Telecommunications, Cable & Utilities
Telecommunications, Cable & Utilities
As I mentioned in my previous blog, model validation is an essential step in evaluating a recently developed predictive model’s performance before finalizing and proceeding with implementation. An in-time validation sample is created to set aside a portion of the total model development sample so the predictive accuracy can be measured on a data sample not used to develop the model. However, if few records in the target performance group are available, splitting the total model development sample into the development and in-time validation samples will leave too few records in the target group for use during model development. An alternative approach to generating a validation sample is to use a resampling technique. There are many different types and variations of resampling methods. This blog will address a few common techniques. Jackknife technique — An iterative process whereby an observation is removed from each subsequent sample generation. So if there are N number of observations in the data, jackknifing calculates the model estimates on N - 1 different samples, with each sample having N - 1 observations. The model then is applied to each sample, and an average of the model predictions across all samples is derived to generate an overall measure of model performance and prediction accuracy. The jackknife technique can be broadened to a group of observations removed from each subsequent sample generation while giving equal opportunity for inclusion and exclusion to each observation in the data set. K-fold cross-validation — Generates multiple validation data sets from the holdout sample created for the model validation exercise, i.e., the holdout data is split into K subsets. The model then is applied to the K validation subsets, with each subset held out during the iterative process as the validation set while the model scores the remaining K-1 subsets. Again, an average of the predictions across the multiple validation samples is used to create an overall measure of model performance and prediction accuracy. Bootstrap technique — Generates subsets from the full model development data sample, with replacement, producing multiple samples generally of equal size. Thus, with a total sample size of N, this technique generates N random samples such that a single observation can be present in multiple subsets while another observation may not be present in any of the generated subsets. The generated samples are combined into a simulated larger data sample that then can be split into a development and an in-time, or holdout, validation sample. Before selecting a resampling technique, it’s important to check and verify data assumptions for each technique against the data sample selected for your model development, as some resampling techniques are more sensitive than others to violations of data assumptions. Learn more about how Experian Decision Analytics can help you with your custom model development.
An introduction to the different types of validation samples Model validation is an essential step in evaluating and verifying a model’s performance during development before finalizing the design and proceeding with implementation. More specifically, during a predictive model’s development, the objective of a model validation is to measure the model’s accuracy in predicting the expected outcome. For a credit risk model, this may be predicting the likelihood of good or bad payment behavior, depending on the predefined outcome. Two general types of data samples can be used to complete a model validation. The first is known as the in-time, or holdout, validation sample and the second is known as the out-of-time validation sample. So, what’s the difference between an in-time and an out-of-time validation sample? An in-time validation sample sets aside part of the total sample made available for the model development. Random partitioning of the total sample is completed upfront, generally separating the data into a portion used for development and the remaining portion used for validation. For instance, the data may be randomly split, with 70 percent used for development and the other 30 percent used for validation. Other common data subset schemes include an 80/20, a 60/40 or even a 50/50 partitioning of the data, depending on the quantity of records available within each segment of your performance definition. Before selecting a data subset scheme to be used for model development, you should evaluate the number of records available in your target performance group, such as number of bad accounts. If you have too few records in your target performance group, a 50/50 split can leave you with insufficient performance data for use during model development. A separate blog post will present a few common options for creating alternative validation samples through a technique known as resampling. Once the data has been partitioned, the model is created using the development sample. The model is then applied to the holdout validation sample to determine the model’s predictive accuracy on data that wasn’t used to develop the model. The model’s predictive strength and accuracy can be measured in various ways by comparing the known and predefined performance outcome to the model’s predicted performance outcome. The out-of-time validation sample contains data from an entirely different time period or customer campaign than what was used for model development. Validating model performance on a different time period is beneficial to further evaluate the model’s robustness. Selecting a data sample from a more recent time period having a fully mature set of performance data allows the modeler to evaluate model performance on a data set that may more closely align with the current environment in which the model will be used. In this case, a more recent time period can be used to establish expectations and set baseline parameters for model performance, such as population stability indices and performance monitoring. Learn more about how Experian Decision Analytics can help you with your custom model development needs.
With delinquencies on the rise, financial institutions are looking for new tools to evaluate and improve the financial lives of customers and members. As the consumer’s bureau, Experian is also committed to improving the financial well-being of consumers. As part of that commitment, Experian supports the mission of the Center for Financial Services Innovation (CFSI), an organization focused on improving the financial health of Americans, especially the underserved, through innovative financial products and services. Experian recently spoke with CFSI’s Thea Garon, a Director on CFSI’s Program Team to learn more about a new free, open-source tool the organization will be launching in June to help financial institutions drive consumer financial health. Here are some insights she shared about the new tool. Can you provide an overview of the CFSI Financial Health Score™ and how it is calculated? The CFSI Financial Health Score™ is designed to help financial service providers, employers, and other organizations diagnose and measure the financial health of their customers, clients, and employees. The framework provides a holistic, moment-in-time snapshot of an individual’s financial health based on eight multiple-choice questions that align with CFSI’s eight indicators of financial health. It includes one Financial Health Score and four sub-scores (Spend, Save, Borrow, and Plan). A set of nationally representative benchmarks offers comparisons across peer groups. CFSI has designed the framework to be free, open-source, simple, and easy-to-use. It’s intended to be a starting point; a proof point that financial health can be quantified, measured, and ultimately improved. Why did CFSI decide to develop this framework? At CFSI, we believe, and have recently released research to support the concept that financial institutions have a business incentive to help their customers lead financially healthy lives. Financial health comes about when your daily financial systems allow you to be resilient and pursue opportunities over time. As a financial service provider, you can help your customers lead financially healthy lives by helping them spend wisely, build savings, borrow responsibly, and plan for the future. To do this, you need a measurement framework to understand and track your customers’ financial health over time. The CFSI Financial Health Score™ is one way to do this. You can use the methodology to diagnose your customers’ financial needs and use these insights to develop products, programs, and solutions to help them improve their financial health over time. You can also share financial health scores directly with your customers to help them understand the actions they can take to improve their own financial health. Ongoing tracking will allow you to assess whether your company is making a meaningful difference in your customers’ lives over time. Can you provide any early examples of how CFSI Health Network members have adopted and incorporated this framework? Approximately 100 financial service providers have downloaded the framework, representing a diverse range of companies, including banks, credit unions, fintechs, non-profits, payment networks, and B2B technology providers. At least 14 companies are actively using the Financial Health Score to measure and track their customers’ financial health and have committed to sharing data and insights with us through CFSI’s Financial Health Leaders program. Some companies, are using the framework to assess their customers’ financial health for strategic planning purposes. Other companies, such as Wright-Patt Credit Union, are using the financial health score to engage their customers in a dialogue about financial health. The credit union has incorporated the framework into their MoneyMagnifier program, a financial coaching program designed to provide free, one-on-one advice and guidance to members in a judgment-free environment. Financial coaches have been trained to use the framework to start a conversation with members to help them improve their spending, saving, borrowing, and planning behaviors. Coaches help members set goals and develop personalized action plans to achieve those goals toward a better financial future, following up with them after six months to measure improvement and advance the conversation. What have you learned from companies who have started measuring and improving their customers’ financial health with the CFSI Financial Health Score™? While interest in advice is high, uptake can be slow. Making the interaction quick and easy, whether online or in person, is critical. The health check lengthens the interaction, so conducting the health check by appointment rather than with walk-in customers, can help set customer expectations for a lengthier interaction, but may reduce the number of potential participants. Enabling customers to expedite the session by taking the survey online can be helpful, but requires development resources to implement. Many companies are exploring the pros and cons of sharing customers’ scores with them. A single score can help motivate individuals to take action that will improve their financial well-being. However, sharing a low score can also be demoralizing to some, and focusing on the number itself can divert attention from behavioral changes and action steps. Some organizations are choosing to use customers’ response patterns to drive recommendations without sharing the score. Others are opting for a middle ground, sharing an indicator (such as green, yellow, red) instead of a specific number. The most effective measurement and improvement strategies go beyond the CFSI Financial Health Score™. While the framework can help you get started identifying high-level needs, targeted recommendations often require a more nuanced understanding of behaviors and challenges. Combining survey data with account or transaction data can provide a more holistic view into a customer’s full financial life. Each organization must find a balance between the comprehensiveness required to provide meaningful advice and the simplicity required to engage both customers and staff. How can interested companies start using the CFSI Financial Health Score™? We will be publicly releasing the CFSI Financial Health Score™ at the EMERGE: Financial Health Forum (June 6 -8 in Los Angeles). The score will be easy to download and completely free to use. Those who are interested in learning more can also sign up for our newsletter to get an update when the Toolkit is released.
The traditional credit score has ruled the financial services space for decades, but it‘s clear the way in which consumers are managing their money and credit has evolved. Today’s consumers are utilizing different types of credit via various channels. Think fintech. Think short-term loans. Think cash-checking services and payday. So, how do lenders gain more visibility to a consumer’s credit worthiness in 2018? Alternative credit data has surfaced to provide a more holistic view of all consumers – those on the traditional file and those who are credit invisibles and emerging. In an all-new report, Experian dives into “The State of Alternative Credit Data,” providing in-depth coverage on how alternative credit data is defined, regulatory implications, consumer personas attached to the alternative financial services industry, and how this data complements traditional credit data files. “Alternative credit data can take the shape of alternative finance data, rental, utility and telecom payments, and various other data sources,” said Paul DeSaulniers, Experian’s senior director of Risk Scoring and Trended/Alternative Data and attributes. “What we’ve seen is that when this data becomes visible to a lender, suddenly a much more comprehensive consumer profile is formed. In some instances, this helps them offer consumers new credit opportunities, and in other cases it might illuminate risk.” In a national Experian survey, 53% of consumers said they believe some of these alternative sources like utility bill payment history, savings and checking account transactions, and mobile phone payments would have a positive effect on their credit score. Of the lenders surveyed, 80% said they rely on a credit report, plus additional information when making a lending decision. They cited assessing a consumer’s ability to pay, underwriting insights and being able to expand their lending universe as the top three benefits to using alternative credit data. The paper goes on to show how layering in alternative finance data could allow lenders to identify the consumers they would like to target, as well as suppress those that are higher risk. “Additional data fields prove to deliver a more complete view of today’s credit consumer,” said DeSaulniers. “For the credit invisible, the data can show lenders should take a chance on them. They may suddenly see a steady payment behavior that indicates they are worthy of expanded credit opportunities.” An “unscoreable” individual is not necessarily a high credit risk — rather they are an unknown credit risk. Many of these individuals pay rent on time and in full each month and could be great candidates for traditional credit. They just don’t have a credit history yet. The in-depth report also explores the future of alternative credit data. With more than 90 percent of the data in the world having been generated in just the past five years, there is no doubt more data sources will emerge in the coming years. Not all will make sense in assessing credit decisions, but there will definitely be new ways to capture consumer-permissioned data to benefit both consumer and lender. Read Full Report
In my first blog post on the topic of customer segmentation, I shared with readers that segmentation is the process of dividing customers or prospects into groupings based on similar behaviors. The more similar or homogeneous the customer grouping, the less variation across the customer segments are included in each segment’s custom model development. A thoughtful segmentation analysis contains two phases: generation of potential segments, and the evaluation of those segments. Although several potential segments may be identified, not all segments will necessarily require a separate scorecard. Separate scorecards should be built only if there is real benefit to be gained through the use of multiple scorecards applied to partitioned portions of the population. The meaningful evaluation of the potential segments is therefore an essential step. There are many ways to evaluate the performance of a multiple-scorecard scheme compared with a single-scorecard scheme. Regardless of the method used, separate scorecards are only justified if a segment-based scorecard significantly outperforms a scorecard based on a broader population. To do this, Experian® builds a scorecard for each potential segment and evaluates the performance improvement compared with the broader population scorecard. This step is then repeated for each potential segmentation scheme. Once potential customer segments have been evaluated and the segmentation scheme finalized, the next step is to begin the model development. Learn more about how Experian Decision Analytics can help you with your segmentation or custom model development needs.
Managing your customer accounts at the identity level is ambitious and necessary, but possible Identity-related fraud exposure and losses continue to grow. The underlying schemes have elevated in complexity. Because it’s more difficult to perpetrate “card present” fraud in the post–chip-and-signature rollout here in the United States, bad guys are more motivated and getting better at identity theft and synthetic identity attacks. Their organized nefarious response takes the form of alternate attack vectors and methodologies — which means you need to stamp out any detected exposure point in your fraud prevention strategies as soon as it’s detected. Experian’s recently published 2018 Global Fraud and Identity Report suggests two-thirds, or 7 out of every ten, consumers want to see visible security protocols when they transact. But an ever-growing percentage of them, fueled in no small part by those tech-savvy millennials, expect to be recognized with little or no friction. In fact, 42 percent of the surveyed consumers who stated they would do more transactions online if there weren’t so many security hurdles to overcome were — you guessed it — millennials. So how do you implement identity and account management procedures that are effective and, in some cases, even obvious while being passive enough to not add friction to the user experience? In other words, from the consumer’s perspective, “Let me know you know me and are protecting me but not making it too difficult for me when I want to access or manage my account.” Let’s get one thing out of the way first. This isn’t a one-time project or effort. It is, however, a commitment to the continued informing of your account management strategies with updated identity intelligence. You need to make better decisions on when to let a low-risk account transaction (monetary or nonmonetary) pass and when to double down a bit and step up authentication or risk assessment checks. I’d suggest this is most easily accomplished through a single, real-time access point to myriad services that should, at the very least, include: Identity verification and reverification checks for ongoing reaffirmation of your customer identity data quality and accuracy. Know Your Customer program requirements, anyone? Targeted identity risk scores and underlying attributes designed to isolate identity theft, first-party fraud and synthetic identity. Fraud risk comes in many flavors. So must your analytics. Device intelligence and risk assessment. A customer identity is no longer just their name, address, Social Security number and date of birth. It’s their phone number, email address and the various devices they use to access your services as well. Knowing how that combination of elements presents itself over time is critical. Layered passive or more active authentication options such as document verification, biometrics, behavioral metrics, knowledge-based verification and alternative data sources. Ongoing identity monitoring and proactive alerting and segmentation of customers whose identity risk has shifted to the point of required treatment. Orchestration, workflow and decisioning capabilities that allow your team to make sense of the many innovative options available in customer recognition and risk assessment — without a “throw the kitchen sink at this problem” approach that will undoubtedly be way too costly in dollars spent and good customers annoyed. Fraud attacks are dynamic. Your customers’ perceptions and expectations will continue to evolve. The markets you address and the services you provide will vary in risk and reward. An innovative marketplace of identity management services can overwhelm. Make sure your strategic identity management partner has good answers to all of this and enables you to future-proof your investments.
Millions of Americans placed a credit freeze or restricted access to their credit file in recent months to keep identity thieves at bay. Credit freezes keep any new creditors from seeing a consumer’s credit file, which makes it nearly impossible for hackers to open new accounts fraudulently. But a credit freeze can also be problematic for consumers when they are finally ready to consider new credit products and loans. We’ve heard from credit unions and other lenders about sharing best practices to help streamline the process for consumers who want to permanently or temporarily lift the freeze to apply for a legitimate line of credit. Following are the three ways to help clients with a frozen Experian report quickly and efficiently allow access. Unfreeze account: This will remove the freeze entirely from the consumer’s credit report so that it may be accessed with the consumer’s permission. To do this, the consumer will need to contact Experian online, by phone or mail and provide his unique personal identification number (PIN) code—provided when the consumer froze his account—to un-freeze the report. Thaw account: An action that will temporarily remove the freeze for a timeframe determined by the consumer. The consumer should contact Experian online, by phone, or mail and provide his unique PIN code to thaw the report. Grant a creditor one-time access: A consumer may provide a different/temporary PIN to a lender to access the report just once. The PIN can be emailed to the consumer, presented on screen if the consumer is online, or provided on the phone or by mail. Typically, a consumer’s request to thaw or un-freeze his credit file online or by phone will thaw or un-freeze the file within minutes. Download Checklist Experian can be reached: Online: www.experian.com/freeze Phone: 888-397-3742 Mail: P.O. Box 9554, Allen, Texas 75013 Remember, if a consumer has a frozen credit file with all three credit reporting agencies, he will need to contact each agency to enable access to his report.
I recently sat down with Kathleen Peters, SVP and Head of Fraud and Identity, to discuss the state of fraud and identity, the pace of change in the space and her recent inclusion in the Top 100 influencers in Identity by One World Identity. ----------- Traci: Congratulations on being included on the Top 100 influencers list. What a nice honor. Kathleen: Yes, thank you. It is a nice honor and inspiring to be included among some great innovators in the industry. The list includes entrepreneurs to leaders of large organizations like us. It’s a nice mix across all facets of identity. T: Tell me about your role. How long have you been at Experian? K: I lead the team that defines the product strategy for our global fraud and ID portfolio. I’ve been with Experian just over four years, joining soon after we acquired 41st Parameter®. T: What was your first job? K: My first job out of college was with Motorola in Chicago. I was an electrical engineer, working on advanced cellphone technology. T: They were not able to keep up with the market? K: The entire industry was caught by the introduction of the iPhone. All the major cellphone companies were impacted — Nokia, Ericsson, Siemens and others. Talk about disrupting an industry. T: Yeah. These are great examples of how the disrupters have taken out the initial companies. Certainly, Motorola, Nokia, those companies. Even RIM Blackberry, which redefined the digital or cellular space, has all but disappeared. K: Yes, exactly. It was interesting to watch RIM Blackberry when they disrupted Motorola’s pager business. Motorola had a very robust pager line. Even then they had a two-way pager with a keyboard. They just missed the idea of mobile email completely. It’s really, really fascinating to look back now. T: Changing the subject a little, what motivates you to get out of bed in the morning? K: One of my favorite questions. I’m a very purpose-driven person. One of the things I really like about my role and one of the reasons I came to Experian in the first place is that I could see this huge potential within the company to combine offline and online identity information and transaction information to better recognize people and stop fraud. T: What do you see as the biggest threat to organizations today? K: I would have to say the pace of change. As we were just talking about, major industries can be disrupted seemingly overnight. We’re in the midst of a real digital transformation in how we live, how we work, how we share information and even how we share money. The threat to companies is twofold. One is the “friendly fire” threat, like the pace of change, disrupters to the market, new ways of doing things and keeping pace with that innovation. The second threat is that with digitization comes new types of security and fraud risks. Today, organizations need to be ever-vigilant about their security. T: How do you stay ahead of that pace of change? K: Well, my husband and I have lived in Silicon Valley since 1997. Technology and innovation are all around us. We read about it and we hear about it in the news. We engage with our neighbors and other people who we meet socially and within our networks. You can’t help but be immersed in it all the time. It certainly influences the way we go about our lives and how we think and act and engage as a family. We’re all technically curious. We have two kids, and our neighborhood high school, Homestead High, is the same high school Steve Jobs went to. It’s fun that way. T: Definitely. What are some of the most effective ways for businesses to combat the threat of fraud? K: I firmly believe that nowadays it all needs to start with identity. What we’ve found — and confirmed through research in our recent Global Fraud Report, plus conversations I’ve had with clients and analysts — is that if you can better recognize someone, you’ll go a long way to prevent fraud. And it does more than prevent fraud; it provides a better experience for the people you’re engaged with. Because once you recognize an individual, that initiates a trusted relationship between the two of you. Once people feel they’re in a trusted relationship, whether it’s a social relationship or a financial transaction, whatever the relationship is — once you feel trusted, you feel safe, you feel protected. And you’re more likely to want to engage again in the future. I believe the best thing organizations can do is take a multilayered approach to authenticating and identifying people upfront. There are so many ways to do this digitally without disrupting the consumer, and this is the best opportunity for businesses. If we collectively get that right, we’ll stop fraud. T: What are some of the things Experian is focusing on to help businesses stop fraud? K: We’ve focused on our CrossCore® platform. CrossCore is a common access and decisioning capability platform that allows the combining and layering of many different approaches — some active, some passive — to identify a customer in a transaction. You can incorporate things like biometrics and behavioral attributes. You can incorporate digital information about the device you’re engaging with. You can layer in online and offline identity information, like that from our Precise ID® product. CrossCore also enables you to layer in other digital attributes and alternative data such as email address, phone number and the validity of that phone number. CrossCore provides a great opportunity for us to showcase innovation, whether that comes from a third-party partner or even from our own Experian DataLabs. T: How significant do you see machine learning moving forward? K: Machine learning, it has all kinds of names, right? I think of machine learning, artificial intelligence, data robotics, parallel computing — all these things are related to what we used to call big data processing, but that’s not really the trendy term anymore. The point is that there is so much data today. There’s a wealth of data from all different sources, and as a society we’re producing it in exponential volumes. Having more and more and more data is not useful if you can’t derive insights from it. That’s why machine learning, augmented with human intervention or direction, is the best way forward, because there’s so much data out there available in the world now. No matter what problem we’re trying to solve, there’s a wealth of data we can amass, but we need to make sense of it. And the way to make sense of massive amounts of data in a reasonable amount of time is by using some sort of artificial intelligence, or machine learning. We’re going to see it in all kinds of applications. We already are today. So, while I think of machine learning as a generic term, I do think it’s going to be with us for a while to quickly compute and derive meaningful insights from the massive amounts of data all around us. T: Thanks, okay. Last question, and I hope a little fun. How would you describe yourself in one word? K: Curious. T: Ah, that’s a good choice. K: I am always curious. That’s why I love living where I live. It’s why I like working in technology. I’ve always wondered how things work, how we might improve on them, what’s under the hood. Why people make the decisions they do. How does someone come up with this? I’m always curious. T: Well, thank you for the time, and congrats again on being included in the Top 100 influencers in Identity.
Traditional credit attributes provide immense value for lenders when making decisions, but when used alone, they are limited to capturing credit behavior during a single moment of time. To add a deeper layer of insight, Experian® today unveiled new trended attributes, aimed at giving lenders a wider view into consumer credit behavior and patterns over time. Ultimately, this helps them expand into new risk segments and better tailor credit offers to meet consumer needs. An Experian analysis shows that custom models developed using Trended 3DTM attributes provide up to a 7 percent lift in predictive performance when compared with models developed using traditional attributes only. “While trended data has been shown to provide additional insight into a consumer’s credit behavior, lack of standardization across different providers has made it a challenge to gain those insights,” said Steve Platt, Experian’s Group President of Decision Analytics and Data Quality. “Trended 3D makes it easy for our clients to get value from trended data in a consistent manner, so they can make more informed decisions across the credit life cycle and, more importantly, give consumers better access to lending options.” Experian’s Trended 3D attributes help lenders unlock valuable insights hidden within credit reports. For example, two people may have similar balances, utilization and risk scores, but their paths to that point may be substantially different. The solution synthesizes a 24-month history of five key credit report fields — balance, credit limit or original loan amount, scheduled payment amount, actual payment amount and last payment date. Lenders can gain insight into: Changes in balances over time Migration patterns from one tradeline or multiple tradelines to another Variations in utilization and credit limits Changes in payment activity and collections Balance transfer and debt consolidation behavior Behavior patterns of revolving trades versus transactional trades Additionally, Trended 3D leverages machine learning techniques to evaluate behavioral data and recognize patterns that previously may have gone undetected. To learn more information about Experian’s Trended 3D attributes, click here.
Many data furnishers are experiencing increases in dispute rates. It’s a tough spot to be in. Data furnishers are not only obligated under the FCRA to investigate and respond to all consumer disputes – reviewing every Automated Consumer Dispute Verification – but they must also do so within less than 30 days. As the number of disputes rise, resources become taxed and the risk of not meeting Fair Credit Reporting Act (FCRA) obligations increases. Let’s face it, consumer disputes aren’t going away, but understanding the reported data and metrics behind disputes can help data furnishers minimize them and defend reporting strategies and processes. 5 Way to Uncover Data Inaccuracy 1. Gain perspective against the industry and peers. Depending on the industry you service, the general benchmarks for dispute rates can vary. It’s important to understand where you fall in regards to dispute rates. Are you trending high or low? As an annualized average, we’ve recently experienced the following industry dispute rates through the end of the year: However, industry averages are just the tip of the iceberg. Measurement against peers can provide a clearer picture of where you fall. Are you an outlier or on par? How do you respond in comparison to peers? Are you deleting the trade as the result of the dispute at a higher rate? This could be an indicator of a systemic problem that needs addressing. 2. Implement pre-submission quality checks. Once you know where you stand, make sure your data is accurate before it heads out the door and hits the consumer’s credit report. Implement manual checks against Metro 2 rules. Build SQL queries to perform your checks. Better yet, use data validation software to automatically identify, track and remediate errors before sending the file to the bureaus. These steps can catch disputes before they happen. 3. Review any data being rejected after submission. Even if your new reporting motto is ‘know before it goes’; once the data has been transmitted, you’ll still want to monitor data being rejected due to Metro 2® errors. When data is rejected that means the update you provided did not make it to file. This leaves room for disputes. Incorporating a robust review of all rejected data in a timely and detailed manner, with updates made before the next reporting period, can improve the accuracy of your data. 4. Audit to identify and correct any stale data on file. An audit for any stale data - which includes open accounts with a balance greater than zero that have not been updated recently - should be performed at least annually. Review, research and remediate any outdated data that could affect your customer, making it susceptible to a dispute. 5. Educate your customers. Why are your customers disputing? Are there common themes within your customer base? Often, a dispute can be eliminated before it happens, with some explanation on the way an account is reported. By providing proactive access to materials and resources that help demystify the credit reporting process, a potentially negative interaction can be turned into a positive learning opportunity, helping the overall customer experience. Learn more about data accuracy solutions.
The nation’s economic recovery is continuing in a positive upward trend with consumer credit scores coming exceptionally close to pre-recession numbers—the healthiest in a decade. Experian’s 8th annual State of Credit report reveals the nation’s average credit score is up two points year-over-year to 675, and is just four points shy of the 2007 average of 679. “The trend line we are seeing is quite promising,” said Michele Raneri, Experian vice president of analytics and new business development. “With employment and consumer confidence on the rise, the data is indicating that we have made great progress as a country since the recession. The economy is expected to expand at a healthy pace this year and we believe that credit will continue to rebound. All of the factors point towards a good year for credit in 2018.” The study also revealed that year-over-year: Personal loan and auto loan originations increased 11 percent and 6 percent, respectively. The average number of retail cards remains at 2.5 per consumer, while the average retail debt increased $73 to $1,841 per consumer. The average number of bankcards increased slightly from 3.03 to 3.06, with the average card balance also increasing by $166 to $6,354. Instances of late payments (includes bankcard and retail) remained about the same at under 1 percent. And importantly, consumers have a positive outlook with consumer confidence up 25 percent. Top of the credit charts As part of the annual study, Experian analyzed consumer credit habits in U.S. cities. As in previous years, Minnesota continues to stand out with three of its cities — Minneapolis, Rochester and Mankato—leading the way with credit scores of 709, 708 and 708, respectively. Wausau, Wis. (706), Green Bay, Wis. (705) round out the top five. Again, Greenwood, Miss., and Albany, Ga., ranked the lowest with scores of 624 and 626. While still at the bottom of the list, Greenwood and Abany residents did improve their scores by two points. Riverside, Calif.,—fifth on the list—improved its score by four points—the greatest increase of any city in the bottom 10. Generational divide Taking the research further, Experian analyzed consumer credit information by generation, and found: Generation Z (born 1996 and later) is building credit through different methods than the generations before them, with heavier student loan debts and fewer credit cards and department store cards. And they are keeping debts low and managing them well. Generation Y/Millennials (born 1977-1995) have seen their scores climb four points over the past year. They’ve also decreased their overall average debt by nearly eight percent, but have added six percent in mortgage debt. Generation X (born 1965-1976) has a credit score of 658, the highest mortgage debt of all generations, and a high instance of late payments compared to the national average. Their scores have improved, so they are managing their debts better than in the past,. Baby Boomers (born 1946-1964) continue to carry quite a bit of mortgage debt, and have the lowest late payment instances of all the generations. The Silent Generation (born 1945 and before) has quite a bit of mortgage debt, but are keeping other debts low and making payments on time. At 729, they have the best credit score of all generations and the fewest late payments of any generation. To review findings from Experian’s 2017 State of Credit report, join WiseBread’s chat Jan. 18. To register, go to www.wisebread.com and follow #wbchat. To chat with Experian live, and learn more about credit, join #CreditChat hosted by @Experian_US on Twitter every Wednesday at Noon PT/3 p.m. ET.
Alternative Data Shedding New Light on Consumers Why Investors Want Alternative Data Banks and Tech Firms Battle Over Something Akin to Gold: Your Data Alternative data for credit has created national headlines in the past year and a lasting buzz in the financial services world. But what exactly qualifies as alternative data in credit? How can it benefit lenders? Consumers? Ask two people these questions and you may get very different answers. Experian defines alternative data as FCRA-compliant data points that are not typically considered when evaluating a potential customer’s creditworthiness. These data points may include rent payments; utility payments, including gas, electric; telecommunications payments, such as mobile telephones; insurance payments; and any other recurring financial obligations. Taking these alternative data points into account can benefit consumers and lenders in multiple ways. Consider that roughly 45 million Americans have either no credit history, or a credit history that is too scarce or outdated to manufacture a credit score. This group of consumers includes not only minority consumers or those from low income neighborhoods, but also the shared economy workforce and millennials without traditional credit histories. Some estimate 121 million U.S. adults are credit-challenged with thin-to-no credit file and subprime credit scores below 600. “People with little or no credit history, or who lack a credit score, have fewer opportunities to borrow money to build a future, and any credit that is available usually costs more,” said Richard Cordray, while he was director of the Consumer Financial Protection Bureau. Indeed, these consumers are in a catch-22; many lenders will not lend to consumers with credit scores of under 620. In turn, these consumers have trouble building credit, and they are blocked from achieving goals like buying a car, owning a home or starting a business. By combining credit reports with alternative data, a more complete picture of subprime, near-prime and thin-file consumers can develop. And analysis of this data can help lenders evaluate a consumer’s ability to pay. When alternative data like rent payments and an individual’s short term lending history are trended appropriately, it can be an accurate predictor of an individual’s financial behavior, and can be an important step toward promoting greater financial inclusion for more consumers. In addition to using alternative data in underwriting, lenders can leverage the data to help with: Expanding the prospecting universe. Data can be used to enrich batch prospecting decisioning criteria to identify better qualified prospects, suppress high-risk consumers, and offer a more complete borrowing history Account review. Alternative data can help signal a consumer’s financial distress earlier, better manage credit lines and grow relationships with existing consumers. Collections. Identify consumers who are rebuilding credit with specialty finance trades, or who are exhibiting high-risk behaviors in the alternative financial services space. More info on Alternative Credit Data More Info on Alternative Financial Services
It’s no secret. Consumers engage and interact with brands through a variety of channels, including email, direct mail, websites and mobile. And since most organizations work to keep the consumer experience at the core, they tend to invest in an omnichannel approach that caters to the consumer’s preferences. The lone exception may be during the collections process. Often, once an account falls behind on payment, the consumer experience falls behind with it. But should it? While many banks and financial institutions view the collections process merely as an opportunity to collect outstanding debt, the potential is much more. If treated effectively, the collections process can present an opportunity to develop a positive customer relationship that builds loyalty over time. If handled poorly, the collections process could cost an organization a number of lifetime customers. To correct this, banks and financial institutions need to implement the same omnichannel approach in the collections process as they do with every other consumer interaction. Collections can no longer be treated as a linear process that leads from one channel to the next. There needs to be a more personalized touch — communicating with consumers through preferred channels, contacting them at the most opportune times. Sound complex? Sure. But consider a recent Experian analysis that invited consumers to establish a nonthreatening dialogue with an online debt recovery system. The analysis revealed 21 percent of visits to an organization’s website were outside the traditional working hours of 8 a.m. to 8 p.m. Furthermore, of the consumers who committed to a repayment plan, only 56 percent did so in a single visit. Each consumer is different. So is each situation. And banks and financial institutions need to acknowledge those differences. Luckily, technology can address the complexities of an omnichannel and personalized approach. Platforms such as Experian’s PowerCurve® Collections enable banks and financial institutions to simplify the collections process for both the consumer and the organization. By treating the collections process the same as any other stage in the consumer journey, organizations have an opportunity to build a relationship. And to do so, banks and financial institutions need to leverage the data and technology at their disposal. If they do so appropriately, they’ll minimize their charge-offs and also create a lifetime customer. To learn more about leveraging the collections process to build customer loyalty, download our white paper Getting in front of the shift to omnichannel collections.
Experian on the State of Identity podcast In today’s environment, any conversation on the identity management industry needs to include some mention of synthetic identity risk. The fact is, it’s top of mind for almost everyone. Institutions are trying to scope their risk level and identify losses, while service providers are innovating ways to solve the problem. Even consumers are starting to understand the term, albeit via a local newscast designed to scare the heck out of them. With all this in mind, I was very happy to be invited to speak with Cameron D’Ambrosi at One World Identity (OWI) on the State of Identity podcast, focusing on synthetic identity fraud. Our discussion focused on some of the unique findings and recommended best practices highlighted in our recently published white paper on the subject, Synthetic identities: getting real with customers. Additionally, we discussed how a lack of agreement on the definition and size of the synthetic identity problem further complicates the issue. This all stems from inconsistent loss reporting, a lack of confirmable victims and an absence of an exact definition of a synthetic identity to begin with. Discussions must continue to better align us all. I certainly appreciate that OWI dedicated the podcast to this subject. And I hope listeners take away a few helpful points that can assist them in their organization’s efforts to better identify synthetic identities, reduce financial losses and minimize reputation risks.
The data to create synthetic identities is available. And the marketplace to exchange and monetize that data is expanding rapidly. The fact that hundreds of millions of names, addresses, dates of birth, and Social Security numbers (SSNs) have been breached in the last year alone, provides an easy path for criminals to surgically target new combinations of data. Armed with an understanding of the actual associations of these personally identifiable information (PII) elements, fraudsters can better navigate the path to perpetrate identity theft, identity manipulation, or synthetic identity fraud schemes on a grand scale. Using information such as birth dates and addresses in combination with Social Security numbers, criminals can target new combinations of data to yield better results with lower risk of detection. Some examples of this would be: identity theft, existing account takeovers, or the deconstruction and reconstruction of those PII elements to better create effective synthetic identities. Experian has continued to evolve and innovate against fraud risks and attacks with an understanding of attack rates, vectors, and the shifting landscape in data availability and security. In doing so, we’ve historically operated under the assumption that all PII is already compromised in some way or is easily done so. Because of this, we employ a layered approach, providing a more holistic view of an identity and the devices that are used over time by that identity. Relying solely on PII to validate and verify an identity is simply unwise and ineffective in this era of data compromise. We strive to continuously cultivate the broadest and most in-depth set of traditional, innovative and alternative data assets available. To do this, we must enable the integration of diverse identity attributes and intelligence to balance risk, while maintaining a positive customer experience. It’s been quite some time since the use of basic PII verification alone has been predictive of identity risk or confidence. Instead, validation and verification is founded in the ongoing definition and association of identities, the devices commonly used by those individuals, and the historical trends in their behavior. Download our newest White Paper, Synthetic Identities: Getting real with customers, for an in-depth Experian perspective on this increasingly significant fraud risk.
Learn More Image
