You are on page 1of 12

Evaluating first-time defaulters From the inside out

Intelligent segmentation helps lenders identify and target new opportunities

Deloitte Center for Financial Services

Contents
1 2 3 6 Foreword Identifying first-time defaulters A potentially valuable segment Diamonds in the rough Using analytics to tap into opportunity Intelligent segmentation approach: Putting it into practice

Foreword

Nearly six months ago, we unveiled the results of a national consumer study that identified a growing customer segment known as first-time defaulters. As the industry began to look at this new customer, banks began asking how and what could be done to address these particular customers needs while making them a profitable contributor to the organizations revenues. This paper aims to shed light on ways bank can interact with first-time defaulters. In particular, it focuses on how banks and lenders can use data analytics to identify and retain these nuanced customers to build profitable, long-term relationships. Applying a predictive modeling approach to current and prospective customers can give financial institutions tools to define customer needs and risk. Like the general population of banking customers, first-time defaulters can be evaluated across the customer development lifecycle but with implied differences involving customer acquisition, customer servicing, cross- and up-selling, and custome retention. Once first-time defaulters have been identified, banks may create offers that improve short- and long-term profitability by using an approach based on collecting, formatting and manipulating data, identifying customer segments, and defining value propositions for each identified segment. Using these enhanced capabilities may allow banks and lenders to effectively target, acquire and retain liquidity-seeking first-time defaulters in a challenging market. Regards,

Andrew Freeman Executive Director Deloitte Center for Financial Services

Deron Weston Principal Deloitte Consulting LLP

Identifying first-time defaulters A potentially valuable segment

Since the most recent economic crisis, many US consumers have experienced significant financial hardship. Many Americans have found themselves without a job, behind on their mortgage or unable to keep up with credit card payments. Some of these individuals, previously with a good credit standing, became delinquent or defaulted on their debt obligations for the first time. According to a survey conducted by the Deloitte Center for Financial Services, fully 22% of Americans with bank accounts experienced a serious negative credit situation during the last two years, half of them for the first time in their credit histories.1 Financial institutions and their customers appear to be gradually recovering from the recession, and the contraction in the retail credit markets appears to be easing. Lenders have begun to look for new ways to revitalize their lending businesses. Offers to riskier borrowers have been increasing,2 as financial institutions may have realized that a larger-than-normal portion of the credit-challenged population may not have been reckless borrowers, even if they did experience a negative credit situation. Over time, these individuals may continue to improve their financial standing and seek to avoid future credit problems by deleveraging, limiting excess consumption, and increasing their savings. This is the segment we refer to as first-time defaulters.

Who are the first-time defaulters? Those who had a negative credit experience, such as a delinquency, foreclosure, bankruptcy, and/or charge-off, for the first time since September 2008.3 Those who were more likely to miss their credit obligations as a result of macroeconomic conditions (such as unemployment and reduced income) than poor decision-making or a lack of financial discipline. Those with a greater propensity to seek out loans in the future. In need of credit, first-time defaulters were more likely to obtain loan products than their prime counterparts, possibly making them a source of much-needed revenue for lenders in the future. Some leading-practice banks employ various degrees of sophistication related to data analytics, but in general there are many opportunities for the industry to adopt these practices. Specifically, if banks can identify first-time defaulters in their customer base, a particular opportunity exists to acquire long-term customers with favorable risk/ return characteristics. For example, one large financial institution is testing a targeted credit card offering, designed for customers whose credit was damaged during the recession. Borrowers are required to link their credit card account to a checking, savings, or brokerage account so that the financial institution can withdraw money from that source if a payment is missed. Meanwhile, use of the card helps the customer to rebuild his or her credit score. Also, in the third quarter of 2010, there was a significant increase from 7% of total offers in 2009 to 17% in 2010 in the number of credit card offers to previously prime customers with blemished credit.4 This share is expected to increase further during 2011. Additionally, banks reported an increased willingness to make consumer installment loans.5

As used in this document, Deloitte means Deloitte Services LP and Deloitte Consulting LLP, which are separate subsidiaries of Deloitte LLP. Please see www.deloitte.com/us/about for a detailed description of the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attest clients under the rules and regulations of public accounting. 2

Diamonds in the rough Using analytics to tap into opportunity

How can financial institutions take advantage of this market opportunity? Advanced data analytics can be used to identify, acquire, solicit, and retain first-time defaulters who have the potential to become valuable long-term banking customers. Advanced analytics is the process of converting a wealth of data into actionable insights through statistical and mathematical models. Using a predictive modeling approach that focuses on current and prospective customers, internal data can be supplemented with a variety of external data sets, giving organizations the tools to define customer needs and risk. This can be particularly effective in segmenting potential customers who may appear to have similar characteristics. Some members of this population may in fact have specific characteristics that help identify them as candidates to become good long-term customers with high value to the organization. For example, among a group of apparently similar 22 to 32 year olds who are in default, an individual whose characteristics include a certain career field, education level, or geographic location might have the potential to become a valuable customer.

How can these diamonds in the rough be uncovered? For existing customers, data from traditional internal sources, such as historical account activity and payment performance, can be combined with nontraditional external individual or household-level data sources, such as lifestyle data (e.g., interest in health, sports preferences, magazine or newspaper subscriptions, type of work, etc.), retail purchase patterns (e.g., average likely market basket, eating-out spend, etc.), social media (i.e., personal data generated from social media/networks used to create more personalized products), U.S. Census data, etc. For potential new customers, banks can also make use of credit bureau data, looking at individual borrowing records, the trajectory of their credit score, and the number of bureau inquiries among other metrics. Armed with this information, organizations can unlock new insights into customer populations by using analytics to apply a customer lifetime value model to create and evaluate variables, develop predictive models, and score individual profiles (Exhibit 1).

Exhibit 1 Using analytics to unlock insights into customer populations


Innovative data sources Business value

Modeling

Traditional internal data sources

Nontraditional external individual or household-level data sources


Consumer Lifestyle

Predictive analytics Data aggregation and data cleansing

Customer acquisition

Product mix/margin Customer transactions Acquisition cost/retention

Customer servicing Evaluate and create variables

Financial

Behavioral

Household

Develop predictive models

Cross- and up-selling

Nontraditional data unlock new insights into customer populations


Source: Deloitte Consulting LLP

Score individual proles

Customer retention

Evaluating first-time defaulters From the inside out

Customer acquisition Data analytics can help financial organizations to move beyond traditional likely to buy marketing models to identify customers who have a specific need. Improved customer segmentation facilitates more effective targeting and acquisition efforts. This insight can allow banks to focus their resources on customers who offer the most significant long-term potential to the organization. When evaluating first-time defaulters for potential acquisition, financial institutions can use analytics to identify those with solid potential by leveraging data in new ways. For example, financial institutions can consider credit-score change and degradation in conjunction with worsening employment indicators for a certain profession in a certain geography and changes in purchase patterns (e.g., journal or magazine subscription cancellations), as well as the specific products that experience delinquency, such as a credit card or an adjustable rate mortgage. After identifying those customers who present the most favorable profiles, banks can use traditional communications and direct marketing activities such as mail, direct mail, or online promotions to attract these potential customers more effectively. As an additional benefit, data analytics may be used to determine a measure of return on marketing investment and help banks most effectively allocate their marketing budget spend. Early adopters can capitalize on the demand from first-time defaulters who are looking for financial products, whether credit cards, savings and checking accounts, or home or car loans, at well above average pricing (within regulatory limits6). There is little evidence in the market that lenders are currently targeting first-time defaulters. Customer servicing Data analytics may provide a deeper understanding of the behavioral and financial characteristics of current and future customers. Financial institutions can now improve day-to-day management of existing accounts and address needs that are particular to first-time defaulters. Through predictive statistical models, financial institutions could potentially anticipate specific needs, proactively meet those needs, and potentially improve customer retention.

Delivering customer service effectively improves the lifetime value of the customer, whether this service includes providing a single point of contact or waiving account fees. As expected, customer satisfaction among individuals with recent credit problems is very low,7 as many banks are trying to end or have ended their relationships with customers in this segment. However, as the economy recovers and jobs rebound, the financial situation of these individuals may also begin to improve, and with it their need to have access to credit cards, home loans, mutual funds, certificates of deposit, and more. For example, a first-time defaulter with a low credit score may have a desire to rebuild a positive credit history. He or she may value the opportunity to learn more about saving and budgeting, setting up automatic debit for recurring expenses, or signing up for electronic spending alerts. Over time, as creditworthiness improves, card limits may be increased, rates lowered, and additional opportunities may be presented. Cross- and up-selling Once a financial institution has identified first-time defaulters with the potential to become high-value, long-term customers, analytics could then be used to determine effective and profitable ways of expanding high potential relationships through models that predict lifetime customer value and likelihood of attrition or potential and intent to buy additional products. Integrated customer behavior, demographic, and attitudinal data can help banks to understand customer needs and make the right offers. The recovering first-time defaulters specific needs may drive financial institutions account targeting and new design offerings. Once a positive credit history has been reestablished and the customer is on a more solid financial footing, he or she may be looking for new car or home loans, IRAs, or financial instruments with higher yields. By disseminating predictive analytics results throughout the enterprise, lenders can provide a more consistent customer experience across various channels and can seek to improve customer value.

Customer retention Sophisticated data analytics such as evolutionary segmentation solutions that account for customer demographics, attitudes, buying patterns, etc. can help financial institutions to identify customers who are most likely to move their accounts to other institutions. Armed with this information, financial organizations can develop customer-specific retention tactics that are consistent with current and expected lifetime value. For example, lenders might offer lower rates or higher credit limits to those customers who have improved their financial standing, or communicate additional product and service offerings that address the individuals needs as his financial situation improves. Although many first-time defaulters may recover and resolve the personal situations that resulted in credit issues, a subset may become repeat defaulters, making them unprofitable customers. Predictive analytics can help enable banks to identify those customers who remain at risk and take necessary corrective actions to help prevent charge-offs. Credit policies and models may need to be updated with application data variables that isolate the

one-time defaulter from the ongoing bad credit risk, such as job history, employment industry, personal liquidity, and product types that may have caused problems (such as adjustable-rate mortgages). This may result in a shift towards more fundamental underwriting that considers a number of factors in addition to a credit bureau score.

Evaluating first-time defaulters From the inside out

Intelligent segmentation approach Putting it into practice

One approach to acquiring, cross-selling, and up-selling first-time defaulters uses intelligent segmentation methods to identify and evaluate first-time defaulter prospects. The more effective the segmentation, the more effective the analytics may be at targeting a quality customer. Many variables can be considered for segmentation, including home-loan balance, income, and situation that caused the default. After the first-time defaulters have been identified, the next step is to create offers for these prospects that can improve the financial institutions short- and long-term profitability and market share. This approach is based on three steps (Exhibit 2): 1. Collect, format, and manipulate data. Gather historical account, product and customer data, external demographics, and psychographics data and evaluate as it relates to pre-underwriting/profitability model and propensity to buy models. This segmentation helps to confirm that prospective customers have a high likelihood Exhibit 2 Customer segmentation approach
1. Collect, format, and manipulate data

of wanting to buy products or open an account and are within the financial institutions risk tolerances. 2. Identify customer segments. Develop customer clusters based on the preliminary risk profile along with potential profitability and propensity to buy using unbiased, assumption-free analytical methods. 3. Define value propositions for each identified segment. Target the customer segments identified as potentially profitable with customized offerings that they are likely to buy and may become profitable to the bank. Several well-known banks and other financial institutions have leveraged the benefits of analytics in identifying likely prospects for credit cards or other financial products and offering an opportunity to add profitable long-term customers.

2. Identify customer segments

3. Dene value propositions for each identied segment

Value proposition A Segment 1


Development of clusters/segments based on the aggregation of data provided and models developed. Internal data may be enhanced with external information, which lets the expanded dataset speak and helps create segments based on value, propensity to buy, and other factors.
Protability Propensity to buy Segment prole 1 Business model description A

Historical account, product, and customer data External demographics and psychographics data Protability/value model Propensity to buy, retention/churn models

Value proposition B Segment 2


Protability Propensity to buy Segment prole 1 Business model description A

Value proposition X Segment N


Protability Propensity to buy Segment prole 1 Business model description A

Test /control pilots to rene models and maximize predictive performance

Source: Deloitte Consulting LLP 6

Example: Growing a profitable credit card market A credit card issuer was trying to grow profitability in the low-income segment in Latin America, but risk management challenges, such as poor collection performance and high credit losses, had inhibited results. The card issuer wanted to provide tools to its card-issuing banks to help them identify the most favorable customers. The card issuer developed predictive models to help credit card issuers and processors improve their collection performance. The card bank wanted to be able to identify and classify first-time defaulters based on their probability of reestablishing a sound financial footing or accepting repayment agreements, as well as to improve its collections strategy. Predictive classification models helped the issuer to separate first-time defaulters from chronic defaulters. Several scoring models were created to predict the probability of a given customer moving from delinquency to a positive credit standing. A predictive model was created that forecast the likelihood of a delinquent customer to accept a repayment agreement and delivered a decision-tree optimization tool that helps increase the effectiveness of a collection strategy. The effectiveness of the issuers collections process rose significantly after the application of these models.

Example: International bank improves value of customer contacts The marketing policy of a large international bank limited the number of customer contacts that could be made each year. As a result, prime customers often received marketing communications from the most timely product group, but not for products that were the most relevant and profitable. For example, they might receive a series of offers during the first part of the year, instead of promotions targeted to the specific interests of a prime customer, such as special rates on second homes, premium credit card offerings, or mutual funds. The bank needed a way to analyze customer behavior to determine the next desirable product offer for a specific segment based on their current situation. The bank had very large amounts of data to be mined, including more than 1,000 attributes and variables for more than 9 million customers. By using data analytics, the banks customers were scored and assigned to offer clusters. More than 3 million prioritized-offer candidates were identified and submitted, and 40 cluster segments were developed.

Evaluating first-time defaulters From the inside out

Conclusion

As the economic climate evolves, banks and other financial institutions have an opportunity to identify customers among a unique segment of the market known as first-time defaulters. Data analytics provide a valuable tool to help identify and target the individuals who offer the most likelihood of long-term potential as profitable customers, in addition to providing insight regarding the most effective products and services to offer them. By applying data analysis to existing financial and third-party data, financial institutions may be able to maximize potential and minimize risk in approaching this market segment.

Contacts

Andrew Freeman Executive Director Deloitte Center for Financial Services +1 212 436 4676 aldfreeman@deloitte.com

Omer Sohail Principal Deloitte Consulting LLP +1 214 840 7220 osohail@deloitte.com

Deron Weston Principal Deloitte Consulting LLP +1 404 631 3519 dweston@deloitte.com

Leandro Dalle Mule Senior Manager Deloitte Consulting LLP +1 617 437 3449 ldallemule@deloitte.com

End notes
1

Deloitte Center for Financial Services, First-Time Defaulters: An underappreciated customer segment for lenders? February 2011. More Card Offers for Consumers with Lower Credit Scores, credit.com, Dec. 16, 2010. For the purpose of this discussion, a default refers to one or more of the following events: three or more times late on a mortgage, three or more times late on a loan other than a mortgage, three or more times late on a credit card bill, bankruptcy, foreclosure, being contacted by a collections agency, been delinquent on child support, delinquent on taxes, delinquent on medical bills, legal judgments, or charge-offs. More Card Offers for Consumers with Lower Credit Scores, credit.com, Dec. 16, 2010. Senior Loan Officer Opinion Survey on Bank Lending Practices, Federal Reserve, January 2011. Subject to the regulations defined by the CARD Act of 2009 and the Dodd-Frank Act. First-time defaulters: Changes on the horizon, Deloitte Center for Financial Services, July 2011.

Evaluating first-time defaulters From the inside out

Insights. Research. Connections. Headquartered in New York City, the Deloitte Center for Financial Services provides insight and research to help improve the business performance of banks, private equity, hedge funds, mutual funds, insurance and real estate organizations operating globally. The Center helps financial institutions understand and address emerging opportunities in risk and information technology, regulatory compliance, growth, and cost management. The Center brings a financial services integrated view to Deloitte and its network of member firms, each of which is a legally separate and independent entity that provide audit, consulting, financial advisory, risk management, and tax services to select clients. With access to the deep intellectual capital of 169,000 people worldwide, Deloitte serves more than one-half of the worlds largest companies, as well as large national enterprises, public institutions, locally important clients, and successful, fast-growing global growth companies. To learn more about the Center, its projects and events, please visit us at www.deloitte.com/us/cfs.

This publication contains general information only and Deloitte is not, by means of this publication, rendering accounting, business, financial, investment, legal, tax, or other professional advice or services. This publication is not a substitute for such professional advice or services, nor should it be used as a basis for any decision or action that may affect your business. Before making any decision or taking any action that may affect your business, you should consult a qualified professional advisor. Deloitte, its affiliates, and related entities shall not be responsible for any loss sustained by any person who relies on this publication. Copyright 2011 Deloitte Development LLC. All rights reserved. Deloitte Touche Tohmatsu Limited

You might also like