Topics

By: Matt Sifferlen I recently read interesting articles on the Knowledge@Wharton and CNNMoney sites covering the land grab that's taking place among financial services startups that are trying to use a consumer's social media activity and data to make lending decisions.  Each of these companies are looking at ways to take the mountains of social media data that sites such as Twitter, Facebook, and LinkedIn generate in order to create new and improved algorithms that will help lenders target potential creditworthy individuals.  What are they looking at specifically?  Some criteria could be: History of typing in ALL CAPS or all lower case letters Frequent usage of inappropriate comments Number of senior level connections on LinkedIn The quantity of posts containing cats or annoying  self-portraits (aka "selfies") Okay, I made that last one up. The point is that these companies are scouring through the data that individuals are creating on social sites and trying to find useful ways to slice and dice it in order to evaluate and target consumers better. On the consumer banking side of the house, there are benefits for tracking down individuals for marketing and collections purposes. A simple search could yield a person's Facebook, Twitter, or LinkedIn profile. The behaviorial information can then be leveraged as a part of more targeted multi-channel and contact strategies. On the commercial banking side, utilizing social site info can help to supplement any traditional underwriting practices. Reviewing the history of a company's reviews on Yelp or Angie's List could share some insight into how a business is perceived and reveal whether there is any meaningful trend in the level of negative feedback being posted or potential growth outlook of the company. There are some challenges involved with leveraging social media data for these purposes. 1. Easily manipulated information 2. Irrelevant information that doesn't represent actual likes, thoughts or relevant behaviors 3. Regulations From a Fraud perspective, most online information can easily and frequently be manipulated which can create a constantly moving target for these providers to monitor and link to the right customer.  Fake Facebook and Twitter pages, false connections and referrals on LinkedIn, and fabricated positive online reviews of a business can all be accomplished in a matter of minutes. And commercial fraudsters are likely creating false business social media accounts today for shelf company fraud schemes that they plan on hatching months or years down the road.  As B2B review websites continue to make it easier to get customers signed up to use their services, the downside is  there will be even more unusable information being created since there are less and less hurdles for commercial fraudsters to clear, particularly for sites that offer their services for free. For now, the larger lenders are more likely to utilize alternative data sources that are third party validated, like rent and utility payment histories, while continuing to rely on tools that can prevent against fraud schemes. It will be interesting to see what new credit and non credit data will be utilized as a common practice in the future as lenders continue their efforts to find more useful data to power their credit and marketing decisions.

By: Joel Pruis As we go through the economic seasons, we need to remember to reassess our strategy.  While we use data as the way to accurately assess the environment and determine the best course of action for your future strategy, the one thing that is for certain is that the current environment will definitely change.  Aspects that we did not anticipate will develop, trends may start to slow or change direction. Moneyball continues to be a movie that gives us some great examples.  We see that Billy Beane and Peter Brand were constantly looking at their position and making adjustments to the team’s roster.  Even before they made any significant adjustments, Beane and Brand found themselves justifying their strategy to the owner (even though the primary issue was with the head coach not playing the roster that maximized the team’s probability of winning).  The first aspect that worked against the strategy was the head coach and while we could go down a tangent about cultural battles within an organization, let's focus on how Beane adjusted.  Beane simply traded the players the head coach preferred to play forcing the use of players preferred by Beane and Brand. Later we see Beane and Brand making final adjustments to the roster by negotiating trades resulting in the Oakland A’s landing Ricardo Rincon.  The change in the league that allowed such a trade was that Rincon’s team was not doing well and the timing allowed the A’s to execute the trade.   Beane adjusted with the changes in the league.  One thing to note, is that he changed the roster while the team was doing well.  They were winning but Beane made adjustments to continue maximizing the team’s potential.  Too often we adjust when things are going poorly and do not adjust when we seem to be hitting our targets. Overall, we need to continually assess what has changed in our environment and determine what new challenges or new opportunities these changes present.  I encourage you to regularly assess what is happening in your local economy.  High-level national trends are constantly on the front page of the news but we need to drill down to see what is happening in a specific market area being served.  As Billy Beane did with the Oakland A’s throughout the season, I challenge you to assess your current strategies and execution against what is happening in your market territory.   Related posts: How Financial Institutions can assess the overall conditions for generating the net yield on the assets How to create decision strategies for small business lending Upcoming Webinar: Learn about the current state of small business, the economy and how it applies to you

After reaching post-recession lows in June, the July S&P/Experian Consumer Credit Default Indices showed that default rates increased slightly in several categories. While the national composite,* first mortgage and auto loan default rates all increased, the bankcard default rate continued to decline and hit a new low of 3.22%.

If you're looking to implement and deploy a knowledge-based authentication (KBA) solution in your application process for your online and mobile customer acquisition channels - then, I have good news for you! Here’s some of the upside you’ll see right away: Revenues (remember, the primary activities of your business?) will accelerate up Your B2C acceptance or approval rates will go up thru automation Manual review of customer applications will go down and that translates to a reduction in your business operation costs Products will be sold and shipped faster if you’re in the retail business, so you can recognize the  sales revenue or net sales quicker Your customers will appreciate the fact that they can do business in minutes vs. going thru a lengthy application approval process with turnaround times of days to weeks And last but not least, your losses due to fraud will go down To keep you informed about what’s relevant when choosing a KBA vendor, here’s what separates the good KBA providers from the bad: The underlying data used to create questions should be from multiple data sources and should vary in the type of data, for example credit and non-credit Relying on public record data sources is becoming a risky proposition given recent adoption of various social media websites and various public record websites Have technology that will allow you to create a custom KBA setup that is unique to your business and business customers, and the proven support structure to help you grow your business safely Provide consulting (performance monitoring)and analytical support that will keep you ahead of the fraudsters trying to game your online environment by assuring your KBA tool is performing at optimal levels Solutions that can easily interface with multiple systems, and assist from a customer experience perspective. How are your peers in the following 3 industries doing at adopting a KBA strategy to help grow and protect their businesses? E-commerce 21% use KBA today and are satisfied with the results* 13% have KBA on roadmap and the list is growing fast* Healthcare 20% use dynamic KBA* Financial Institutions 30% combination of dynamic & static KBA* 20% dynamic KBA* What are the typical uses of KBA?* Call center Web / mobile verification Enrollment ID verification Provider authentication Eligibility *According to a 2012 report on knowledge-based authentication by Aite Group LLC Knowledge-based authentication, commonly referred to as KBA, is a method of authentication which seeks to prove the identity of someone accessing a service, such as a website. As the name suggests, KBA requires the knowledge of personal information of the individual to grant access to the protected material. There are two types of KBA: "static KBA", which is based on a pre-agreed set of "shared secrets"; and "dynamic KBA", which is based on questions generated from a wider base of personal information.  

Small-business credit conditions strengthened in Q2 2013, lifting the Experian/Moody's Analytics Small Business Credit Index 2.8 points to 111.7 - the highest level since it began tracking. Consumer spending growth was modest, but steady and consumer confidence is at multiyear highs. This is a reassuring signal that consumer spending is unlikely to backtrack in the near future. Furthermore, credit quality improved for every business size, with the total share of delinquent dollars 2.4 percentage points lower than a year ago and at the lowest point on record.

According to a recent survey by freecreditscore.com™, women find financial responsibility more attractive in assessing a romantic partner (96 percent) than physical attractiveness (87 percent) or career ambition (87 percent). Men slightly favor good looks over financial responsibility (92 percent versus 91 percent); however, 20 percent of men surveyed would not marry someone with a poor credit score.

The average bankcard balance per consumer in Q2 2013 was $3,831, a 1.3 percent decline from the previous year. Consumers in the VantageScore® near prime and subprime credit tiers carried the largest average bankcard balances at $5,883 and $5,903 respectively. The super prime tier carried the smallest average balance at $1,881.

Using data from IntelliViewSM, Credit.com recently compiled a list of states with the highest average bankcard utilization rates. Alaska took first place, with an average utilization ratio of 27.73 percent. This should come as no surprise since Alaska has recently topped lists for highest credit card balances and highest revolving debt.

By: Maria Moynihan Government organizations that handle debt collection have similar business challenges regardless of agency focus and mission. Let’s face it, debtors can be elusive. They are often hard to find and even more difficult to collect from when information and processes are lacking. To accelerate debt recovery, governments must focus on optimization--particularly, streamlining how resources get used in the debt collection process.  While the perception may be that it’s difficult to implement change given limited budgets, staffing constraints or archaic systems, minimal investment in improved data, tools and technology can make a big difference. Governments most often express the below as their top concerns in debt collection: Difficulty in finding debtors to collect on late tax submissions, fines or fees. Prioritizing collection activities--outbound letters, phone calls, and added steps in decisioning. Difficulty in incorporating new tools or technology to reduce backlogs or accelerate current processes. By simply utilizing right party contact data and tools for improved decisioning, agencies can immediately expose areas of greater possible ROI over others. Credit and demographic data elements like address, income models, assets, and past payment behavior can all be brought together to create a holistic view of an individual or business at a point in time or over time. Collections tools for improved monitoring, segmentation and scoring could be incorporated into current systems to improve resource allotment. Staffing can then be better allocated to not only focus on which accounts to pursue by size, but by likelihood to make contact and payment. Find additional best practices to optimize debt recovery in this guide to Maximizing Revenue Potential in the Public Sector. Be sure to check out our other blog posts on debt collection.

I don’t know about your neighborhood this past Fourth of July, but mine contained an interesting mix of different types of fireworks. From our front porch, we watched a variety of displays simultaneously: an organized professional fireworks show several miles away, our next-door neighbor setting off the “Safe and Sane” variety and the guy at the end of the street with clearly illegal ones. This made me think about how our local police approach this night. There’s no way they can investigate every report or observance of illegal fireworks as well as all of the other increased activity that occurs on a holiday. So it must come down to prioritization, resources and risk assessment. When it comes to fraud prevention, compliance and risk, businesses — much the same as the police — have a lot of ground to cover and limited resources. Consider the bureau alerts (aka high-risk conditions) on a credit report. They’re an easy, quick tool that can help mitigate risk and save money cost-effectively. When considering bureau alerts, clients commonly ask the following questions: How do I investigate all of the alerts with the limited resources I have? How should I prioritize the ones I am able to review? I usually recommend that, if possible, they incorporate a fraud risk score into their evaluation process. The job of the fraud risk score is to take a very large amount of data and put it into an easy-to-understand and actionable form. It is built to evaluate negative or risky information (at Experian, this includes bureau alerts and many other items) as well as positive or low-risk information (analysis of address, Social Security number, date of birth, and other current and historical personal information). The result is a holistic assessment rather than a binary flag, which can be tuned to resource levels, risk tolerance or other drivers. That’s always where I start. If a fraud score is not an option, then I suggest prioritizing the alerts by the most risk and the frequency of occurrence. With some light analysis, you’ll typically see that the frequency of the most risky alerts is often low, so you can be sure to review each one — or as many as possible. As the frequency of occurrence increases, you then can make decisions about which ones to review or how many of them you can handle. For example, I worked with a client recently to prioritize high-risk but low-frequency alerts. Almost all involved the Social Security number (SSN): The inquiry SSN was recorded as deceased The report contained a security statement There was a high probability that the SSN belongs to another person The best on-file SSN was recorded as deceased  I would expect other organizations to have a similar prioritized risk-to-frequency ratio. However, it’s always good (and pretty easy) to make sure your data backs this up. That way, you’re making the most of your limited resources and your tools.

A recent survey of government benefit agencies shows an increased need for fraud detection technology to prevent eligibility fraud. Only 26 percent of respondents currently use fraud detection technology, and 57 percent cite false income reporting as the leading cause of fraud. Insufficient resources and difficulty integrating multiple data sources were the greatest challenges in preventing eligibility fraud.

The desire to return to portfolio growth is a clear trend in mature credit markets, such as the US and Canada. Historically, credit unions and banks have driven portfolio growth with aggressive out-bound marketing offers designed to attract new customers and members through loan acquisitions. These offers were typically aligned to a particular product with no strategy alignment between multiple divisions within the organization.  Further, when existing customers submitted a new request for credit, they were treated the same as incoming new customers with no reference to the overall value of the existing relationship. Today, however, financial institutions are looking to create more value from existing customer relationships to drive sustained portfolio growth by increasing customer retention, loyalty and wallet share. Let’s consider this idea further. By identifying the needs of existing customers and matching them to individual credit risk and affordability, effective cross-sell strategies that link the needs of the individual to risk and affordability can ensure that portfolio growth can be achieved while simultaneously increasing customer satisfaction and promoting loyalty. The need to optimize customer touch-points and provide the best possible customer experience is paramount to future performance, as measured by market share and long-term customer profitability. By also responding rapidly to changing customer credit needs, you can further build trust, increase wallet share and profitably grow your loan portfolios.  In the simplest sense, the more of your products a customer uses, the less likely the customer is to leave you for the competition. With these objectives in mind, financial organizations are turning towards the practice of setting holistic, customer-level credit lending parameters. These parameters often referred to as umbrella, or customer lending, limits. The challenges Although the benefits for enhancing existing relationships are clear, there are a number of challenges that bear to mind some important questions to consider: ·     How do you balance the competing objectives of portfolio loan growth while managing future losses? ·     How do you know how much your customer can afford? ·     How do you ensure that customers have access to the products they need when they need them ·     What is the appropriate communication method to position the offer? Few credit unions or banks have lending strategies that differentiate between new and existing customers.  In the most cases, new credit requests are processed identically for both customer groups. The problem with this approach is that it fails to capture and use the power of existing customer data, which will inevitably lead  to suboptimal decisions. Similarly, financial institutions frequently provide inconsistent lending messages to their clients. The following scenarios can potentially arise when institutions fail to look across all relationships to support their core lending and collections processes: 1.     Customer is refused for additional credit on the facility of their choice, whilst simultaneously offered an increase in their credit line on another. 2.     Customer is extended credit on a new facility whilst being seriously delinquent on another. 3.     Customer receives marketing solicitation for three different products from the same institution, in the same week, through three different channels. Essentials for customer lending limits and successful cross-selling By evaluating existing customers on a periodic (monthly) basis, financial institutions can assess holistically the customer’s existing exposure, risk and affordability. By setting customer level lending limits in accordance with these parameters, core lending processes can be rendered more efficient, with superior results and enhanced customer satisfaction. This approach can be extended to consider a fast-track application process for existing relationships with high value, low risk customers. Traditionally, business processes have not identified loan applications from such individuals to provide preferential treatment. The core fundamentals of the approach necessary for the setting of holistic customer lending (umbrella) limits include: ·     The accurate evaluation of credit and default risk ·     The calculation of additional lending capacity and affordability ·     Appropriate product offerings for cross-sell ·     Operational deployment Follow my blog series over the next few months as we explore the essentials for customer lending limits and successful cross-selling.

There are two core fundamentals of evaluating loan loss performance to consider when generating organic portfolio growth through the setting of customer lending limits.  Neither of which can be discussed without first considering what defines a “customer.” Definition of a customer The approach used to define a customer is critical for successful customer management and is directly correlated to how joint accounts are managed. Definitions may vary by how joint accounts are allocated and used in risk evaluation. It is important to acknowledge: Legal restrictions for data usage related to joint account holders throughout the relationship Impact on predictive model performance and reporting where there are two financially linked individuals with differently assigned exposures Complexities of multiple relationships with customers within the same household – consumer and small business Typical customer definitions used by financial services organizations: Checking account holders: This definition groups together accounts that are “fed” by the same checking account. If an individual holds two checking accounts, then she will be treated as two different and unique customers. Physical persons: Joint accounts allocated to each individual. If Mr. Jones has sole accounts and holds joint accounts with Ms. Smith who also has sole accounts, the joint accounts would be allocated to both Mr. Jones and Ms. Smith. Consistent entities: If Mr Jones has sole accounts and holds joint accounts with Ms. Smith who also has sole accounts, then 3 “customers” are defined: Jones, Jones & Smith, Smith. Financially-linked individuals: Whereas consistent entities are considered three separate customers, financially-linked individuals would be considered one customer: “Mr. Jones & Ms. Smith”. When multiple and complex relationships exist, taking a pragmatic approach to define your customers as financially-linked will lead to a better evaluation of predicted loan performance. Evaluation of credit and default risk Most financial institutions calculate a loan default probability on a periodic basis (monthly) for existing loans, in the format of either a custom behavior score or a generic risk score, supplied by a credit bureau. For new loan requests, financial institutions often calculate an application risk score, sometimes used in conjunction with a credit bureau score, often in a matrix-based decision. This approach is challenging for new credit requests where the presence and nature of the existing relationship is not factored into the decision. In most cases, customers with existing relationships are treated in an identical manner to those new applicants with no relationship – the power and value of the organization’s internal data goes overlooked whereby customer satisfaction and profits suffer as a result.   One way to overcome this challenge is to use a Strength of Relationship (SOR) indicator. Strength of Relationship (SOR) indicator The Strength of Relationship (SOR) indicator is a single-digit value used to define the nature of the relationship of the customer with financial institution. Traditional approaches for the assignment of a SOR are based upon the following factors  Existence of a primary banking relationship (salary deposits)  Number of transactional products held (DDA, credit cards)  Volume of transactions  Number of loan products held  Length of time with bank The SOR has a critical role in the calculation of customer level risk grades and strategies and is used to point us to the data that will be the most predictive for each customer. Typically the stronger the relationship, the more we know about our customer, and the more robust will be predictive models of consumer behavior. The more information we have on our customer, the more our models will lean towards internal data as the primary source. For weaker relationships, internal data may not be robust enough alone to be used to calculate customer level limits and there will be a greater dependency to augment internal data with external third party data (credit bureau attributes.) As such, the SOR can be used as a tool to select the type and frequency of external data purchase. Customer Risk Grade (CRG) A customer-level risk grade or behavior score is a periodic (monthly) statistical assessment of the default risk of an existing customer. This probability uses the assumption that past performance is the best possible indicator of future performance. The predictive model is calibrated to provide the probability (or odds) that an individual will incur a “default” on one or more of their accounts. The customer risk grade requires a common definition of a customer across the enterprise. This is required to establish a methodology for treating joint accounts. A unique customer reference number is assigned to those customers defined as “financially-linked individuals”.  Account behavior is aggregated on a monthly basis and this information is subsequently combined with information from savings accounts and third party sources to formulate our customer view. Using historical customer information, the behavior score can accurately differentiate between good and bad credit risk individuals. The behavior score is often translated into a Customer Risk Grade (CRG). The purpose of the CRG is to simplify the behavior score for operational purposes making it easier for noncredit/ risk individuals to interpret a grade more easily than a mathematical probability. Different methods for evaluating credit risk will yield different results and an important aspect in the setting of customer exposure thresholds is the ability to perform analytical tests of different strategies in a controlled environment. In my next post, I’ll dive deeper into adaptive control, champion challenger techniques and strategy design fundamentals.  Related content: White paper: Improving decisions across the Customer Life Cycle

Small-business credit conditions improved in Q1 2013, reversing much of the deterioration seen during Q4 2012. The Q1 rise was fueled primarily by falling delinquency rates in every segment compared with a year earlier. The total share of delinquent dollars was 11.2 percent for Q1 2013 - 1.4 percentage points lower than a year ago.

A recent Experian credit trends analysis of new mortgages and bankcards from Q1 2013 shows a 16 percent year-over-year increase in mortgage origination volume and a 20 percent increase in bankcard limits. Providing further evidence of continued economic recovery throughout the nation, mortgage delinquency rates reached multi-year lows and bankcard delinquency rates reached near-record lows.