Big Data Changes the Analytics Paradigm

Big Data is a hot topic today that stems back to the early days of high-performance computing and parallel computing, which I worked on during my time in theoretical physics at Duke and Los Alamos. These days, Big Data tools facilitate the ease in applying these concepts. Interestingly, much of...

Making the most of score differences

I previously blogged about how a consumer’s FICO® Score may vary from one CRA to another, due mostly to differences in data reported to each of the credit reporting agencies. This begs the question: when pulling scores from more than one CRA, which should be used for credit decisioning? The...

Celebrating fraud innovation

I'm proud to announce that FICO® Falcon® Fraud Manager 6 Analytics was named a finalist in the CONNECT Most Innovative New Product Awards, in the software category. This accolade was driven by the analytic innovations that I often blog about here, including: Adaptive Analytics, which are reducing account false positive...

Score differences across credit bureaus reflect true data differences

I recently had the pleasure of speaking at the Philadelphia Federal Reserve Bank’s Community Development Studies and Education Department’s conference “The Impact of Workout Options on Borrower’s Credit Reports and Scores.” The conference was well attended by regulators, lenders and consumer credit and housing counselors. FICO’s research on the score...

Webinar: Best Practices in Analytics and Model Validation

Next week, FICO will host free webinars that share best practices in analytics and model validation. With the proliferation of models used in financial services, and today's tightly regulated and volatile markets, organizations must reassess how well models are being strategically applied and how well they're being managed. In addition,...

Rising Stars v. Fallen Angels: Insights into changing credit behavior

FICO® Score migration patterns offer significant insight into consumer credit behavior. There's much to be learned by exploring these patterns—particularly whose score went up, whose went down and whose stayed the same—during dynamic economic times. We've just published new research analyzing score movement during recent economic volatility, from October 2006...

Recession causes FICO® Score swings

Last month I posted that the national distribution of FICO® 8 Scores has had two major shifts during the recession. Some readers were puzzled that the observed shifts weren’t significantly larger, in light of the sour US economy. Actually, what appear to be small national shifts are quite dramatic changes,...

Fighting Enterprise Fraud

Increasingly banks are looking to leverage the full breadth of data related to customers to make better decisions, and fraud is no exception. There is a strong desire to break down silos, so fraud/risk behaviors in one area of the customer’s interaction with the bank can be utilized in other...

New Analytics for Emerging Payments

Payment cards are changing. Whereas a plastic card used to access a single funding account, now we increasingly see cards—and very soon, mobile phones—that can access multiple funding accounts. This trend not only increases personalization options, but also fraud detection capabilities, if you leverage a cardholder’s history of what funding...

FICO® Scores Shift During Recession

A comparison of nationwide FICO® Scores from 2005-2011 illustrates that score distribution has remained relatively stable at a national level. However a close look at the numbers suggests that U.S. lenders have experienced two distinct phases of consumer credit risk in the recession thus far. Early in the recession, lenders...

Closing the Gap on Fraud Model Degradation

Fraudsters are continually adjusting their strategies to circumvent fraud detection systems. In my last few posts, I've been discussing how adaptive analytics are built to counter this problem. Because of this, the latest version of FICO™ Falcon® Fraud Manager leverages adaptive analytics. The adaptive model adjusts the base neural network...

Strengthening conventional fraud detection

Financial institutions are always looking for ways to combat newer fraud schemes—schemes that arise between fraud model developments and are not well-represented in the historical data. As I discussed in a recent post, one way to boost performance is to add analytics that are adaptive or self-learning. Deploying adaptive models...

How can fraud models combat new tricks?

The fight against payment card fraud resembles an arms race. Card issuers are deploying ever more sophisticated anti-fraud measures, and fraudsters are continually evolving strategies to evade those measures. Typically, issuers rely upon neural network fraud models trained on huge historical datasets to recognize recurring fraud patterns and reduce fraud...

Defining what makes a “good” model

Central to developing and evaluating an analytic model is the definition of what constitutes a “good model.” At FICO, we view it as the dimensions of good. Let’s take fraud models as an example. What makes one model look high-performing may be misleading if that performance degrades quickly. A model...

How do FICO® 8 scores change the score distribution?

One reason there are more consumers today with scores at the high and low ends of the 300-850® score range for FICO® Scores is that we have improved the FICO scoring models. The newest version — the FICO 8 Score — is a stronger predictor of future credit risk. Because...

FICO® Scores drift downward

- Posted by Tom Quinn, FICO® Score Product Manager A comparison of nationwide FICO® Scores from 2008, 2009 and 2010 indicates that consumer credit risk has increased over the past two years. The distribution of FICO Scores drifted down slightly on FICO’s 300-850® score range and score performance shifted in...

Welcome to the FICO Banking Analytics blog — why are we here?

- Posted by Tom Quinn, FICO® Score Product Manager Today's bankers are information junkies. We should know - as the creators of the FICO® score and other predictive analytics solutions, we are constantly providing our clients with new research and insights into credit trends. We created this blog to share...