Tag: analytics

Given the option between offshore and onshore data science resources, how do you decide? Let’s discuss a few things to consider.

An analytics environment can have enterprise-wide impact. Instant access to customer data, actionable analytics and intelligence tools drive the most value.

Gavin Harding, Senior Business Consultant, continues in this Q&A with insight that spans across all lenders and their use of alternative data.

In banking, as in baseball, data and analytics are key to making informed, data-driven decisions for your team and your business.

Any analytical environment is only as good as the data you put into it. Check these four key features when choosing the right one for your organization.

There are a lot of people talking about big data who are not fully leveraging the value of their data. How do you use data to innovate and stay competitive?

At their heart, car dealers have always been marketers. It's part of learning the trade and understanding the business to gain natural insight into modern marketing and advertising practices. One could even argue that the experience gained through knowledge passed down, trial and error, and exposure to the automotive game itself can yield better strategies than a marketing degree. With all that said, it's still important to have the right data to guide the decisions as well as the tools necessary to decipher the data. Although we have a vast amount of information at our fingertips, it's very possible to truly build on "actionable data" and allow it to define the parameters for a dealership's marketing strategy. One of the most important things to consider when you're building and enhancing your strategies is that the data allows for decision making on the macro and micro levels. We see trend reports, analytics, and test cases that can influence decisions on both sides of the spectrum. Making decisions on the macro level means wholesale changes or additions. For example, the overall effectiveness of a particular classified advertising website can be broken down to determine whether or not it's making the right type of impact. Dealers have so many options today to advertise both online and offline, so making sure that any particular venue is effective is key to success. On the micro level, decisions can be made about how to position the dealership within the individual venues. You may be a big believer in search pay-per-click advertising, for example, and data can help to guide you or your vendor partners to position the dealership properly on search. Knowing which messages about individual cars are effective can be a guide. Then, understanding what zip codes have the highest opportunity level for the individual model can mold your PPC spend, while demographic data can drive effective messaging and help you optimize campaign creative and landing pages. Having access to the data is only the first step. Looking at the data appropriately is an important second step that many dealers are missing. Putting it all together into a decision-driving model is the step that almost every dealer should embrace to allow them to make the best decisions, macro or micro.

  The auto industry has been riding a wave of prosperity for the past seven years, bouncing back nicely from the 2008 market collapse. But, it looks like rising sales of the past 10 years, are, well...a thing of the past. According to Alix Partners, 2016 sales of 17.5 million units might be the high-water sales mark, at least through 2022. Alix Partners says the next five years sales will range between 15.6 million to 16.8 million annually. Suddenly, it will be challenging for dealers to stay in strong growth mode. How can dealers best react to the tightening market? The Experian white paper “Data Tools Evolve to Give Dealers an Edge in a Tight Sales Market” takes a look at how new and improved data and analytic tools can provide deeper insights to help automotive retailers unlock sales. The paper reviews current market sales statistics, historical sales trends and how dealers reacted during similar market conditions in the past. In addition, the paper provides a look at the challenges faced by automotive retailers, in terms of shrinking gross profit, higher advertising expenses and increased competition. Automotive retailers also will find information on the importance of customer conquesting and a look at technology tools to help provide a deeper understanding and actionable intelligence about local markets. Data and analytics are no longer the private purview of large mega-dealers. The Experian white paper outlines today’s data tools that can be implemented quickly and cost effectively by dealers of any size. To learn more about these trends, download the paper here: https://www.experian.com/automotive/dealerwhitepaper.html

Many clients use the same debt collection strategy they’ve used for years never considering the customer experience for the debtor

Fraud Solutions Made Easy — solving new fraud problems by Adapting Legacy Solutions 

Who sports higher scores, less debt and more on-time payments? According to Experian’s latest analysis, women take the credit title.

Experian data shows consumers are more confident managing their credit since the recession. The Q3 2015 Experian Market Intelligence Brief was released today featuring data that highlights consumer credit card debt has now reached its highest level since Q4 2009. Credit card debt levels reached $650 billion in Q3 2015, the highest it has been since Q4 2009 when it was $667 billion. Credit card delinquency rates on outstanding balances 60 or more days past due have decreased 71 percent during the same time period. Combining those indicators with the national unemployment rate dropping 50 percent during the same span illustrates a positive economic outlook on credit card trends among lenders and consumers. “Overall credit card limits have increased 102 percent since Q4 2009 with $82 billion originated in Q3 2015,” said Kelly Kent, vice president of Experian Decision Analytics. “The increase in limits from lenders and the steady climb in credit card debt combined with exceptional delinquency rates signals greater confidence among consumers as they are showing more assurance in managing their credit since the recession. We expect to see credit card debt increase in Q4 based on historical seasonal trends driven by the holiday shopping season especially with the early positive holiday sales as a sign.” The Q3 2015 Experian Market Intelligence Brief report is now available.

The overarching ‘business driver’ in adopting a risk-based authentication strategy, particularly one that is founded in analytics and proven scores, is the predictive ‘lift’ associated with using scoring in place of a more binary rule set. While basic identity element verification checks, such as name, address, Social Security number, date-of-birth, and phone number are important identity proofing treatments, when viewed in isolation, they are not nearly as effective in predicting actual fraud risk. In other words, the presence of positive verification across multiple identity elements does not, alone, provide sufficient predictive value in determining fraud risk. Positive verification of identity elements may be achieved in customer access requests that are, in fact, fraudulent. Conversely, negative identity element verification results may be associated with both ‘true’ or ‘good’ customers as well as fraudulent ones. In other words, these false positive and false negative conditions lead to a lack of predictive value and confidence as well as inefficient and unnecessary referral and out-sort volumes. The most predictive authentication and fraud models are those that incorporate multiple data assets spanning traditionally used customer information categories such as public records and demographic data, but also utilize, when possible, credit history attributes, and historic application and inquiry records. A risk-based fraud detection system allows institutions to make customer relationship and transactional decisions based not on a handful of rules or conditions in isolation, but on a holistic view of a customer’s identity and predicted likelihood of associated identity theft, application fraud, or other fraud risk. To implement efficient and appropriate risk-based authentication procedures, the incorporation of comprehensive and broadly categorized data assets must be combined with targeted analytics and consistent decisioning policies to achieve a measurably effective balance between fraud detection and positive identity proofing results. The inherent value of a risk-based approach to authentication lies in the ability to strike such a balance not only in a current environment, but as that environment shifts as do its underlying forces.

To calculate the expected business benefits of making an improvement to your decisioning strategies, you must first identify and prioritize the key metrics you are trying to positively impact.  For example, if one of your key business objectives is improved enterprise risk management, then some of the key metrics you seek to impact, in order to effectively address changes in credit score trends, could include reducing net credit losses through improved credit risk modeling and scorecard monitoring. Assessing credit risk is a key element of enterprise risk management and can addressed as part of your application risk management processes as well as other decisioning strategies that are applied at different points in the customer lifecycle. In working with our clients, Experian has identified 15 key metrics that can be positively impacted through optimizing decisions.  As you review the list of metrics below, you should identify those metrics that are most important to your organization. • Approval rates • Booking or activation rates • Revenue • Customer net present value • 30/60/90-day delinquencies • Average charge-off amount • Average recovery amount • Manual review rates • Annual application volume • Charge-offs (bad debt & fraud) • Avg. cost per dollar collected • Average amount collected • Annual recoveries • Regulatory compliance • Churn or attrition Based on Experian’s extensive experience working with clients around the world to achieve positive business results through optimizing decisions, you can expect between a 10 percent and 15 percent improvement in any of these metrics through the improved use of data, analytics and decision management software. The initial high-level business benefit calculation, therefore, is quite important and straightforward.  As an example, assume your current approval rate for vehicle loans is 65 percent, the average value of an approved application is $200 and your volume is 75,000 applications per year.  Keeping all else equal, a 10 percent improvement in your approval rates (from 65 percent to 72 percent) would generate $10.7 million in incremental business value each year ($200 x 75,000 x .65 x 1.1).  To prioritize your business improvement efforts, you’ll want to calculate expected business benefits across a number of key metrics and then focus on those that will deliver the greatest value to your organization.  

The term “risk-based authentication” means many things to many institutions.  Some use the term to review to their processes; others, to their various service providers.  I’d like to establish the working definition of risk-based authentication for this discussion calling it:  “Holistic assessment of a consumer and transaction with the end goal of applying the right authentication and decisioning treatment at the right time.” Now, that “holistic assessment” thing is certainly where the rubber meets the road, right? One can arguably approach risk-based authentication from two directions.  First, a risk assessment can be based upon the type of products or services potentially being accessed and/or utilized (example: line of credit) by a customer.  Second, a risk assessment can be based upon the authentication profile of the customer (example: ability to verify identifying information).  I would argue that both approaches have merit, and that a best practice is to merge both into a process that looks at each customer and transaction as unique and therefore worthy of  distinctively defined treatment. In this posting, and in speaking as a provider of consumer and commercial authentication products and services, I want to first define four key elements of a well-balanced risk based authentication tool: data, detailed and granular results, analytics, and decisioning. 1.  Data: Broad-reaching and accurately reported data assets that span multiple sources providing far reaching and comprehensive opportunities to positively verify consumer identities and identity elements. 2.  Detailed and granular results: Authentication summary and detailed-level outcomes that portray the amount of verification achieved across identity elements (such as name, address, Social Security number, date of birth, and phone) deliver a breadth of information and allow positive reconciliation of high-risk fraud and/or compliance conditions.  Specific results can be used in manual or automated decisioning policies as well as scoring models, 3.  Analytics:  Scoring models designed to consistently reflect overall confidence in consumer authentication as well as fraud-risk associated with identity theft, synthetic identities, and first party fraud.  This allows institutions to establish consistent and objective score-driven policies to authenticate consumers and reconcile high-risk conditions.  Use of scores also reduces false positive ratios associated with single or grouped binary rules.  Additionally, scores provide internal and external examiners with a measurable tool for incorporation into both written and operational fraud and compliance programs, 4.  Decisioning: Flexibly defined data and operationally-driven decisioning strategies that can be applied to the gathering, authentication, and level of acceptance or denial of consumer identity information.  This affords institutions an opportunity to employ consistent policies for detecting high-risk conditions, reconcile those terms that can be changed, and ultimately determine the response to consumer authentication results – whether it be acceptance, denial of business or somewhere in between (e.g., further authentication treatments). In my next posting, I’ll talk more specifically about the value propositions of risk-based authentication, and identify some best practices to keep in mind.