This latest trend is optimizing allocation of resources and the collections actions based on the latest information, costs and expected results. Here are some key take-aways from this interesting use case:

Industry: Auto Finance

Company: Leading auto finance company

Business Challenge: Improve long term collections performance by allocating accounts to collections strategies in the way that makes the best use of available resources.

How FICO Xpress Optimization Suite Helped:

  • Analyzes risk and delinquency behavioral patterns.
  • Uses mathematical optimization to minimize losses and control operating expenses.
  • Selects the right treatment for each stage of delinquency while using number of available resources as a constraint.
  • Optimally allocates collections resources over time (headcount, collections technology, etc)
  • Seamlessly incorporates a test-and-learn experimental design capability within the optimization process

Results: Xpress Optimization Suite will enable near real-time adjustments to the process by providing daily strategy re-optimizations and redeployment. In addition, the company will gain business insight into the various tradeoffs within the collections organization, enabling them to right-size their collections resources dynamically.

August 22, 2012

Navigating the Hype to Find Real Business Value


Gartner recently released their latest set of Hype Cycle reports that cover a wide range of technology trends and where they sit on the road from trigger to productivity. These reports are a great way to get an early preview of emerging technologies and track how they progress from concept to mainstream practice. New items in the 2012 report include Big Data, the Internet of Things and Strategic Business Capabilities.

Decision management is a key component of many of the trends reviewed by Gartner:

  • Business Process Management – Agility continues to be a driver for BPM adoption and Business Rules Management is a primary component for delivering that agility. The BPM1 report shows that rules are becoming more mainstream but maturity and usage is still low in most companies, which means there is still a lot of opportunity for improvement. Leading organizations are going beyond the basics to focus on adding more intelligence.
  • Predictive Analytics– A key capability in the Analytic Applications2 and Big Data3 Hype Cycle reports is predictive analytics. Gartner’s findings include – “…the only reason to pursue any Big Data initiatives is to deliver against a business objective”. This report goes on to say that success requires asking the right questions and using the right technologies to get the answers. Fraud detection and claims analytics are specifically pointed out as examples.
Gartner’s overarching advice is for companies to develop a better understanding of the types of decisions they are making and that unutilized business data presents a significant opportunity for improvement. Overall we think their assessment reinforces FICO’s decision management vision and our advice is that the best investment you can make is to focus on automating and improving the decisions that drive the most business value.

1 Gartner, Hype Cycle for Business Process Management, 2012, John Dixon, July 27, 2012. 2 Gartner, Hype Cycle for Analytic Applications, 2012, Gareth Herschel, August 8, 2012.  3 Gartner, Hype Cycle for Big Data, 2012, Anne Lapkin, July 31, 2012

August 06, 2012

Using Rules to Upgrade Legacy Systems and Meet Regulatory Needs

The latest round of federal and state regulations has put tremendous pressure on compliance departments. As companies scramble to put new systems and procedures in place, it is no surprise that legacy COBOL systems are especially difficult to bring into compliance. And, by the way, the other reasons for wanting to modernize these systems still hold true. Legacy applications are a major stumbling block as companies seek greater agility in getting new products and policies to market, and they make it very hard to provide a timely and consistent experience across all customer touchpoints as Web and mobile channels drive the need for greater personalization at ever higher volumes. Companies are also worried about the increased risk of aging hardware and software, along with the declining availability of skills to maintain these systems.

We’re seeing renewed interest in how business rules management can help with this problem by providing a low-risk, step-wise approach.  It starts with using rules to more easily update key sections of the COBOL applications, and then uses the resulting rules projects to provide a smooth migration path to more modern platforms like Java and .NET.

Come learn more about FICO’s unique approach to building agility into legacy systems using Business Rules Management Systems. Enroll in our August 9 webinar.


July 25, 2012

Decision Management for Insurance Underwriting


We recently posted a press release describing how Lion of Africa is using FICO Blaze Advisor for their underwriting needs. Lion of Africa is one of the leading insurance companies in South Africa and is working to empower and transform South Africa’s financial services sector. This is a great example of how we’re seeing more of our customers use rules and analytics together. Here are some key take-aways from this interesting use case:

Industry: Insurance (commercial and personal lines segments)

Company: Lion of Africa

Business Challenge: Reduce costs and put more competitive offers into the market faster using a single rating engine.

How Blaze Advisor Helped:

  • Business User Control: Blaze Advisor provides the ability to create, modify, test and monitor underwriting decisions across Lion of Africa’s business, eliminating the cost and effort of supporting several different rating engines. This gives the entire underwriting team the flexibility and control to meet each customer’s needs swiftly.
  • Regulatory Transparency: Blaze Advisor simulates the impacts of new underwriting guidelines on Lion of Africa’s book of business and provides complete transparency to internal auditors and insurance regulators.
  • Deployment Streamlining: Blaze Advisor streamlines deployment of predictive models, adding another dimension of decision insight to Lion of Africa’s capabilities.

Results: With rules, predictive analytics and the addition of third-party data, Lion of Africa will significantly improve their existing fraud detection, prevention and conversion capabilities. Initially, Blaze Advisor will be used for personal lines underwriting, but going forward, it will help Lion of Africa advance its vision for a connected and customer-centric insurance operation.

July 20, 2012

Bullish Growth Projected for Analytics

Our radar picked up some interesting findings from IDC on the global business analytics market. After an impressive 14% growth in 2011, IDC forecasts continued growth at nearly 10% through 2016. The use of business analytics is becoming more mainstream, thanks in no small part to Big Data. As more companies learn that analytics can unlock the potential within the data, they are investing in new software solutions.

Although the economy continues to cause uncertainty, IDC predicts that demand for analytics will increase for the foreseeable future. According to the detailed white paper, this is partly because “compliance, security, fraud detection, and risk management requirements are driving demand for software ranging from reporting tools to analytic applications”. Visualization, experimentation and optimization are seen as technologies worthy of increased investment.

IDC ranked FICO #1 in the Services Operations Analytics category. We’ve held this position for the last 7 years thanks to our strengths in lending decisions, fraud prevention, next best marketing offers and many other decision management solutions. That, plus the fact that we’ve established ourselves as top players in the Advanced Analytics Tools and Performance Management categories, should make the next 5 years very exciting.

July 09, 2012

Engaging Business Users with Xpress-Insight

We recently gave James Taylor of Decision Management Solutions a tour of our latest release of Xpress, where we showed off the new visualization capabilities of Insight. James posted a “First Look – FICO Xpress Optimization 7.3” today on his blog and noted:

This kind of environment is important in optimization because the result of a model is often not readily explicable – the best answer is mathematically the best but the drivers for this are too complex to be readily understood. Being able to interact with the model, test the edges, try different scenarios and compare them all helps make business owners feel comfortable with the result – the optimization equivalent of impact analysis. Without this, business owners will not be active participants in optimization (just as impact analysis tools in business rules are essential for business user rule management).

I absolutely agree that it's critical to actively engage the business owner in the solution, and true to form, James is often able to say just what I'm thinking, only better. You can read his full post at

July 02, 2012

Turning Insights into Actions


As an analytic scientist, I know how exciting it can be to unearth a novel, actionable insight with the potential to improve the business. And I also know how challenging it can be to persuade business leaders to recognize the value, to the point where they are comfortable adopting such changes in their decision strategies.

Naturally, any line of business owner is concerned not only that the numbers are right, and that the insights are real, but also that any change to the existing decision strategy remains in compliance, and is palatable to the business.  The business owner thinks beyond the simple performance metrics, and brings valuable, subjective criteria that reflect their experience and business judgment. Is the proposed decision strategy intuitive? Are the treatments fair, easy to understand and sensible? Managing the balance between analytic insight and business acumen isn’t always easy.

But we're making it easier. The latest release of FICO Decision Optimizer reflects our experience with these important challenges. Analysts can now directly articulate key palatability criteria within the optimization problem, to achieve optimized action assignments across customer segments that still make great business sense. They can also compare new customer strategies against existing strategies to show the contrasting impact on business metrics, such as profitability and risk. Together, these new capabilities can help create a more immediate agreement that the revised strategies achieve better business benefits on multiple fronts.

To learn more about how Decision Optimizer 6.3 can help you improve your customer strategies, check out our website for more information.

June 26, 2012

Helping Banks Manage Risk, in Europe and Everywhere Else

Unless you’ve been off the grid for most of the year, you know that solvency and credit risk are dominating concerns for European banks and governments these days. Predictive models have long been vital tools for driving safe, effective lending decisions at the retail and commercial level, but recently the demand for greater transparency around these models has sharply increased.

At an IDC event held last week in Europe, FICO highlighted how banks can improve risk management, regulatory compliance and competitive advantage by strengthening their management of predictive models, such as those used to measure customers’ credit risk.

Last year, FICO released our FICO® Model Central™ Solution to provide a complete environment for managing predictive models in a reliable, automated and integrated way. It presents a management dashboard of overall model health, alerting personnel to performance degradation so they can take action before business decisions are adversely impacted. The solution can also accelerate the deployment of predictive models into a bank’s operational systems, which allows tomorrow’s decisions to better utilize the most recent behavioral shifts. An IDC Financial Insights white paper on this topic is scheduled for release in July, and you can also read our news release for more details.

While this isn’t a cure for what’s ailing our global economies, it can certainly illuminate the health of operational credit decisions and improve tomorrow’s actions.

June 22, 2012

How Banks are Taking Big Data Lessons from Retailers


The news is filled with stories about how companies are beginning to harness the masses of data swirling around us, thanks to the advent of social media and a wealth of other transactional data. The key challenge is to sift through the immense streams of information and arrive at something useful.

In a recent article (“Banks harnessing big data to analyse customers' shopping habits”), FICO’s own Andrew Jennings told Computing that financial institutions are taking cues from retailers. Each retailer knows, for example, a customer's product purchase habits and preferences within their own enterprise.  But they don't see what their customers do at adjacent or competing retailers. Banks have access to broader shopping patterns than retailers, and both parties stand to gain from a shared view of that information.

And so a novel partnership has formed. Banks and retailers are finding they can better understand and serve their mutual customers by utilizing their respective insights. With predictive analytics tools like FICO® Model Builder, companies can leverage data to create better decision strategies to manage credit risk, reduce fraud, and in this case, increase customer loyalty. Chalk one up for effective collaboration.

June 14, 2012

Finding Value in Social Media Data


Everyone is looking for new techniques that will help them leverage Big Data. One of FICO’s scientists, Xing Zhao, recently married a popular collaborative filtering algorithm, matrix factorization, with our powerful segmented ensemble models, in FICO Model Builder. The result was strong enough to earn him a top 5 finish in the 2012 Knowledge Discovery and Data Mining competition (KDD Cup).

This year’s competition attracted over 900 teams of high caliber scientists, academics and students, as well as renowned industry experts. Placing in the top 5 is admirable. What’s even more impressive is that Xing did it as a solo effort, in his own spare time, while competing against highly focused academic teams.

KDD 2012 is a top forum for presenting and discussing academic and industry advancements in data mining, data science, Big Data and predictive analytics. This year’s KDD Cup competition challenged participants to create a recommendation system to predict whether a user would follow another user in Tencent Weibo, a Chinese micro-blogging site. Tencent provided the largest and most complex data set ever made available in a KDD Cup contest.

“The Segmented Ensemble module in Model Builder was vital to my solution, as there were many interactions between the variables and it was important to capture those interactions to make the model more predictive”, said Xing Zhao. In addition, he says, “This challenge was a great way to show that Model Builder works well with very large data sets and that scorecard ensembles can achieve great results quickly.”

Congratulations Xing for tackling such a big problem, and showing that scorecards can be great for more than just credit risk.

Search Site



  • enter your email

Upcoming Events

  • FICO Tools & Analytics User Forum 2012
    BERLIN: September 11-12, 2012 LONDON: September 18-19, 2012 Gain new insights for improving business performance through advanced analytics and decision management tools.