Customer Targeting & Segmentation
Alex Lintner, Group President at Experian, recently had the chance to sit down with Peter Renton, creator of the Lend Academy Podcast, to discuss alternative credit data,1 UltraFICO, Experian Boost and expanding the credit universe. Lintner spoke about why Experian is determined to be the leader in bringing alternative credit data to the forefront of the lending marketplace to drive greater access to credit for consumers. “To move the tens of millions of “invisible” or “thin file” consumers into the financial mainstream will take innovation, and alternative data is one of the ways which we can do that,” said Lintner. Many U.S. consumers do not have a credit history or enough record of borrowing to establish a credit score, making it difficult for them to obtain credit from mainstream financial institutions. To ease access to credit for these consumers, financial institutions have sought ways to both extend and improve the methods by which they evaluate borrowers’ risk. By leveraging machine learning and alternative data products, like Experian BoostTM, lenders can get a more complete view into a consumer’s creditworthiness, allowing them to make better decisions and consumers to more easily access financial opportunities. Highlights include: The impact of Experian Boost on consumers’ credit scores Experian’s take on the state of the American consumer today Leveraging machine learning in the development of credit scores Expanding the marketable universe Listen now Learn more about alternative credit data 1When we refer to \"Alternative Credit Data,\" this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term \"Expanded FCRA Data\" may also apply in this instance and both can be used interchangeably.
Once you have kids, your bank accounts will never be the same. From child care to college, American parents spend, on average, over $233,000 raising a child from birth through age 17. While moms and dads are facing the same pile of bills, they often don’t see eye to eye on financial matters. In lieu of Father’s Day, where spending falls $8 million behind Mother’s Day (sorry dads!), we’re breaking down the different spending habits of each parent: Who pays the bills? With 80% of mothers working full time, the days of traditional gender roles are behind us. As both parents share the task of caring for the children, they also both take on the burden of paying household bills. According to Pew Research, when asked to name their kids’ main financial provider, 45% of parents agreed they split the role equally. Many partners are finding it more logical to evenly contribute to shared joint expenses to avoid fighting over finances. However, others feel costs should be divvied up according to how much each partner makes. What do they splurge on? While most parents agree that they rarely spend money on themselves, splurge items between moms and dads differ. When they do indulge, moms often purchase clothes, meals out and beauty treatments. Dads, on the other hand, are more likely to binge on gadgets and entertainment. According to a recent survey on millennial dads, there’s a strong correlation between the domestic tasks they’re taking on and how they’re spending their money. For instance, most dads are involved in buying their children’s books, toys and electronics, as well as footing the bill for their leisure activities. Who are they more likely to spend on? No parent wants to admit favoritism. However, research from the Journal of Consumer Psychology found that you’re more likely to spend money on your daughter if you’re a woman and more likely to spend on your son if you’re a man. The suggested reasoning behind this is that women can more easily identify with their daughters and men with their sons. Overall, parents today are spending more on their children than previous generations as the cost of having children in the U.S. has exponentially grown. How are they spending? When it comes to money management both moms and dads claim to be the “saver” and label the other as the “spender.” However, according to Experian research, there are financial health gaps between men and women, specifically when it pertains to credit. For example, women have 11% less average debt than men, a higher average VantageScore and the same revolving debt utilization of 30%. Even with more credit cards, women have fewer overall debts and are managing to pay those debts on time. There’s no definite way to say whether moms are spending “better” than dads, or vice versa. Rather, each parent has their own strengths and weaknesses when it comes to allocating money and managing expenses. To gain better insight on the different ways consumers are spending money, consider Experian TAPSSM, which allows you to more accurately estimate consumer spend on all general-purpose credit and charge cards over the last 12 months. Learn more about Experian TAPS
Consumer credit trends are continuously changing, making it imperative to keep up with the latest developments in originations, delinquencies on mortgages, credit cards and auto loans. By monitoring consumer behavior and market trends over time, you can predict and prepare for potential issues within each market. In this 30-minute webinar, our featured speakers, Gavin Harding, Experian Senior Business Consultant, and Alan Ikemura, Experian Data Analytics Senior Product Manager, reveal Q1 2019 market intelligence data and explore recent advances in consumer credit trends. Watch our on-demand webinar
You’ve Got Mail! Probably a lot of it. Birthday cards from Mom, a graduation announcement from your third cousin’s kid whose name you can’t remember and a postcard from your dentist reminding you you’re overdue for a cleaning. Adding to your pile, are the nearly 850 pieces of unsolicited mail Americans receive annually, according to Reader’s Digest. Many of these are pre-approval offers or invitations to apply for credit cards or personal loans. While many of these offers are getting to the right mailbox, they’re hitting a changing consumer at the wrong time. The digital revolution, along with the proliferation and availability of technology, has empowered consumers. They now not only have access to an abundance of choices but also a litany of new tools and channels, which results in them making faster, sometimes subconscious, decisions. Three Months Too Late The need to consistently stay in front of customers and prospects with the right message at the right time has caused a shortening of campaign cycles across industries. However, for some financial institutions, the customer acquisition process can take up to 120 days! While this timeframe is extreme, customer prospecting can still take around 45-60 days for most financial institutions and includes: Bureau processing: Regularly takes 10-15 days depending on the number of data sources and each time they are requested from a bureau. Data aggregation: Typically takes anywhere from 20-30 days. Targeting and selection: Generally, takes two to five days. Processing and campaign deployment: Usually takes anywhere from three days, if the firm handles it internally, or up to 10 days if an outside company handles the mailing. A Better Way That means for many firms, the data their customer acquisition campaigns are based off is at least 60 days old. Often, they are now dealing with a completely different consumer. With new card originations up 20% year-over-year in 2019 alone, it’s likely they’ve moved on, perhaps to one of your competitors. It’s time financial institutions make the move to a more modern form of prospecting and targeting that leverages the power of cloud technology, machine learning and artificial intelligence to accelerate and improve the marketing process. Financial marketing systems of the future will allow for advanced segmentation and targeting, dynamic campaign design and immediate deployment all based on the freshest data (no more than 24-48 hours old). These systems will allow firms to do ongoing analytics and modeling so their campaign testing and learning results can immediately influence next cycle decisions. Your customers are changing, isn’t it time the way you market to them changes as well?
The universe has been used as a metaphor for many things – vast, wide, intangible – much like the credit universe. However, while the man on the moon, a trip outside the ozone layer, and all things space from that perspective may seem out of touch, there is a new line of access to consumers. In Experian\'s latest 2019 State of Alternative Credit Data report, consumers and lenders alike weigh in on the growing data set and how they are leveraging the data in use cases across the lending lifecycle. While the topic of alternative credit data is no longer as unfamiliar as it may have been a year or two ago, the capabilities and benefits that can be experienced by financial institutions, small businesses and consumers are still not widely known. Did you know?: - 65% of lenders say they are using information beyond the traditional credit report to make a lending decision. - 58% of consumers agree that having the ability to contribute payment history to their credit file make them feel empowered. - 83% of lenders agree that digitally connecting financial account data will create efficiencies in the lending process. These and other consumer and lender perceptions of alternative credit data are now launched with the latest edition of the State of Alternative Credit Data whitepaper. This year’s report rounds up the different types of alternative credit data (from alternative financial services data to consumer-permissioned account data, think Experian BoostTM), as well as an overview of the regulatory landscape, and a number of use cases across consumer and small business lending. In addition, consumers also have a lot to say about alternative credit data: With the rise of machine learning and big data, lenders can collect more data than ever, facilitating smarter and more precise decisions. Unlock your portfolio’s growth potential by tapping into alternative credit data to expand your consumer universe. Learn more in the 2019 State of Alternative Credit Data Whitepaper. Read Full Report View our 2020 State of Alternative Credit Data Report for an updated look at how consumers and lenders are leveraging alternative credit data.
It’s been over 10 years since the first rumblings of Great Recession started in 2008. Today, Americans are experiencing high levels of consumer confidence, marked by high employment rates and increasing credit balances over last year. What have we learned over the last decade? And how do we compare to our behaviors then? Experian released the 9th annual state of credit report, which provides a comprehensive look at the credit performance of consumers across America by highlighting consumer credit scores and borrowing behaviors. Who’s faring the best since the recession? According to the data, younger consumers. “We’re continuing to see the positive effects of economic recovery, especially among younger consumers,” said Michele Raneri, Vice President of Analytics and Business Development at Experian. “Since the recession, responsible credit card behaviors and lower debt among younger consumers is driving an upward trend in average credit scores across the nation. Over the last ten years, those 18 – 21 increased their credit scores by 23 points on average compared to those 18-21 ten years ago.” As a whole, 2018 was a year marked by financial reform, consumer protection and the return of volatility for the financial markets. A large portion of the analytics from this year’s report took a close look at the credit behaviors of today and compared them to 2008, the year the US headed into the worst recession in 80 years. 10-Year Lookback 2008 2017 2018 Average number of credit cards 3.40 3.06 3.04 Average credit card balances $7,101 $6,354 $6,506 Average number of retail credit cards 3.03 2.48 2.59 Average retail credit card balances $1,759 $1,841 $1,901 Average VantageScore[1,2] 685 675 680 Average revolving utilization 28% 30% 30% Average non-mortgage debt $23,929 $24,706 $25,104 Average mortgage debt $191,357 $201,811 $208,180 Average 30 days past due delinquency rates 5.4% 4.0% 3.9% Average 60 days past due delinquency rates 2.9% 1.9% 1.9% Average 90+ days past due delinquency rates 7.1% 7.3% 6.7% In regards to credit scores, the average VantageScore increased 5 points from last year, reaching 680 , while still down from 2008. Segmented by state and gender, Minnesota had the highest credit scores for both men and women. Data also showed that women had higher credit scores than men, consistent with 2017 and 2008. The past year has been flooded with headlines illustrating increased spending for American consumers. How do the numbers compare with 2008 data? In comparison with 10 years ago, the number of retail trades since 2008 are down, while average balance is up, according to Experian’s State of Credit Report. Additionally, the number of credit cards is down for all age groups, and balance is also down for consumers 22-71 years of age. Average revolving utilization has creeped up in the past decade, but only two percentage points from 28% to 30%, while both average non-mortgage and mortgage debt has increased 5% and 9% respectively. Not surprisingly, the report reflects that delinquency rates have also increased over 20% since 2008, though down from last year. In conclusion, there’s a lot to learn from both 2008 and 2018. One of the most important and resonating takeaways might be that while fortune may not seem to favor the young, younger consumers are exhibiting responsible behaviors and higher credit scores, setting a precedence for consistent and better financial health in the future. Learn more Experian Boost can help consumers instantly improve their credit score by incorporating their positive payment history from utility and phone bills, among other consumer-permissioned data. [1] VantageScore is a registered trademark of VantageScore Solutions, LLC. [2] VantageScore range is 300-850 VantageScore Calculated on the VantageScore 3.0 model. Your VantageScore 3.0 from Experian indicates your credit risk level and is not used by all lenders, so don’t be surprised if your lender uses a score that’s different from your VantageScore 3.0.
Day 2 at this year’s Vision conference was fueled with new technology and inspiration. The morning session opened with Robert Boxberger, Experian President, Decision Analytics, and also featured two live demos, one on Experian’s solution for the upcoming CECL compliance deadline and the second for mobile credit, including two use cases on instant issuance and lead generation, which has resulted in a 28% conversion rate of hot leads for one of Experian’s marquee clients. Keynote Speaker: Aimée Mullins \"Get comfortable with the uncomfortable\" was just one of the mantras shared on Tuesday morning by Aimée Mullins, an actor, Olympian, TEDTalk speaker, and one of the youngest honorees to be inducted into the National Women’s Hall of Fame, among many other accomplishments. “It is our uniqueness that’s our greatest asset that we can leverage for our greatest strength,” said Mullins during her keynote centered on achieving the “impossible.” As a bi-lateral amputee (or “double BK” also known as double below-the-knee amputee, as she referenced), Mullins had doctors and experts tell her and her parents what she would not be able to do. Instead, she encouraged Tuesday’s audience to never stop thinking like a child, to use their curiosity to find new ways where you want to go, and to practice curiosity like a sport to keep from getting comfortable, and therefore static. “It made my not knowing what I can do so much more powerful than an expert\'s presumption of what he thought I could do,” she said. Session Highlights – Day 2 Consumer Trust What engenders trust as consumers? And what does it take to build online trust? With 51% of new account fraud victims personally knowing the perpetrator and 3.4 billion total losses from fraudulent account openings (Javelin Feb 2019), there are five key components to building trust: digital adoption, transparency, fraud management, recognition and authentication. Today’s consumers want to use the digital channel, have both security and ease of access, be recognized, know how their personal information is being used, and engage and trust with biometrics. Artificial Intelligence – Chat Bots and Beyond According to Gartner, “\'Conversational AI-first\' will supersede ‘cloud-first,’ ‘mobile first’ as the most important high-level imperative for the next 10 years.” As evidenced by Google Duplex’s realistic conversations with humans, including the use of “uh” and “um,” conversational AI is positioned to redefine the next generation of human interface, aimed at achieving better customer satisfaction and elevate the customer relationship. Marketing Analytics The marketing analytics landscape is changing. Today’s marketing problems – including the always limited budget and need to produce greater ROI – require tactical strategies to target the right consumers. Enter Experian’s AscendTM marketing platform. Leveraging this tool, including its neural networks that were demonstrated Monday morning, helps gain new insights into consumer behavior. Fraud in the Digital Wild West A panel discussion featuring representatives from Merchant Risk Council, USAA and Alliance Data compared fighting fraud to herding cats. Challenges discussed included the ongoing struggle to find balance between limiting friction during the authentication process, while also protecting customers, as well as fraudsters’ tendencies to tap into victims’ emotions and curiosity (think phishing schemes). As one of the panelists offered as a piece of advice, “Fraudsters share best practices, so should we.” Visibility for the Invisibles People are more than the sum of their parts. The traditional credit score may show a consumer’s reputation, but layering trended and alternative data sets adds their character. Not only can trended data and alternative credit data – including leveraging education attributes – make invisible consumers visible, they can also reveal that a consumer with a presumably superlative credit score is actually a “credit zombie.” These data sets enable the opportunity to create first chances, drive second chances and re-evaluate risk, while also driving a strong growth strategy. CECL After reviewing the basics of CECL and the upcoming deadlines (ranging from Q1 2020 to Q1 2022), a review of CECL compliance challenges and potential product changes preceded a modeling techniques case study and a list of key impacts to businesses. Those impacts include: product profitability, loss forecasting methodology, data management and processes and capital ratios. Experian’s CECL forecasting solution leverages Experian’s extensive historical data and Ascend Analytical Sandbox. Using a best practice modeling pipeline to improve efficiency and reduce operational risks, the solution combines advanced machine learning, traditional model techniques and modeling experience to improve performance and reduce risk of overfitting. Keynote Speaker: Kobe Bryant Kobe Bryant closed out the day with stories from his highly-decorated 20-year career with the Los Angeles Lakers, some tips on trash talk and lessons in leadership. “I had to figure out how to be undeniable,” Bryant said, on competing for minutes at the start of his career. In addition to his basketball legacy, including wining five NBA championships, being named an NBA MVP, a two-time NBA Finals MVP and winning two Olympic gold medals, Bryant also launched the Kobe and Vanessa Bryant Family Foundation, hosts the Kobe Academy and has formed Kobe Inc. He’s a storyteller, an Oscar winner, and his name has become synonymous with standing for uncompromising excellence. How to be successful? “Make sure you have the right people on the team,” Bryant said. “Passionate. Borderline obsessive.” One of his key takeaways from his basketball career that translates to his leadership on and off the court happened when his pre-game and game time thinking shifted from internal to external. “You have to put yourself 2nd, 3rd, 4th…you have to put the team first,” Bryant said. For more coverage, follow #ExperianVision on Twitter or check the Experian Insights LinkedIn page.
“Experian is transforming our business from a traditional credit bureau to a true technology and software provider,” said Craig Boundy, CEO of Experian, North America, as part of his opening remarks Monday morning to kick off the 2019 Experian Vision Conference. “We are committed to working as a force of good.” Covering the themes of financial inclusion, giving consumers control of their lives and better outcomes, a digital-first society, and the latest trends in fraud and security, Boundy addressed a crowd of over 850. Alex Lintner, Experian’s Group President, gave a quick history of the past 3,000 years, from the first credit card, to the addition of wheels to a suitcase, to the iPhone and artificial intelligence. “Innovation is not invention,” Lintner said. He gave the example of the iPhone and how a tear down analysis revealed there were no new elements; however, it was the translation of an idea into a good or service that benefited everyone (as the entire audience raised their hand when asked who had a smart phone). Lintner’s mainstage presentation also featured three live demos, including how the Ascend Technology Platform takes complex model building and outputs from days and weeks to a few clicks, to the incorporation of Small Business Financial Exchange (SBFE) data into the Ascend Analytical Sandbox (incorporating more than 17 years of small business tradeline data and 150 predictive attributes) and lastly, Experian Boost, which according to a live tracker, has boosted consumer credit scores by a total of 3.2 million points, as of this morning, since its launch eight weeks ago. Keynote Speaker: Gary D. Cohn Gary D. Cohn, Former Director of the U.S. National Economic Council, was Monday morning’s keynote speaker. He weighed in on the domestic and global economy, policy issues, financial institutions’ responsibilities and some of his predictions. Cohn brought attention to the ever-changing financial services space, including new forms of encryption and the world of biometric security, calling the financial services industry the “tip of the spear” when it comes to the digitization of the world. Session Highlights - Day 1 Machine Learning From the building blocks of neural networks to artificial intelligence, machine learning has been used in the areas of financial services that do not have adverse actions – think fraud, ID, collections. As we look to harness machine learning for models and other spaces (including adverse action), it’s important to delineate descriptive data (what’s happening now); predictive data (what’s happening in the future); prescriptive data (what am I going to do now); and cognitive data (are we asking the right question?). In addition, it’s necessary to address the five advanced analytic drivers including customer experience, cost, risk and loss, growth and compliance. Home Equity & Lending US macroeconomic trends show consumer confidence is still on an upward trend. While investor confidence is a little volatile, the GDP remains strong (though slightly slowing down) and unemployment is low and forecasted to remain low. Since 2006, the US hasn’t returned in the HELOC space. Mortgage and personal loans are up 20% and 13% respectively, while mortgages have dropped 1% and HELOCs have dropped 2%. With an estimated market potential of over $700 billion, HELOCs may be an untapped credit line given the strength of the economy. Identity Evolution From dumpster divers, aka pulling receipts out of dumpsters behind businesses, to today’s identity-based authentication, there’s been an evolution of how identity is defined as well as its corresponding risks. According to Experian’s Global Fraud & Identity Report, 74% of consumers value security as the most important part of the online experience (over convenience and personalization). However, 74% of consumers abandoned a shopping session that required too much information, and 72% of consumers said they were willing to share more data if it meant a seamless experience. What does this mean? Consumers want it all. Identity today now includes proxies and activity, which can also mean greater risk. Because of aggregators and other associated entities acting on a consumer’s behalf, there are lots of nuances that will need to be looked through. Consumer-Permissioned Data In order to be more consumer-centric, there are four levers through which consumers are given control: data accuracy, knowing their financial profile, the ability to improve their scores (via Experian BoostTM and UltraFICOTM) and protecting consumers when they permission access to their identity credentials. Using Experian Boost, consumers have seen an average increase of 13 points for consumers with positive changes. Additionally, using alternative credit data, financial institutions can score more people and score more accurately. One hundred million consumers could gain greater access to credit with consumer-permissioned data sources. --- Meanwhile, the tech showcase featured over 20 demos covering alternative data, digital credit marketing, consumer empowerment, fraud and identity, integrated decisioning and technology. More insights from Vision to come. Follow @ExperianVision and #ExperianVision on Twitter to see more of the action.
Do more with less. Once the mantra of the life-hacking movement, it seems to be the charge given to marketers across the globe. Reduce waste; increase conversion rates; customize messages at a customer level; and do it all faster and more efficiently (read cheaper) than you did last quarter. The marketing challenges facing all companies seem to be more pronounced for financial institutions – not surprising for an industry with a reputation for late adoption. But doing more with less is not just a catchphrase thrown around by lean-obsessed consultants, it’s a response to key changes and challenges in the market. Here are 3 of the top marketing challenges creating business problems for financial institutions today. Budget constraints and misalignment As someone charged with the marketing remit in your firm, this probably comes as no surprise to you. Marketing budgets are stagnant, if not shrinking. Based on a 2018 report from CMO Survey, marketing budgets represent just over 11% of firm expenditures, a level which has remained largely constant over the last six years.Meanwhile, budgets at many financial firms appear to be out-of-touch with today’s ever-evolving market. In this Financial Brand report, virtually no financial institution committed more than 40% of their budget to mobile marketing, a stat unchanged from the prior two years. More channels mean even more segmentation Gone are the days where a company can rely heavily on traditional media to reach targets and clients. Now more than ever, your customers have access to a compounding amount of media on a proliferating number of channels. Some examples: In 2018, the Pew Research Center found most Americans (68%) get their news from social media. Cable companies recently followed streaming services to offer seamless service and experience across TV, desktop and mobile. Apple and Disney are two of several media juggernauts who are throwing their new streaming services and networks into the ring.This level of access is driving a shift in customers’ expectations for how, when and where they consume content. They want custom messages delivered in a seamless experience across the various channels they use. Shorter campaign cycles According to a recent study by Microsoft, humans now have shorter attention spans, at 8 seconds, than goldfish at 9 seconds. This isn’t surprising considering the levels of digital reach and access your customers are presented with. But this is also forcing a shortening of content and campaign cycles in response. Marketers are now expected to plan, launch and analyze engaging campaigns to meet and stay ahead of customer need and expectation. Ironically, while there’s an intentional shortening of campaign cycles, there’s also a corporate focus to prolong and grow the customer relationship. It’s clear, competing in today’s world requires transforming your organization to address rapidly increasing complexity while containing costs. Competing against stagnant marketing budgets, proliferating media channels and shorter campaign cycles while delivering results is a formidable task, especially if your financial institution is not effectively leveraging data and analytics as differentiators. CMOs and their marketing teams must invest in new technologies and revisit product and channel strategies that reflect the expectations of their customers. How is your bank or credit union responding to these financial marketing challenges? Download Customer Acquisition eBook
Your consumers’ credit score plays an important role in how lenders and financial institutions measure their creditworthiness and risk. With a good credit score, which is generally defined as a score of 700 or above, they can quickly be approved for credit cards, qualify for a mortgage, and have easier access to loans with lower interest rates. In the spirit of Financial Literacy Month, we’ve rounded up what it takes for consumers to have a good credit score, in addition to some alternative considerations. Pay on Time Life gets busy and sometimes your consumers miss the “credit card payment due” note on their calendar squished between their work meetings and doctor’s appointment. However, payment history is one of the top factors in most credit scoring models and accounts for 35% of their credit score. As the primary objective of your consumers’ credit score is to illustrate to lenders just how likely they are to repay their debts, even one missed payment can be viewed negatively when reviewing their credit history. However, if there is a missed payment, consider checking their alternative financial services payments. They may have additional payment histories that will skew their creditworthiness more so than just their record according to traditional credit lines alone. Limit Credit Cards When your consumers apply for a new loan or credit card, lenders “pull” their credit report(s) to review their profile and weigh the risk of granting them credit or loan approval. The record of the access to their credit reports is known as a “hard” inquiry and has the potential to impact their credit score for up to 12 months. Plus, if they’re already having trouble using their card responsibly, taking on potential new revolving credit could impact their balance-to-limit ratio. For your customers that may be looking for new cards, Experian TAPSSM can be used to accurately estimate your consumers spend on all general-purpose credit and charge cards, so you can identify where there is additional wallet share and assign their credit lines based on actual spending need. Have a Lengthy Credit History The longer your consumers’ credit history, the more time they’ve spent successfully managing their credit obligations. When considering credit age, which makes up 21% of their credit score, credit scoring models evaluate the ages of your consumers’ oldest and newest accounts, along with the average age of all their accounts. Every time they open new credit cards or close an old account, the average age of their credit history is impacted. If your consumer’s score is being negatively affected by their credit history, consider adding information from alternative credit data sources for a more complete view. Manage Debt Wisely While some types of debt, such as a mortgage, can help build financial health, too much debt may lead to significant financial problems. By planning, budgeting, only borrowing when it makes sense, and setting themselves up for unexpected financial expenses, your consumers will be on the path to effective debt management. To get a better view of your consumers spending, consider Experian’s Trended3DTM, a trended attribute set that helps lenders unlock valuable insights hidden within their consumers’ credit scores. By using Trended3DTM data attributes, you’ll be able to see how much of your consumers’ credit line they typically utilize, whether they tend to revolve or transact, and if they are likely to transfer a balance. By adopting these habits and making smart financial decisions, your consumers will quickly realize that it’s never too late to rebuild their credit score. For example, they can potentially instantly improve their score with Experian Boost, an online tool that scans their bank account transactions to identify mobile phone and utility payments. The positive payments are then added to their Experian credit file and increase their FICO® Score in real time. Learn More About Experian Boost Learn More About Experian TAPS
If you’re a credit risk manager or a data scientist responsible for modeling consumer credit risk at a lender, a fintech, a telecommunications company or even a utility company you’re certainly exploring how machine learning (ML) will make you even more successful with predictive analytics. You know your competition is looking beyond the algorithms that have long been used to predict consumer payment behavior: algorithms with names like regression, decision trees and cluster analysis. Perhaps you’re experimenting with or even building a few models with artificial intelligence (AI) algorithms that may be less familiar to your business: neural networks, support vector machines, gradient boosting machines or random forests. One recent survey found that 25 percent of financial services companies are ahead of the industry; they’re already implementing or scaling up adoption of advanced analytics and ML. My alma mater, the Virginia Cavaliers, recently won the 2019 NCAA national championship in nail-biting overtime. With the utmost respect to Coach Tony Bennett, this victory got me thinking more about John Wooden, perhaps the greatest college coach ever. In his book Coach Wooden and Me, Kareem Abdul-Jabbar recalled starting at UCLA in 1965 with what was probably the greatest freshman team in the history of basketball. What was their new coach’s secret as he transformed UCLA into the best college basketball program in the country? I can only imagine their surprise at the first practice when the coach told them, “Today we are going to learn how to put on our sneakers and socks correctly. … Wrinkles cause blisters. Blisters force players to sit on the sideline. And players sitting on the sideline lose games.” What’s that got to do with machine learning? Simply put, the financial services companies ready to move beyond the exploration stage with AI are those that have mastered the tasks that come before and after modeling with the new algorithms. Any ML library — whether it’s TensorFlow, PyTorch, extreme gradient boosting or your company’s in-house library — simply enables a computer to spot patterns in training data that can be generalized for new customers. To win in the ML game, the team and the process are more important than the algorithm. If you’ve assembled the wrong stakeholders, if your project is poorly defined or if you’ve got the wrong training data, you may as well be sitting on the sideline. Consider these important best practices before modeling: Careful project planning is a prerequisite — Assemble all the key project stakeholders, and insist they reach a consensus on specific and measurable project objectives. When during the project life cycle will the model be used? A wealth of new data sources are available. Which data sources and attributes are appropriate candidates for use in the modeling project? Does the final model need to be explainable, or is a black box good enough? If the model will be used to make real-time decisions, what data will be available at runtime? Good ML consultants (like those at Experian) use their experience to help their clients carefully define the model development parameters. Data collection and data preparation are incredibly important — Explore the data to determine not only how important and appropriate each candidate attribute is for your project, but also how you’ll handle missing or corrupt data during training and implementation. Carefully select the training and validation data samples and the performance definition. Any biases in the training data will be reflected in the patterns the algorithm learns and therefore in your future business decisions. When ML is used to build a credit scoring model for loan originations, a common source of bias is the difference between the application population and the population of booked accounts. ML experts from outside the credit risk industry may need to work with specialists to appreciate the variety of reject inference techniques available. Segmentation analysis — In most cases, more than one ML model needs to be built, because different segments of your population perform differently. The segmentation needs to be done in a way that makes sense — both statistically and from a business perspective. Intriguingly, some credit modeling experts have had success using an AI library to inform segmentation and then a more tried-and-true method, such as regression, to develop the actual models. During modeling: With a good plan and well-designed data sets, the modeling project has a very good chance of succeeding. But no automated tool can make the tough decisions that can make or break whether the model is suitable for use in your business — such as trade-offs between the ML model’s accuracy and its simplicity and transparency. Engaged leadership is important. After modeling: Model validation — Your project team should be sure the analysts and consultants appreciate and mitigate the risk of over fitting the model parameters to the training data set. Validate that any ML model is stable. Test it with samples from a different group of customers — preferably a different time period from which the training sample was taken. Documentation — AI models can have important impacts on people’s lives. In our industry, they determine whether someone gets a loan, a credit line increase or an unpleasant loss mitigation experience. Good model governance practice insists that a lender won’t make decisions based on an unexplained black box. In a globally transparent model, good documentation thoroughly explains the data sources and attributes and how the model considers those inputs. With a locally transparent model, you can further explain how a decision is reached for any specific individual — for example, by providing FCRA-compliant adverse action reasons. Model implementation — Plan ahead. How will your ML model be put into production? Will it be recoded into a new computer language, or can it be imported into one of your systems using a format such as the Predictive Model Markup Language (PMML)? How will you test that it works as designed? Post-implementation — Just as with an old-fashioned regression model, it’s important to monitor both the usage and the performance of the ML model. Your governance team should check periodically that the model is being used as it was intended. Audit the model periodically to know whether changing internal and external factors — which might range from a change in data definition to a new customer population to a shift in the economic environment — might impact the model’s strength and predictive power. Coach Wooden used to say, “It isn’t what you do. It’s how you do it.” Just like his players, the most successful ML practitioners understand that a process based on best practices is as important as the “game” itself.
So often a microscope is set on examining millennials and their behaviors – especially when it comes to their priorities and finances. But there’s a new generation entering the economy, with an entirely new set of preferences, behaviors and approach to money. Enter Gen Z. According to Bloomberg, this year, Generation Z becomes the biggest consumer cohort globally, “displacing millennials as a top obsession for investors.” This generation (falling between the ages of seven and 22) is 61 million strong and has a spending power of $143 billion in the U.S. alone. While much of the population that makes up Generation Z may still be in school, they are already creating their reputation as conscientious consumers. And lenders and financial institutions need to get in front of them if they want a chance at these meaningful investments. Because this generation has grown up in a world where the internet has always existed, everything can be ordered and delivered on demand, and communications occur over mobile platforms like Instagram and Snapchat, they view the world – and finances – through a different lens. Bloomberg suggests the following Gen Z broad trends; which investors should consider if they want this growing generation in their portfolios: They can be influenced. According to a recent Bloomberg survey, 52% of Gen Zers said they primarily find out about new products from social media. And they are 3 times more likely to purchase a product recommended by one of their favorite influencers than by a television or film celebrity. They have different vices – beyond just their smartphone addictions. As they are growing up in a world where screen time is eminent and cannabis is becoming legal (already legal in 10 U.S. states), they live with a different world view than many of the other generations. They don’t have to go to stores. Gen Z shops via clicks, not bricks. They choose their brand loyalties carefully. This generation is interested in environmental issues and ethical shopping, which drives their consumer activities, meaning it’s time for new considerations when it comes to marketing. They eat differently. Less likely to eat meat, we’re already seeing the shift that fast-food restaurants and packaged-food distributors are taking. What does this mean for financial institutions? You don’t have to be a social media influencer to get Gen Z in your portfolio – but it wouldn’t hurt. Many reports indicate that by 2020, Gen Z will command nearly 40% of all consumer shopping. With shopping driven by scrolling and purpose-driven purchases facilitated primarily by online transactions, gaining an understanding of these young consumers’ credit and charge card habits means you can better understand bankcard wallet share and target them as they start joining the workforce and beyond. In the not-too-distant future, there will be a need to examine high spend to increase interchange income. Trended data solutions can gain insight into these consumers as well as help you target and offer new lines of credit as they purchase with purpose – fueling them with credit to fund the ventures that matter to them most. Learn More
A court in a Northern China province has developed a mobile app designed to enforce court rulings and create a socially credible environment. The app, which can be accessed via WeChat, China\'s most popular instant messaging platform, is designed to alert users when they are within a 500-meter radius of someone in debt. Users will get personal information about the debtors, including their exact location, names, national ID numbers, and why they have a low score. It\'s the latest innovation to become integrated into China\'s social credit system. What is a social credit system? China\'s social credit system, which will be enforced in 2020, aims to standardize the social reputation of citizens and businesses. It will rank citizens by attaching a score to various aspects of their social life - ranging from paying court fees to drinking alcohol to failing to pay bills. Although there are proposed consequences for low scorers, including travel bans and loan declines, 80% of citizens recently surveyed by the Washington Post support it. While the app seems like it could be a plotline from a \"Black Mirror\" episode, with its emphasis on reputation scoring and location-based activation, there are reasons it makes sense for the rather remote northern province. With many people in China still not having formal access to traditional banks, being able to alternatively assess their trustworthiness and risk could provide them the ability to access loans, rent houses, and even send their children to school. Additionally, to increase their scores, Chinese citizens are displaying improved behavior. China isn\'t the first country to attempt to gain a robust understanding of its consumers through alternative data sources. While U.S. financial institutions have experimented with using social media as a factor in determining a borrower\'s risk, Philippines-based Lenddo, a world leader in scoring and identity verification technology, is doing that and more. The company looks at social media, email, and mobile headset activity to determine repayment ability. Moreover, Discovery Bank in South Africa believes there\'s a correlation between fiscal responsibility and physical health. The South African bank plans to begin tracking the habits of its 4.4 million customers and offering better deals to those who are living a healthier lifestyle. For example, consumers can earn points for visiting the gym, getting a flu shot, or buying healthy groceries. The more points a consumer collects the better deals and savings they\'ll receive. The willingness to share data is not a characteristic unique to South African or Chinese citizens. A recent Accenture study of 47,000 banking and insurance customers showed that consumers are willing to share personal data in exchange for better customer assistance and discounts on products and services. The full extent of the impact on social credit to Chinese citizens is impossible to calculate, simply because the system doesn\'t fully exist yet. However, it does serve as an example of the many ways that credit scoring and the use of customer-permissioned data are evolving. Long gone are the days of mailing checks, ordering from a catalog, or even needing to carry cash. What\'s next?
Perhaps the most reliable mailbox tenant, thick envelopes splashed with “limited time offer” or other flashy designations offering various card and credit products – otherwise known as prescreen offers – are a mainstay in many households. What is prescreen? Prescreen is a process that happens behind-the-scenes where a lender screens a consumer’s credit to determine whether to extend a firm offer of credit. The process takes place without the consumer’s knowledge and without any negative impact to their credit score. For lenders and financial institutions, a prescreen is a way to pick and choose the criteria of the consumers you want to target for a particular offer – often in the form of better terms, interest rates or incentives. Typically, a list of consumers meeting specific credit criteria is compiled by a Credit Reporting Agency, like Experian, and then provided to the requesting lending institutions or their mailing service. In other words? Increase response rates and conversion by targeting the right consumers and eliminating unqualified prospects. Additionally, prescreening consumers also reduces high-risk accounts, targeting the best prospects in order to reach them at the right time with the right offer for their needs. Important to note: a prescreen is not the same thing as a prequalification. Gone are the days of batch-and-blasting. It’s expensive and a challenge for constantly limited marketing budgets. Prescreen decreases acquisition and mailing costs by segmenting a lender’s prospect list. In one case, a lender experienced a 10% lift in its overall conversion rate with a single campaign by targeting individuals who were most likely to respond to their over. Governed by the Fair Credit Reporting Act (FCRA), lenders initiating prescreen campaigns for credit products must also adhere to certain rules. What qualifies one of these campaigns? A firm offer of credit An inquiry posting is required (though it is a “soft” inquiry) Consumers also have the option to opt out of preapproved and prescreen credit offer lists In addition to acquisitions via direct mail, there are various types of prescreen tailored to the multiple channels where marketing takes place in today’s world. For example, Instant Prescreen can increase new account acquisitions by performing the preapproval process in seconds, while the customer is on your website, on the phone with you or at your business. Similar to how you might screen calls on your cell phone by letting them go to your voicemail inbox or screen candidates’ resumes before inviting them for an interview for an open position at your company, a prescreened credit offer is not much different. Focusing on your audience that is most likely to respond to your offers is an easy way to increase your ROI and should be considered a best practice when it comes to your marketing efforts. Learn More About Prescreen
Are You #TeamTrended or #TeamAlternative? There’s no such thing as too much data, but when put head to head, differences between the data sets are apparent. Which team are you on? Here’s what we know: With the entry and incorporation of alternative credit data into the data arena, traditional credit data is no longer the sole determinant for credit worthiness, granting more people credit access. Built for the factors influencing financial health today, alternative credit data essentially fills the gaps of the traditional credit file, including alternative financial services data, rental payments, asset ownership, utility payments, full file public records, and consumer-permissioned data – all FCRA-compliant data. Watch this video to see more: Trended data, on the other hand shows actual, historical credit data. It provides key balance and payment data for the previous 24 months to allow lenders to leverage behavior trends to determine how individuals are utilizing their credit. Different splices of that information reveal particular behavior patterns, empowering lenders to then act on that behavior. Insights include a consumer’s spend on all general purpose credit and charge cards and predictive metrics that identify consumers who will be in the market for a specific type of credit product. In the head-to-head between alternative credit data and trended data, both have clear advantages. You need both on your roster to supplement traditional credit data and elevate your game to the next level when it comes to your data universe. Compared to the traditional credit file, alternative credit data can reveal information differentiating two consumers. In the examples below, both consumers have moderate limits and have making timely credit card payments according to their traditional credit reports. However, alternative data gives insight into their alternative financial services information. In Example 1, Robert Smith is currently past due on his personal loan, whereas Michelle Lee in Example 2 is current on her personal loan, indicating she may be the consumer with stronger creditworthiness. Similarly, trended data reveals that all credit scores are not created equal. Here is an example of how trended data can differentiate two consumers with the same score. Different historical trends can show completely different trajectories between seemingly similar consumers. While the traditional credit score is a reliable indication of a consumer’s creditworthiness, it does not offer the full picture. What insights are you missing out on? Go to Infographic Get Started Today
Learn More Image
