All posts by Andrew Flint

Analytics & Optimization Choosing the Right Analytics: Text Analytics and Semantic Scorecards

Oct082013

We’re back, with a new edition of our series on choosing the right analytics for the job.  Today’s situation: data is in ample supply, but too much of it feels beyond the reach of traditional analytic algorithms.  By volume, 80 percent of the data out there is untapped and much of it is unstructured – too messy and just too complex to crack open. Regression models thrive on numbers and numbers only, so data in the form of customer call logs, on-line support chats and detailed case records are just irrelevant noise to them. And when the source information doesn’t “fit” neatly into a lot of our tools, we often write it off as unusable or meaningless. But the right tools can bring those large, untapped troves of textual information into reach.  Text analytics represent a large body of techniques that can help us improve on what we know, and even offer entirely new insights into our customers’ behaviors and needs. In particular, supervised text mining techniques can help us learn which terms, phrases and content connect...

Leave a comment

Analytics & Optimization The Big, the Raw and the Complex: Challenges in Big Data Analytics

Aug272013

“A bounty hunting scam joins two men in an uneasy alliance against a third in a race to find a fortune in gold buried in a remote cemetery,” reads the plot summary of 1966's quintessential spaghetti western, The Good, the Bad and the Ugly. The state of Big Data Analytics can feel like a different kind of spaghetti western, this one titled The Big, the Raw and the Complex. The Big In this version of the story, we’re still searching for buried gold — actionable insights about what can delight our customers and improve our bottom line — but instead of tracking down one unknown grave in one unnamed cemetery, we’re inspecting all the blades of grass on every hill and dale in our data landscape. If that survey contained a petabyte of information (one million gigabytes, or nearly 5,000 days of high definition video), then today’s high-end PC would require about 3 months just to read through that data, one time. And while Big is good — more data gives us a chance to build stronger, more refined models — Big can be pretty tough when...

Leave a comment

Analytics & Optimization Bullish Growth Projected for Analytics

Jul202012

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...

Leave a comment

Analytics & Optimization Engaging Business Users with Xpress-Insight

Jul092012

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...

Leave a comment

Analytics & Optimization Turning Insights into Actions

Jul022012

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...

Leave a comment

Analytics & Optimization Helping Banks Manage Risk, in Europe and Everywhere Else

Jun262012

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...

Leave a comment

Analytics & Optimization How Banks are Taking Big Data Lessons from Retailers

Jun222012

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...

1 Comment

Analytics & Optimization Finding Value in Social Media Data

Jun142012

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...

1 Comment