All posts by Alan Ikemura

In today's competitive market, expanding your organization’s customer base can be a daunting task. Limited marketing budgets, high acquisition costs, and the pressure of financial inclusion initiatives can lead to poor response rates and make it challenging to reach the right consumers. If your prescreen policies are too conservative, you might miss out on valuable opportunities. On the other hand, overly lenient policies can lead to wasted resources on uninterested consumers. So how can you strike the perfect balance and ensure your marketing efforts are both effective and efficient? Challenges for financial institutions Research shows that 55% of financial institutions reported building response models that don’t make it to production.[1] This can lead to wasted time and effort as employees work to build models that are never used, which can have a severe negative impact on organizations’ productivity and team members’ morale. In addition, most organizations are not well-equipped to conduct their own analytics, citing limited access to data for response modeling and challenges with incorporating models into a comprehensive campaign strategy. Many institutions are unsure of who to send offers to, which channels to utilize, which offers to send, or how often to send them. To effectively reach consumers, financial institutions need to: Easily access and understand the right data Quickly move to production Deploy models with little to no friction Monitor and refresh models to avoid deterioration Maintain regulatory compliance  So how can your organization accomplish all this to ensure you’re reaching the right consumers with your offers? Ascend Intelligence Services™ Target Ascend Intelligence Services Target (Target) is a cutting-edge solution designed to help businesses target the right consumers with precision. This service leverages custom response models and optimized prescreen strategies to enhance response rates and maximize revenue. At the heart of Target are custom response models developed by industry experts using advanced machine learning (ML) techniques. These models analyze historical data alongside Experian's best-in-class data to identify consumers who meet credit criteria and are more likely to respond to offers. By accurately predicting consumer behavior, these models enable organizations to maximize the return on investment (ROI) of their marketing campaigns and achieve their revenue goals. Additionally, exclusive access to alternative datasets from nontraditional lenders, rental data inputs, and full-file public records provides a comprehensive view of consumer behavior. The inclusion of 24 months of trended data and over 2,000 attributes can further enhance your ability to determine the next best action for each consumer. Watch this video to learn more about Ascend Intelligence Services Target. Optimized prescreen strategy Target's prescreen strategy is mathematically optimized to calculate the impact of your offer on each consumer simultaneously. This approach selects the best consumers to target, allowing you to: Increase response and take-up rates for improved portfolio performance. Minimize prescreen costs by targeting the right people who are more likely to respond to your offers. Expand your lending universe safely and meet diversity and inclusion initiatives by providing the right offer to previously overlooked consumers. Seamlessly integrate into your existing prescreen process for rapid time to value. By incorporating additional variables such as trended and alternative data, you can reach more consumers who might have been overlooked, improving financial inclusion and safely growing your portfolio. The power of optimization allows you to tailor your offers to each consumer, increasing response and take-up rates and enhancing the profitability of your campaigns. Visit our website to learn more about how your organization can utilize our prescreen strategies to maximize your revenue. Learn more [1] Experian research

How can lenders ensure they’re making the most accurate and fair lending decisions? The answer lies in consistent model validations. What are model validations? Model validations are vital for effective lending and risk-based pricing programs. In addition to helping you determine which credit scoring model works best on your portfolio, the performance (odds) charts from validation results are often used to set score cutoffs and risk-based pricing tiers. Validations also provide the information you need to implement a new score into your decisioning process. Factors affecting model validations Understanding how well a score predicts behavior, such as payment delinquency or bankruptcy, enables you to make more confident lending decisions. Model performance and validation results can be impacted by several factors, including: Dynamic economic environment – Shifts in unemployment rates, interest rate hikes and other economic indicators can impact consumer behavior. Regulatory changes affecting consumers – For example, borrowers who benefited from a temporary student loan payment pause may face challenges as they resume payments. Scorecard degradation – A model that performed well several years ago may not perform as well under current conditions. When to perform model validations The Office of the Comptroller of the Currency’s Supervisory Guidance on Model Risk Management states model validations should be performed at least annually to help reduce risk. The validation process should be comprehensive and produce proper documentation. While some organizations perform their own validations, those with fewer resources and access to historical data may not be able to validate and meet the guidance recommendations. Regular validations support compliance and can also give you confidence that your lending strategies are built on solid, current data that drive better outcomes. Good model validation practices are critical if lenders are to continue to make data-driven decisions that promote fairness for consumers and financial soundness for the institution. Make better lending decisions If you’re a credit risk manager responsible for the models driving your lending policies, there are several things you can do to ensure that your organization continues to make fair and sound lending decisions: Assess your model inventory. Ensure you have comprehensive documentation showing when each model was developed and when it was last validated. Validate the scores you are using on your data, along with those you are considering, to compare how well each model performs and determine if you are using the most effective model for your needs. Produce validation documentation, including performance (odds) charts and key performance metrics, which can be shared with regulators. Utilize the performance charts produced from the validation to analyze bad rates/approval rates and adjust cutoff scores as needed. Explore alternative credit scoring models to potentially enhance your scoring process. As market conditions and regulations continue to evolve, model validations will remain an essential tool for staying competitive and making sound lending decisions. Ready to ensure your lending decisions are based on the latest data? Learn more about Experian’s flexible validation services and how we can support your ongoing success. Contact us today to schedule a consultation. Learn more

Machine learning (ML), the newest buzzword, has swept into the lexicon and captured the interest of us all. Its recent, widespread popularity has stemmed mainly from the consumer perspective. Whether it’s virtual assistants, self-driving cars or romantic matchmaking, ML has rapidly positioned itself into the mainstream. Though ML may appear to be a new technology, its use in commercial applications has been around for some time. In fact, many of the data scientists and statisticians at Experian are considered pioneers in the field of ML, going back decades. Our team has developed numerous products and processes leveraging ML, from our world-class consumer fraud and ID protection to producing credit data products like our Trended 3DTM attributes. In fact, we were just highlighted in the Wall Street Journal for how we’re using machine learning to improve our internal IT performance. ML’s ability to consume vast amounts of data to uncover patterns and deliver results that are not humanly possible otherwise is what makes it unique and applicable to so many fields. This predictive power has now sparked interest in the credit risk industry. Unlike fraud detection, where ML is well-established and used extensively, credit risk modeling has until recently taken a cautionary approach to adopting newer ML algorithms. Because of regulatory scrutiny and perceived lack of transparency, ML hasn’t experienced the broad acceptance as some of credit risk modeling’s more utilized applications. When it comes to credit risk models, delivering the most predictive score is not the only consideration for a model’s viability. Modelers must be able to explain and detail the model’s logic, or its “thought process,” for calculating the final score. This means taking steps to ensure the model’s compliance with the Equal Credit Opportunity Act, which forbids discriminatory lending practices. Federal laws also require adverse action responses to be sent by the lender if a consumer’s credit application has been declined. This requires the model must be able to highlight the top reasons for a less than optimal score. And so, while ML may be able to deliver the best predictive accuracy, its ability to explain how the results are generated has always been a concern. ML has been stigmatized as a “black box,” where data mysteriously gets transformed into the final predictions without a clear explanation of how. However, this is changing. Depending on the ML algorithm applied to credit risk modeling, we’ve found risk models can offer the same transparency as more traditional methods such as logistic regression. For example, gradient boosting machines (GBMs) are designed as a predictive model built from a sequence of several decision tree submodels. The very nature of GBMs’ decision tree design allows statisticians to explain the logic behind the model’s predictive behavior. We believe model governance teams and regulators in the United States may become comfortable with this approach more quickly than with deep learning or neural network algorithms. Since GBMs are represented as sets of decision trees that can be explained, while neural networks are represented as long sets of cryptic numbers that are much harder to document, manage and understand. In future blog posts, we’ll discuss the GBM algorithm in more detail and how we’re using its predictability and transparency to maximize credit risk decisioning for our clients.

Using bankcard utilization to forecast holiday spend It’s officially November, and like me, you’ve probably noticed all the holiday promotions in your mailbox and inbox. With only a brief window of holiday shopping available, it’s a retailer’s race to get consumer discretionary dollars. As we near the end of 2015, the U.S. economy continues to improve steadily, and consumers are cautiously optimistic about their financial well-being. National unemployment[i] is down to 5.1 percent, and while the Consumer Confidence Index®[ii] slipped to 97.6 in October, it is still higher than it was at the end of 2014. So will the U.S. consumer spend more this holiday season? One way to measure this behavior is through bankcard utilization rates — i.e., how much of their available credit consumers use. Overall, average bankcard utilization didn’t show much movement in Q3 2015, averaging 20.6 percent, compared with 20.3 percent the year before (a 1.5 percent increase).[iii] However, when we look at utilization rates by VantageScore® credit score tier, we see not only varying year-over-year (YOY) changes among consumer risk segments, but, more importantly, significant disparity in the overall usage of available credit.   Q3 2014 Q3 2015 YOY increase Super Prime (781-850) 5.5% 5.6% 1.8% Prime (661-780) 27.4% 27.8% 1.4% Near Prime (601-660 63.8% 64.5% 1.2% Subprime (501-600) 76.1% 78.4% 3.1% Deep Subprime (300-500) 94.7% 97.6% 3.1% Super-prime consumers use less than 6 percent of their available credit limits, while consumers in the deep-subprime tier use nearly every dollar allotted. So while we can’t yet determine how “black” this holiday season will be, we can predict that the lower a consumer’s credit tier, the more that consumer will rely on bankcards to fund his or her holiday shopping. For more credit and market insights, join Robert Stone and I for a Webinar, Unique insights on consumer credit trends and outlook for the remainder of 2015. [i]Bureau of Labor Statistics [ii]The Conference Board [iii]Experian IntelliView℠ VantageScore® is a registered trademark of VantageScore Solutions, LLC.

With the constant (and improving!) changes in the consumer credit landscape, understanding the latest trends is vital for institutions to validate current business strategies or make adjustments to shifts in the marketplace.  For example, a recent article in American Banker described how a couple of housing advocates who foretold the housing crisis in 2005 are now promoting a return to subprime lending. Good story lead-in, but does it make sense for MY business?  How do you profile this segment of the market and its recent performance?  Are there differences by geography?  What other products are attracting this risk segment that could raise concerns for meeting a new mortgage obligation?   There is a proliferation of consumer loan and credit information online from various associations and organizations, but in a static format that still makes it challenging to address these types of questions. Fortunately, new web-based solutions are being made available that allow users to access and interrogate consumer trade information 24x7 and keep abreast of constantly changing market conditions.  The ability to manipulate and tailor data by geography, VantageScore® credit score risk segments and institution type are just a mouse click away.  More importantly, these tools allow users to customize the data to meet specific business objectives, so the next subprime lending headline is not just a story, but a real business opportunity based on objective, real-time analysis. Explore the features from one such tool available.  

The Fed’s Comprehensive Capital Analysis and Review (CCAR) and Capital Plan Review (CapPR) stress scenarios depict a severe recession that, although unlikely, the largest U.S. banks must now account for in their capital planning process.  The bank holding companies’ ability to maintain adequate capital reserves, while managing the risk levels of growing portfolios are key to staying within the stress test parameters and meeting liquidity requirements. While each banks’ portfolios will perform differently, as a whole, the delinquency performance of major products such as Auto, Bankcard and Mortgage continues to perform well.   Here is a comparison between the latest quarter results and two years ago from the Experian – Oliver Wyman Market Intelligence Reports.   Although not a clear indication of how well a bank will perform against the hypothetical scenario of the stress tests, measures such as Probability of Default, Loss Given Default and Exposure at Default to indicate a bank’s risk may be dramatically improved from just a few years ago given recent delinquency trends in core portfolios. Recently we released a white paper that provides an introduction to Basel III regulation and discusses some of its impact on banks and the banking system.  We also present a real business case showing how organizations turn these regulatory challenges into buisness opportunities by optimizing their credit strategies.   Download the paper - Creating value in challenging times: An innovative approach to Basel III compliance.  

With the constant (and improving!) changes in the consumer credit landscape, understanding the latest trends is vital for institutions to validate current business strategies or make adjustments to shifts in the marketplace.  For example, a recent article in American Banker described how a couple of housing advocates who foretold the housing crisis in 2005 are now promoting a return to subprime lending. Good story lead-in, but does it make sense for “my” business?  How do you profile this segment of the market and its recent performance?  Are there differences by geography?  What other products are attracting this risk segment that could raise concerns for meeting a new mortgage obligation?   There is a proliferation of consumer loan and credit information online from various associations and organizations, but in a static format that still makes it challenging to address these types of questions. Fortunately, new web-based solutions are being made available that allow users to access and interrogate consumer trade information 24x7 and keep abreast of constantly changing market conditions.  The ability to manipulate and tailor data by geography, VantageScore risk segments and institution type are just a mouse click away.  More importantly, these tools allow users to customize the data to meet specific business objectives, so the next subprime lending headline is not just a story, but a real business opportunity based on objective, real-time analysis.

Up to this point, I’ve been writing about loan originations and the prospects and challenges facing bankcard, auto and real estate lending this year.  While things are off to a good start, I’ll use my next few posts to discuss the other side of the loan equation: performance. If there’s one thing we learned during the post-recession era is that growth can have consequences if not managed properly.  Obviously real estate is the poster child for this phenomenon, but bankcards also realized significant and costly performance deterioration following the rapid growth generated by relaxed lending standards. Today, bankcard portfolios are in expansion mode once again, but with delinquency rates at their lowest point in years.  In fact, loan performance has improved nearly 50% in the past three years through a combination of tighter lending requirements and consumers’ self-imposed deleveraging.   Lessons learned from issuers and consumers have created a unique climate in which growth is now balanced with performance. Even areas with greater signs of payment stress have realized significant improvements.   For example, the South Atlantic region’s 4.2% 30+ DPD performance is 11% higher than the national average, but down 27% from a year ago.   Localized economic factors definitely play a part in performance, but the region’s higher than average origination growth from a broader range of VantageScore® credit score consumers could also explain some of the delinquency stress here. And that is the challenge going forward: maintaining bankcard’s recent growth while keeping performance in check.  As the economy and consumer confidence improves, this balancing act will become more difficult as issuers will want to meet the consumer’s appetite for spending and credit.  Increased volume and utilization is always good for business, but it won’t be until the performance of these loans materializes that we’ll know whether it was worth it.

In my last two posts on bankcard and auto originations, I provided evidence as to why lenders have reason to feel optimistic about their growth prospects in 2012.  With real estate lending however, the recovery, or lack thereof looks like it may continue to struggle throughout the year. At first glance, it would appear that the stars have aligned for a real estate turnaround.  Interest rates are at or near all-time lows, housing prices are at post-bubble lows and people are going back to work with the unemployment rate at a 3-year low just above 8%. However, mortgage originations and HELOC limits were at $327B and $20B for Q3 2011, respectively.  Admittedly not all-time quarterly lows, but well off levels of just a couple years ago.  And according to the Mortgage Bankers Association, 65% of the mortgage volume was from refinance activity. So why the lull in real estate originations?  Ironically, the same reasons I just mentioned that should drive a recovery. Low interest rates – That is, for those that qualify.  The most creditworthy, VantageScore® credit score A and B consumers made up nearly 77% of the $327B mortgage volume and 87% of the $20B HELOC volume in Q3 2011.  While continuing to clean up their portfolios, lenders are adjusting their risk exposure accordingly. Housing prices at multi-year lows - According to the S&P Case Shiller index, housing prices were 4% lower at the end of 2011 when compared to the end of 2010 and at the lowest level since the real estate bubble.  Previous to this report, many thought housing prices had stabilized, but the excess inventory of distressed properties continues to drive down prices, keeping potential buyers on the sidelines. Unemployment rate at 3-year low – Sure, 8.3% sounds good now when you consider we were near 10% throughout 2010.  But this is a far cry from the 4-5% rate we experienced just five years ago.   Many consumers continue to struggle, affecting their ability to make good on their debt obligations, including their mortgage (see “Housing prices at multi-year lows” above), in turn affecting their credit status (see “Low interest rates” above)… you get the picture. Ironic or not, the good news is that these forces will be the same ones to drive the turnaround in real estate originations.  Interest rates are projected to remain low for the foreseeable future, foreclosures and distressed inventory will eventually clear out and the unemployment rate is headed in the right direction.  The only missing ingredient to make these variables transform from the hurdle to the growth factor is time.

If you attended any of our past credit trends Webinars, you’ve heard me mention time and again how auto originations have been a standout during these times when overall consumer lending has been a challenge.   In fact, total originated auto volumes topped $100B in the third quarter of 2011, a level not seen since mid-2008. But is this growth sustainable?  Since bottoming at the start of 2009, originations have been on a tear for nearly three straight years.  Given that, you might think that auto origination’s best days are behind it.   But these three key factors indicate originations may still have room to run: 1.       The economy Just as it was a factor in declining auto originations during the recession, the economy will drive continued increases in auto sales.  If originations were growing during the challenges of the past couple of years, the expected improvements in the economy in 2012 will surely spur new auto originations. 2.       Current cars are old A recent study by Experian Automotive showed that today’s automobiles on the road have hit an all-time high of 10.6 years of age.  Obviously a result of the recent recession, consumers owning older cars will result in pent up demand for newer and more reliable ones. 3.       Auto lending is more diversified than ever I’m talking diversification in a couple of ways: Auto lending has always catered to a broader credit risk range than other products.  In recent years, lenders have experimented with moving even further into the subprime space.   For example, VantageScore® credit score D consumers now represent 24.4% of all originations vs. 21.2% at the start of 2009.   There is a greater selection of lenders that cater to the auto space.  With additional players like Captives, Credit Unions and even smaller Finance companies competing for new business, consumers have several options to secure a competitively-priced auto loan. With all three variables in motion, auto originations definitely have a formula for continued growth going forward.  Come find out if auto originations do in fact continue to grow in 2012 by signing up for our upcoming Experian-Oliver Wyman credit trends Webinar.  

As we kick off the new year, I thought I’d dedicate a few blog posts to cover what some of the consumer credit trends are pointing to for potential growth opportunities in 2012, specifically on new loan originations for bankcard, automotive and real estate lending. With the holiday season behind us (and if you’re anything like me, you have the credit card statements to prove it!), I thought I’d start off with bankcards for my first post of the year. Everyone’s an optimist at the start of a new year and bankcard issuers have a right to feel cautiously optimistic about 2012 based on the trends of last year.  In the second quarter of 2011, origination volumes grew to nearly $47B, up 28% from the same quarter a year earlier.  Actually, originations have been steadily growing since the middle of 2010 with increasing distribution across all VantageScore risk bands and an impressive 42% increase in A paper volume.  So, is bankcard the new power portfolio for growth in 2012? The broad origination risk distribution may signal the return of balance-carrying consumers (aka:  revolvers) from those that pay with credit cards, but pay off the balance every month (aka: transactors).  The tighter lending criteria imposed in recent years has improved portfolio performance significantly, but at the expense of interest fee profitability from revolver use.  This could change as more credit cards are put in the hands of a broader consumer risk base.  And as consumer confidence continues to grow, (it reached 64.5 in December, 10 points higher than November according to the Conference Board) , consumers in all risk categories will no doubt begin to leverage credit cards more heavily for continued discretionary spend, as highlighted in the most recent Experian – Oliver Wyman quarterly webinar. Of course, portfolio growth with the increased risk exposure requires a watchful eye on the delinquency performance of outstanding balances.  We continue to be at or near historic lows for delinquency, but did see a small uptick in early stage delinquencies in the third quarter of 2011. That being said, issuers appear to have a good pulse on the card-carrying consumer and are capitalizing on the improved payment behavior to maximize their risk/reward payoff.   So all-in-all, strong 2011 results and portfolio positioning has set the table for a promising 2012.  Add an improving economy to the mix and card issuers could shift from cautious to confident in their optimism for the new year.  

With the raising of the U.S. debt ceiling and its recent ramifications consuming the headlines over the past month, I began to wonder what would happen if the general credit consumer had made a similar argument to their credit lender. Something along the lines of, “Can you please increase my credit line (although I am maxed out)? I promise to reduce my spending in the future!” While novel, probably not possible. In fact, just the opposite typically occurs when an individual begins to borrow up to their personal “debt ceiling.” When the amount of credit an individual utilizes to what is available to them increases above a certain percentage, it can adversely affect their credit score, in turn affecting their ability to secure additional credit. This percentage, known as the utility rate is one of several factors that are considered as part of an individual’s credit score calculation. For example, the utilization rate makes up approximately 23% of an individual’s calculated VantageScore® credit score. The good news is that consumers as a whole have been reducing their utilization rate on revolving credit products such as credit cards and home equity lines (HELOCs) to the lowest levels in over two years. Bankcard and HELOC utilization is down to 20.3% and 49.8%, respectively according to the Q2 2011 Experian – Oliver Wyman Market Intelligence Reports. In addition to lowering their utilization rate, consumers are also doing a better job of managing their current debt, resulting in multi-year lows for delinquency rates as mentioned in my previous blog post. By lowering their utilization and delinquency rates, consumers are viewed as less of a credit risk and become more attractive to lenders for offering new products and increasing credit limits. Perhaps the government could learn a lesson or two from today’s credit consumer.

A surprising occurrence is happening in the consumer credit markets. Bank card issuers are back in acquisition mode, enticing consumers with cash back, airline points and other incentives to get a share of their wallet. And while new account originations are nowhere near the levels seen in 2007, recent growth in new bank card accounts has been significant; 17.6% in Q1 2011 when compared to Q1 2010. So what is accounting for this resurgence in the credit card space while the economy is still trying to find its footing and credit is supposedly still difficult to come by for the average consumer? Whether good or bad, the economic crisis over the past few years appears to have improved consumers debt management behavior and card issuers have taken notice. Delinquency rates on bank cards are lower than at any time over the past five years and when compared to the start of 2009 when bank card delinquency was peaking; current performance has improved by over 40%. These figures have given bank card issuers the confidence to ease their underwriting standards and re-establish their acquisition strategies. What’s interesting however is the consumer segments that are driving this new growth. When analyzed by VantageScore, new credit card accounts are growing the fastest in the VantageScore D and F tiers with 46% and 53% increases year over year respectively. For comparison, VantageScore A and B tiers saw 5% and 1% increases during the same time period respectively.   And although VantageScore D and F represent less than 10% of new bank card origination volume ($ limits), it is still surprising to see such a disparity in growth rates between the risk categories. While this is a clear indication that card issuers are making credit more readily available for all consumer segments, it will be interesting to see if the debt management lessons learned over the past few years will stick and delinquency rates will continue to remain low. If these growth rates are any indication, the card issuers are counting on it.