Customer Targeting & Segmentation
With Hispanic Heritage Awareness Month underway and strategic planning season in full swing, the topic of growing membership continues to take front stage for credit unions. Miriam De Dios Woodward (CEO of Coopera Consulting) is an expert on the Hispanic opportunity, working with credit unions to help them grow by expanding the communities they serve. I asked Miriam if she could provide her considerations for credit unions looking to further differentiate their offerings and service levels in 2019 and beyond. There’s never been a better time for credit unions to start (or grow) Hispanic engagement as a differentiation strategy. Lending deeper to this community is one key way to do just that. Financial institutions that don’t will find it increasingly difficult to grow their membership, deposits and loan balances. As you begin your 2019 strategic planning discussions, consider how your credit union could make serving the Hispanic market a differentiation strategy. Below are nine ways to start. 1. Understand your current membership and market through segmentation and analytics. The first step in reaching Hispanics in your community is understanding who they are and what they need. Segment your existing membership and market to determine how many are Hispanic, as well as their language preferences. Use this segmentation to set a baseline for growth of your Hispanic growth strategy, measure ongoing progress and develop new marketing and product strategies. If you don’t have the bandwidth and resources to conduct this segmentation in-house, seek partners to help. 2. Determine the product gaps that exist and where you can deepen relationships. After you understand your current Hispanic membership and market, you will want to identify opportunities to improve the member experience, including your lending program. For example, if you notice Hispanics are not obtaining mortgages at the same rate as non-Hispanics, look at ways to bridge the gaps and address the root causes (i.e., more first-time homebuyer education and more collaboration with culturally relevant providers across the homebuying experience). Also, consider how you might adapt personal loans to meet the needs of consumers, such as paying for immigration expenses or emergencies with family in Latin America. 3. Explore alternative credit scoring models. Many credit products accessible to underserved consumers feature one-size-fits-all rates and fees, which means they aren’t priced according to risk. Just because a consumer is unscoreable by most traditional credit scoring models doesn’t mean he or she won’t be able to pay back a loan or does not have a payment history. Several alternative models available today can help lenders better evaluate a consumer’s ability to repay. Alternative sources of consumer data, such as utility records, cell phone payments, medical payments, insurance payments, remittance receipts, direct deposit histories and more, can be used to build better risk models. Armed with this information – and with the proper programs in place to ensure compliance with regulatory requirements and privacy laws – credit unions can continue making responsible lending decisions and grow their portfolio while better serving the underserved. 4. Consider how you can help more Hispanic members realize their desire to become homeowners. In 2017, more than 167,000 Hispanics purchased a first home, taking the total number of Hispanic homeowners to nearly 7.5 million (46.2 percent of Hispanic households). Hispanics are the only demographic to have increased their rate of homeownership for the last three consecutive years. What’s more, 9 percent of Hispanics are planning to buy a house in the next 12 months, compared to 6 percent of non-Hispanics. This means Hispanics, who represent about 18 percent of the U.S. population, may represent 22 percent of all new home buyers in the next year. By offering a variety of home loan options supported by culturally relevant education, credit unions can help more Hispanics realize the dream of homeownership. 5. Go beyond indirect lending for auto loans. The number of cars purchased by Hispanics in the U.S. is projected to double in the period between 2010 and 2020. It’s estimated that new car sales to Hispanics will grow by 8 percent over the next five years, compared to a 2 percent decline among the total market. Consider connecting with local car dealers that serve the Hispanic market. Build a pre-car buying relationship with members rather than waiting until after they’ve made their decision. Connect with them after they’ve made the purchase, as well. 6. Consider how you can help Hispanic entrepreneurs and small business owners. Hispanics are nine times more likely than whites to take out a small business loan in the next five years. Invest in products and resources to help Hispanic entrepreneurs, such as small business-friendly loans, microloans, Individual Taxpayer Identification Number (ITIN) loans, credit-building loans and small-business financial education. Also, consider partnering with organizations that offer small business assistance, such as local Hispanic chambers of commerce and small business incubators. 7. Rethink your credit card offerings. Credit card spending among underserved consumers has grown rapidly for several consecutive years. The Center for Financial Services Innovation (CFSI) estimates underserved consumers will spend $37.6 billion on retail credit cards, $8.3 billion on subprime credit cards and $0.4 billion on secured credit cards in 2018. Consider mapping out a strategy to evolve your credit card offerings in a way most likely to benefit the unique underserved populations in your market. Finding success with a credit-builder product like a secured card isn’t a quick fix. Issuers must take the necessary steps to comply with several regulations, including Ability to Repay rules. Cards and marketing teams will need to collaborate closely to execute sales, communication and, importantly, cardmember education plans. There must also be a good program in place for graduating cardmembers into appropriate products as their improving credit profiles warrant. If offering rewards-based products, ensure the rewards include culturally relevant offerings. Work with your credit card providers. 8. Don’t forget about lines of credit. Traditional credit lines are often overlooked as product offerings for Hispanic consumers. These products can provide flexible funding opportunities for a variety of uses such as making home improvements, helping family abroad with emergencies, preparing families for kids entering college and other expenses. Members who are homeowners and have equity in their homes have a potential untapped source to borrow cash. 9. Get innovative. Hispanic consumers are twice as likely to research financial products and services using mobile apps. Many fintech companies have developed apps to help Hispanics meet immediate financial needs, such as paying off debt and saving for short-term goals. Others encourage long-term financial planning. Still other startups have developed new plans that are basically mini-loans shoppers can take out for specific purchases when checking out at stores and online sites that participate. Consider how your credit union might partner with innovative fintech companies like these to offer relevant, digital financial services to Hispanics in your community. Next Steps Although there’s more to a robust Hispanic outreach program than we can fit in one article, credit unions that bring the nine topics highlighted above to their 2019 strategic planning sessions will be in an outstanding position to differentiate themselves through Hispanic engagement. Experian is proud to be the only credit bureau with a team 100% dedicated to the Credit Union movement and sharing industry best practices from experts like Miriam De Dios Woodward. Our continued focus is providing solutions that enable credit unions to continue to grow, protect and serve their field of membership. We can provide a more complete view of members and potential members credit behavior with alternative credit data. By pulling in new data sources that include alternative financing, utility and rental payments, Experian provides credit unions a more holistic picture, helping to improve credit access and decisioning for millions of consumers who may otherwise be overlooked. About Miriam De Dios Woodward Miriam De Dios Woodward is the CEO of Coopera, a strategy consulting firm that helps credit unions and other organizations reach and serve the Hispanic market as an opportunity for growth and financial inclusion. She was named a 2016 Woman to Watch by Credit Union Times and 2015 Latino Business Person of the Year by the League of United Latin American Citizens of Iowa. Miriam earned her bachelor’s degree from Iowa State University, her MBA from the University of Iowa and is a graduate of Harvard Business School’s Leading Change and Organizational Renewal executive program.
Machine learning (ML), the newest buzzword, has swept into the lexicon and captured the interest of us all. Its recent, widespread popularity has stemmed mainly from the consumer perspective. Whether it’s virtual assistants, self-driving cars or romantic matchmaking, ML has rapidly positioned itself into the mainstream. Though ML may appear to be a new technology, its use in commercial applications has been around for some time. In fact, many of the data scientists and statisticians at Experian are considered pioneers in the field of ML, going back decades. Our team has developed numerous products and processes leveraging ML, from our world-class consumer fraud and ID protection to producing credit data products like our Trended 3DTM attributes. In fact, we were just highlighted in the Wall Street Journal for how we’re using machine learning to improve our internal IT performance. ML’s ability to consume vast amounts of data to uncover patterns and deliver results that are not humanly possible otherwise is what makes it unique and applicable to so many fields. This predictive power has now sparked interest in the credit risk industry. Unlike fraud detection, where ML is well-established and used extensively, credit risk modeling has until recently taken a cautionary approach to adopting newer ML algorithms. Because of regulatory scrutiny and perceived lack of transparency, ML hasn’t experienced the broad acceptance as some of credit risk modeling’s more utilized applications. When it comes to credit risk models, delivering the most predictive score is not the only consideration for a model’s viability. Modelers must be able to explain and detail the model’s logic, or its “thought process,” for calculating the final score. This means taking steps to ensure the model’s compliance with the Equal Credit Opportunity Act, which forbids discriminatory lending practices. Federal laws also require adverse action responses to be sent by the lender if a consumer’s credit application has been declined. This requires the model must be able to highlight the top reasons for a less than optimal score. And so, while ML may be able to deliver the best predictive accuracy, its ability to explain how the results are generated has always been a concern. ML has been stigmatized as a “black box,” where data mysteriously gets transformed into the final predictions without a clear explanation of how. However, this is changing. Depending on the ML algorithm applied to credit risk modeling, we’ve found risk models can offer the same transparency as more traditional methods such as logistic regression. For example, gradient boosting machines (GBMs) are designed as a predictive model built from a sequence of several decision tree submodels. The very nature of GBMs’ decision tree design allows statisticians to explain the logic behind the model’s predictive behavior. We believe model governance teams and regulators in the United States may become comfortable with this approach more quickly than with deep learning or neural network algorithms. Since GBMs are represented as sets of decision trees that can be explained, while neural networks are represented as long sets of cryptic numbers that are much harder to document, manage and understand. In future blog posts, we’ll discuss the GBM algorithm in more detail and how we’re using its predictability and transparency to maximize credit risk decisioning for our clients.
Consumer confidence is nearing an 18-year high. Unemployment figures are at record lows. Retail spend is healthy, and expected to stay that way through the back-to-school and holiday shopping booms. Translation for credit card issuers? The swiping and spending continue. In fact, credit card openings were up 4% in the first quarter of 2018 compared to the same time last year, and card utilization is hovering around 20.5%. Even with the Fed’s gradual 2018 rate hikes, consumers are shopping. In a new Mintel report, outstanding credit card debt is now $1.03 trillion (as of the end of Q1, 2018), and the number of consumers with credit cards is growing fastest among people aged 18 to 34. In the retail card arena specifically, boomers and Gen X’ers are leading the charge, opening 45% and 27% of new retails cards, respectively. “A stronger economy always bodes well for credit cards,” said Kelley Motley, director of analytics for Experian. “Now is the time for card issuers to zero in on their most loyal consumers and ensure they are treating them with the right offers, rewards and premium benefits.” Consumer data reveals the top incentives when selecting a rewards-based card includes cash back, gas rewards and retail cards (including travel rewards and airfare). In fact, for younger consumers, offering rewards has proven to be the most effective way to get them to switch from debit to credit cards. Cash back was the most preferred reward for consumers aged 18 to 44 when asked about their motivation to apply for a new card. For individuals 45 and older, 0% interest was the top motivator. Of course, beyond credit card opens, the ideal is to engage with the consumers who are utilizing the card the most. From a segmentation standpoint, the loyal retail cardholder has an average VantageScore® of 671 with an average total balance of $1,633. They use the card regularly and consistently make payments. Finding more loyalists is the goal and can be achieved with informed segmentation insights and targeted prescreen campaigns. On the flip side, insights can inform card issuers with data, helping them to avoid wasting marketing dollars on consumers who merely want to game a quick credit card offer and then close an account. A batch and blast marketing approach no longer works in the credit card marketing game. “Consumers expect you to know them and their financial needs,” said Paul DeSaulniers, senior director of Experian’s segmentation solutions. “The data exists and tells you exactly who to target and how to structure the offer – you just need to execute.”
As more financial institutions express interest and leverage alternative credit data sources to decision and assess consumers, lenders want to be assured of how they can best utilize this data source and maintain compliance. Experian recently interviewed Philip Bohi, Vice President for Compliance Education for the American Financial Services Association (AFSA), to learn more about his perspective on this topic, as well as to gain insights on what lenders should consider as they dive into the world of alternative credit data. Alternative data continues to be a hot topic in the financial services space. How have you seen it evolve over the past few years? It’s hard to pinpoint where it began, but it has been interesting to observe how technology firms and people have changed our perceptions of the value and use of data in recent years. Earlier, a company’s data was just the information needed to conduct business. It seems like people are waking up to the realization that their business data can be useful internally, as well as to others. And we have come to understand how previously disregarded data can be profoundly valuable. These insights provide a lot of new opportunities, but also new questions. I would also say that the scope of alternative credit data use has changed. A few years ago, alternative credit data was a tool to largely address the thin- and no-file consumer. More recently, we’ve seen it can provide a lift across the credit spectrum. We recently conducted a survey with lenders and 23% of respondents cited “complying with laws and regulations” as the top barrier to utilizing alternative data. Why do you think this is the case? What are the top concerns you hear from lenders as it relates to compliance on this topic? The consumer finance industry is very focused on compliance, because failure to maintain compliance can kill a business, either directly through fines and expenses, or through reputation damage. Concerns about alternative data come from a lack of familiarity. There is uncertainty about acquiring the data, using the data, safeguarding the data, selling the data, etc. Companies want to feel confident that they know where the limits are in creating, acquiring, using, storing and selling data. Alternative data is a broad term. When it comes to utilizing it for making a credit decision, what types of alternative data can actually be used? Currently the scope is somewhat limited. I would describe the alternative data elements as being analogous to traditional credit data. Alternative data includes rent payments, utility payments, cell phone payments, bank deposits, and similar records. These provide important insights into whether a given consumer is keeping up with financial obligations. And most importantly, we are seeing that the particular types of obligations reflected in alternative data reflect the spending habits of people whose traditional credit files are thin or non-existent. This is a good thing, as alternative data captures consumers who are paying their bills consistently earlier than traditional data does. Serving those customers is a great opportunity. If a lender wants to begin utilizing alternative credit data, what must they know from a compliance standpoint? I would begin with considering what the lender’s goal is and letting that guide how it will explore using alternative data. For some companies, accessing credit scores that include some degree of alternative data along with traditional data elements is enough. Just doing that provides a good business benefit without introducing a lot of additional risk as compared to using traditional credit score information. If the company wants to start leveraging its own customer data for its own purposes, or making it available to third parties, that becomes complex very quickly. A company can find itself subject to all the regulatory burdens of a credit-reporting agency very quickly. In any case, the entire lifecycle of the data has to be considered, along with how the data will be protected when the data is “at rest,” “in use,” or “in transit.” Alternative data used for credit assessment should additionally be FCRA-compliant. How do you see alternative credit data evolving in the future? I cannot predict where it will go, but the unfettered potential is dizzying. Think about how DNA-based genealogy has taken off, telling folks they have family members they did not know and providing information to solve old crimes. I think we need to carefully balance personal privacy and prudent uses of customer data. There is also another issue with wide-ranging uses of new data. I contend it takes time to discern whether an element of data is accurately predictive. Consider for a moment a person’s utility bills. If electricity usage in a household goes down when the bills in the neighborhood are going up, what does that tell us? Does it mean the family is under some financial strain and using the air conditioning less? Or does it tell us they had solar panels installed? Or they’ve been on vacation? Figuring out what a particular piece of data means about someone’s circumstances can be difficult. About Philip Bohi Philip joined AFSA in 2017 as Vice President, Compliance Education. He is responsible for providing strategic direction and leadership for the Association’s compliance activities, including AFSA University, and is the staff liaison to the Operations and Regulatory Compliance Committee and Technology Task Forces. He brings significant consumer finance legal and compliance experience to AFSA, having served as in-house counsel at Toyota Motor Credit Corporation and Fannie Mae. At those companies, Philip worked closely with compliance staff supporting technology projects, legislative tracking, and vendor management. His private practice included work on manufactured housing, residential mortgage compliance, and consumer finance matters at McGlinchey Stafford, PLLC and Lotstein Buckman, LLP. He is a member of the Virginia State Bar and the District of Columbia Bar. Learn more about the array of alternative credit data sources available to financial institutions.
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.
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
Hispanics are not only the fastest growing minority in the United States, but according to the Hispanic Wealth Project’s (HWP) 2017 State of Hispanic Homeownership Report, they would prefer to own a home rather than rent. Hispanic Millennials—who are entering their home-buying years—are particularly eager for homeownership. This group is educated, are entrepreneurs and business owners that over index on mobile use, and 9 of 10 say wanting to own a home is part of their Hispanic DNA. For them, it’s not a matter of if but when and how they will become homeowners. An optimistic outlook is also a trait of Hispanic Millennials, who generally are more positive about the future than the average Millennial. They are also confident in their ability to handle different types of tasks that are part of their day-to-day lives. And at 35 percent, the share of bilingual Hispanic Millennials with a household income of $100,000 or more is consistent with U.S. Millennials as a whole Homeownership challenges Yet, despite their optimism and goal of homeownership, Hispanic homeownership at 46.2 percent lags when compared to the overall U.S. home ownership rate of 63.9 percent in 2017. There are signs the gap could narrow; Hispanics are the only demographic to have increased their rate of homeownership for the past three years. Moreover, the report shows Hispanics are responsible for 46.5 percent of net U.S. homeownership gains since 2000. Still, the 2017 State of Hispanic Homeownership Report notes that a shortage of affordable housing, prolonged natural disasters in states with a significant Hispanic presence (California, Florida, Texas), and uncertainty over immigration policy could hinder Hispanic homeownership growth. An opportunity to reach Hispanics It seems most Hispanic Millennials will strive for homeownership at some point in their life, as they believe owning a home is best for their family’s future. With no convincing needed, there is a tremendous opportunity for mortgage providers to look deeper into the reasons behind Hispanic Millennials’ optimism to determine how to insert themselves into that dynamic. Research highlights the importance of creating interest in financial advice and making this a potential means of gaining trust. Hispanic Millennials who gain a better understanding of the benefits—not only for them but for generations to come—and costs of owning a home may translate their confidence into action.
At Experian, innovation is at the heart of our culture. We strive for continuous improvement, from finding new ways to better use data to identifying ways to make access to credit faster and simpler for millions of people around the world. So we are especially proud that one of our latest innovations—Text for Credit—was recognized by FinTech Breakthrough, an organization that highlights the top companies, technologies and products in the global FinTech market. The Innovation Award for Consumer Lending comes in a year of significant innovation milestones for Experian. In addition to introducing Text for Credit, we’ve partnered with Finicity, and also created a more open and adaptive technology environment by implementing API capabilities across the Experian network. We recently introduced Text for Credit, the first credit solution that enables consumers to apply for credit with a simple text message. Using mobile identification through our Smart Lookup process, consumers can be recognized by their device credentials, bypassing the need to fill out a lengthy credit application. Our Text for Credit product enables consumers to apply for real-time access to credit while standing in line to make their purchases, or before entering an auto dealership. This recognition as an innovator is a testament to our employees’ focus on putting the consumer and our customers at the center of what we do, and powering innovative opportunities to secure better, more productive futures for people and organizations. What’s next We are also exploring other opportunities to make the consumer experience more convenient. As we’re becoming a keyboard-less society, we’re looking at the next frontier: voice technology. The progression to voice-activated services has started already using voice commands through Amazon Alexa and Google Home-enabled devices. And while voice technology is still in its infancy, it’s not a tremendous leap to envision being able to use voice commands to access lines of credit in a store, like Text for Credit now. Experian DataLabs is exploring many possibilities for voice-activated credit, using several different devices—more than just via phone. As technology innovators, our greatest challenge is determining which potential solutions to pursue. It comes down to a simple equation: the magnitude of impact a new application may have, plus its probability of success. So far, we’ve found plenty of options that satisfy both criteria—and our curiosity, too. With technology, machine learning and ever-smarter applications of big data, we can deliver intriguing and convenient experiences to shoppers in ways we never imagined a decade ago. Predicting the future has never been this much fun.
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.
Marketers are keenly aware of how important it is to “Know thy customer.” Yet customer knowledge isn’t restricted to the marketing-savvy. It’s also essential to credit risk managers and model developers. Identifying and separating customers into distinct groups based on various types of behavior is foundational to building effective custom models. This integral part of custom model development is known as segmentation analysis. Segmentation is the process of dividing customers or prospects into groupings based on similar behaviors such as length of time as a customer or payment patterns like credit card revolvers versus transactors. The more similar or homogeneous the customer grouping, the less variation across the customer segments are included in each segment’s custom model development. So how many scorecards are needed to aptly score and mitigate credit risk? There are several general principles we’ve learned over the course of developing hundreds of models that help determine whether multiple scorecards are warranted and, if so, how many. A robust segmentation analysis contains two components. The first is the generation of potential segments, and the second is the evaluation of such segments. Here I’ll discuss the generation of potential segments within a segmentation scheme. A second blog post will continue with a discussion on evaluation of such segments. When generating a customer segmentation scheme, several approaches are worth considering: heuristic, empirical and combined. A heuristic approach considers business learnings obtained through trial and error or experimental design. Portfolio managers will have insight on how segments of their portfolio behave differently that can and often should be included within a segmentation analysis. An empirical approach is data-driven and involves the use of quantitative techniques to evaluate potential customer segmentation splits. During this approach, statistical analysis is performed to identify forms of behavior across the customer population. Different interactive behavior for different segments of the overall population will correspond to different predictive patterns for these predictor variables, signifying that separate segment scorecards will be beneficial. Finally, a combination of heuristic and empirical approaches considers both the business needs and data-driven results. Once the set of potential customer segments has been identified, the next step in a segmentation analysis is the evaluation of those segments. Stay tuned as we look further into this topic. Learn more about how Experian Decision Analytics can help you with your segmentation or custom model development needs.
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.
Expert offers insights into turnkey big data access The data is out there – and there is a lot of it. In the world of credit, there are more than 220 million credit-active consumers. Bolt on insights from the alternative financial services space and that number climbs even higher. So, what can analysts do with this information? With technology and the rise of data scientists, there are certainly opportunities to dig in and explore. To learn more, we chatted with Chris Fricks, data and product expert, responsible for Experian’s Analytical Sandbox™. 1. With the launch of Experian’s all-new Ascend platform, one of the key benefits is full-file access to our Sandbox environment. What exactly can clients access and are there specific tools they need to dig into the data? Clients will have access to monthly snapshots of 12-plus years of the full suite of Experian scores, attributes, and raw credit data covering the full national consumer base. Along with the data access, clients can interact and manipulate the data with the analytic tools they prefer. For example, a client can log into the environment through a standard Citrix portal and land on a Windows desktop. From there, they can access applications like SAS, R, Python, or Tableau to interrogate the data assets and derive the necessary value. 2. How are clients benefiting from this access? What are the top use cases you are seeing? Clients are now able to speed analytic findings to market and iterate through the analytics lifecycle much faster. We are seeing clients are engaging in new model development, reject inferencing, and industry/peer benchmarking. One of the more advanced use cases is related to machine learning – think of artificial intelligence for data analytics. In this instance, we have tools like H2O, a robust source of data for users to draw on, and a platform that is optimized to bring it all together in a cohesive, easy-to-use manner. 3. Our Experian database has details on 220 million credit-active consumers. Is this data anonymized, and how are we ensuring sensitive details are secure? We use the data from our credit database, but we’ve assigned unique consumer-level and trade-level encrypted pins to ensure security. Once the encrypted PINs are assigned, they remain the same over time. Then all PII is scrubbed and everything is rendered de-identifiable from an individual consumer and lender perspective. Our pinning technique allows users to accurately track individual trades and consumers through time, but also prevents any match back to individual consumers and lenders. 4. I imagine having access to so much data could be overwhelming for clients. Is more necessarily better? You’re right. Access to our full credit file can be a lot to handle. While general users will not “actively” use the full file daily, statisticians and data scientists will see an advantage to having access to the larger universe. For example, if a statistician only has access to 10% of the Sandbox and wants to look at a specific region of the country, they may find their self in a situation with limited data that it is no longer statistically significant. By accessing the full file, they can sample down based on the full population from the region they are concerned with analyzing. 5. Who are the best-suited individuals to dig into the Sandbox environment and assess trends and findings? The environment is designed to serve the front-line analysts responsible for coding and analytics that gets reported out to various levels of leadership. It also enables the socialization of those findings with leadership, helping them to interact and give feedback on what they are seeing. Learn more about Experian’s Analytical Sandbox and request a demo.
Are you ready to launch a new product to capture the revenue growth opportunities in today’s market? The competition is heating up for new growth, as banks increased personal loan balances by 10 percent year-over-year in 2015 and another 6 percent in 2016.* Many lenders are now looking for robust data to understand the market opportunity based on their risk appetite. This challenge usually takes a significant investment in consumer credit data to gain the necessary insights. In helping lenders launch new products, I’ve found there are common areas of focus and specific steps you must take to move from the initial business case to more tactical planning. The following details come to mind: refining risk thresholds, pricing, loss forecasting and use of models within the initial go-to-market strategy. These project tasks can’t be successfully completed without having the right breadth and depth of data available. Knowing the past can help you create a better future for your business. When I start working with a client on a new product launch, I want to ensure they have sufficient data that can provide a comprehensive historical consumer view. In my experience, the best data to use will show an exhaustive view of consumer behaviors through the economic cycle. Having this large volume of data enables me to evaluate the business strategy and risks through the financial crisis while also giving my clients the foundation for compliance with loss forecasting regulations. Obtaining this breadth of data often can be a significant, but necessary, investment. Data is a great starting point, but it isn’t enough. Understanding the data sufficiently to design an effective go-to-market strategy is critical for success. I’ve found that identifying specific attributes helps give my clients a deep dive into the structure of a consumer’s credit history at the trade level. This level of information provides insight into the structure of the consumer’s wallet and preferences. Additionally, this depth of data allows my clients to develop powerful custom models for use in their business strategy. Being prepared is half the victory. Having comprehensive data that will help you understand consumer spending behavior and the risk they carry through the economic cycle will assist in creating a successful go-to-market strategy. Our Market Entry ServicesTM data sets are analytics-ready, including attributes and performance flags, to give you a holistic view of your target market. Having this breadth and depth of data, along with strong tactical planning and execution, will ensure your success in launching new products and entering new markets. *Experian–Oliver Wyman Market Intelligence Report
Consumers are hungry for more personalized marketing, and I’m an actual example. As a new stepmom to two young kids, who has a full-time job, I rarely have any down time. No revelation there. I no longer have time to surf the web to buy clothes. And shepherding everyone to an actual store to shop? #forgetaboutit I’m not alone. Of the 57 percent of women in the U.S. workforce, 70 percent have a child under the age of 18. We don’t always have the time to shop for clothes, financial products, and nearly anything else, but it doesn’t mean we don’t need or want to. I would give the right bank or retailer my data in exchange for personalized marketing offers in my inbox, social feeds and mailbox. And many others would, too. Sixty-three percent of Millennial consumers and 58 percent of Gen Xers are willing to share data with companies in exchange for personalized offers, discounts and rewards. This indicates consumers are craving more customized marketing. Providing their personal data to get that is acceptable to them. In the financial services space, Mintel research shows that just 61 percent of male consumers, 49 percent of consumers aged 18-44, and 44 percent of Hispanic Millennials have a general-purpose credit card, either with or without rewards (Mintel’s Marketing Financial Services Report for June 2017). This indicates a significant market opportunity for cards that offer segmented or boosted rewards based on specific sectors and categories. Here are some other interesting trends specific to financial services: Relying on Experts Although chatbots and robo-advisors allow easy access to many financial services, 81 percent of consumers prefer in-person meetings when it comes to personalized financial advice. According to Mintel, men aged 18-44 are most interested in a free consultation with a financial advisor, and 19 percent of consumers are open to a free consultation. This interest surpasses attending free classes about finance and receiving email and mobile alerts from a financial institution. Quick, Efficient Delivery While consumers are calling for increased personalization, they also want it delivered quickly and efficiently. These expectations create unique challenges for financial institutions of all sizes. Some banks have embraced “card finder” apps, which allow consumers the convenience of inputting personal information to generate customized offers. There is a huge opportunity for financial institutions to leverage available consumer data to understand their target audience, and then deliver relevant products via multiple channels where they are consuming media now. Those who do will be positioned to provide personalized financial recommendations that were impossible just a few years ago.
Learn More Image
