Share with your friends


Analytics Magazine

Listening to the customer

Using analytics to understand consumer lending behavior.

Arnold PravinataBy Arnold Pravinata

Most consumer lending organizations pride themselves on “listening to the customer,” but for many, “listening” is actually more instinctual, with courses of action determined by previous experience or by examining past patterns of customer behavior. Very few actually make a concerted effort to truly listen to current and prospective customers via cognitive interviews and surveys.

Tools available for data analysis allow true customer focus, where product offerings can be shaped based on a statistical understanding of the drivers that bring specific types of customers to the organization to address their specific short- and long-term goals.

In the financial services marketplace, this kind of analysis is particularly important. The market is becoming crowded with loan offerings that are difficult for customers to properly compare. Acquiring and keeping customers in a crowded marketplace requires the extra effort of conducting deeper analysis to determine why a typical consumer might use your offering.

With this aim in mind, Best Egg, a financial technology and services provider, recently worked with the brand and data science team at the marketing agency Moxie on an expansive process to understand customer behaviors related to borrowing. This joint research combined insights from interviews to construct an in-depth survey of personal finance behaviors, perceptions and beliefs. The research team leveraged advanced graph analytics methodologies to determine the defining groups of borrowers, and measured these groups using pattern recognition software to identify predictors of audience types.

The result was a fascinating cross-section of buying behaviors, with real insight into how and why people borrowed. This is, of course, extremely useful information for building consumer loyalty.

The Case for Deep Analysis

Particularly in the financial services arena, businesses cannot reasonably expect to apply a broad-stroke analytical solution to its customer base while also creating a product offering that stands out in a crowded marketplace. For example, if general customer feedback suggests that pricing is too high, it’s important to fully understand whether such feedback is coming from across the collective customer base or from specific customer profiles.

Without deep analytics, an organization’s natural reaction would probably be to lower pricing across the board. While this type of sweeping action might help address some customer concerns, overall it may not be the best solution. In fact, it may unnecessarily and adversely affect the financial performance of the company and returns to its investors, when a better solution might have been to leverage the company’s brand to change how pricing is framed.

Similarly, if a general survey suggests that customers want products beyond debt consolidation, it’s important to understand whether this feedback is coming from all of your customers or specific customer profiles (e.g., prospects versus established clients). Without deep analytics, an organization’s natural reaction may be to add product offerings to all its customers. Although this may address some customer concerns, it may not be necessary for the entire base, which is simply seeking the best possible debt consolidation offering.

By conducting deep analytics and tailoring actions to specific types of customers, we can better differentiate ourselves from other lenders. As a result, it becomes easier to acquire and keep customers.

Qualitative Insights and Motivation

Collaborating with Moxie, Best Egg used cognitive interviewing techniques to conduct qualitative, in-depth interviews with a cross-section of participants, including both customers and noncustomer prospects. The results of this qualitative phase also formed the basis for follow-up research – an online survey to measure and validate the qualitative findings.

The goal was to truly understand the customer: Who are they? What is their social status? What do they need? By identifying the “why” behind their current behavior in a specific circumstance/situation, we gain an additional depth of understanding of the customers’ motivation.

Best Egg worked with Moxie on an expansive process to understand customer behaviors related to borrowing.

Best Egg worked with Moxie on an expansive process to understand customer behaviors related to borrowing.
Source: ThinkStock

But motivation to act is what really matters. What are the factors that motivate the customers to act? What matters to them? For that reason, the approach incorporated a behavioral science methodology focusing on motivation.

Motivation is the main driver of human behavior and purchasing decisions. The more relevant and differentiating a product is to a consumer, the higher the expected cognitive reward, and therefore, the more they are willing to pay.

Motivation can be divided into two categories: explicit and implicit. Of the two, explicit motivations are more easily identifiable, because they are features of a product. Implicit motivations, on the other hand, are what the brand provides.

Explicit motivations are functional product motivations or personal consumer goals. These are the “table stakes” necessary for a product to compete in any mature category. Explicit motivations get to the root of how customers feel about the product itself: Why is it the best choice among other competing products? Can I get the best pricing? Can I get the funds soon? Can I contact a customer service representative when I need one?

Implicit motivations are the emotional motivations or goals that are linked to a brand. These implicit motivations are the key to differentiating a brand. They offer insight into how customers feel about the brand and the company that provides the product. Is it trustworthy? Would I feel good to be a customer of this brand/company?

These motivations are how brands differentiate themselves. And the only way to uncover them is through behavioral economics insights and behavioral science methodologies. When combined, they provide an understanding of how and why people make decisions.

Behavioral Profiles and Findings

The Best Egg study used specialized pattern recognition analysis software to reveal relationships across consumer data. This allowed us to find and measure the conditional probability of relationships across the entire study. These connections then became predictors for building behavioral profiles. Behavioral profiles differ from traditional segmentation in that they create groups based on choice and motivation, instead of demographics.

To begin, we had to identify key indicators of choice or motivation. In our study, we focused on groups (that is, customers and prospective borrowers) and their financial situation. We then identified other items that may have a strong conditional probability to occur with those choices.

As a result, we saw that our customers had a strong conditional probability of being able to pay for everyday expenses but not have the ability to save. Interestingly, we observed that this probability existed regardless of income level, and our qualitative interviews gave us perspective as to their motivations. Our prospective borrowers, on the other hand, had a stronger probability to be able to save for unplanned situations but did not save for the long term. The borrowing motivation of this group was very different from the first.

Where is this work leading us? As mentioned at the outset, we now have some clear ideas of both explicit motivations for our consumer borrowers, as well as their implicit or emotional motivations that will help us create a clear differentiating benefit for our particular brand. The features of our products will continue to speak to borrowers’ explicit motivations. In that regard, we will not necessarily see much in the way of new features that might set us apart from our competition.

What we will be able to do (and are in the process of doing, through branding workshops across Best Egg) is find the kind of marketing statements that will resonate with the emotional or implicit drivers that prompt a current user to stay with the Best Egg platform, or to provide the compelling value proposition to convert prospects to users.

It’s this type of work – conducted and updated on a regular basis – that actually forms the backbone of what would otherwise be a vague notion of “listening to the customer.” This work can’t be done in a vacuum, and brands can’t rely on past experience to guide them. The only way to really listen to the customer is to do precisely that – really listen.

Arnold Pravinata ( is chief decision science officer at Best Egg.

Analytics data science news articles

Related Posts

  • 32
    More than a decade ago, I worked at an enterprise software company whose scheduling product was based on a novel and proprietary machine learning algorithm. Though I had fallen into this role as a result of my background in modeling and optimization, I quickly received an education in how the…
    Tags: customer, customers
  • 30
    The growing effectiveness of digital media has changed the way marketers interact with customers. New age customers are informed and empowered. The challenge for organizations is to be a part of the customers’ conversations involving their product and to influence their choices. Hence, the adoption of digital channels such as…
    Tags: customers, customer, product


Fighting terrorists online: Identifying extremists before they post content

New research has found a way to identify extremists, such as those associated with the terrorist group ISIS, by monitoring their social media accounts, and can identify them even before they post threatening content. The research, “Finding Extremists in Online Social Networks,” which was recently published in the INFORMS journal Operations Research, was conducted by Tauhid Zaman of the MIT, Lt. Col. Christopher E. Marks of the U.S. Army and Jytte Klausen of Brandeis University. Read more →

Syrian conflict yields model for attrition dynamics in multilateral war

Based on their study of the Syrian Civil War that’s been raging since 2011, three researchers created a predictive model for multilateral war called the Lanchester multiduel. Unless there is a player so strong it can guarantee a win regardless of what others do, the likely outcome of multilateral war is a gradual stalemate that culminates in the mutual annihilation of all players, according to the model. Read more →

SAS, Samford University team up to generate sports analytics talent

Sports teams try to squeeze out every last bit of talent to gain a competitive advantage on the field. That’s also true in college athletic departments and professional team offices, where entire departments devoted to analyzing data hunt for sports analytics experts that can give them an edge in a game, in the stands and beyond. To create this talent, analytics company SAS will collaborate with the Samford University Center for Sports Analytics to support teaching, learning and research in all areas where analytics affects sports, including fan engagement, sponsorship, player tracking, sports medicine, sports media and operations. Read more →



INFORMS Annual Meeting
Nov. 4-7, 2018, Phoenix

Winter Simulation Conference
Dec. 9-12, 2018, Gothenburg, Sweden


Applied AI & Machine Learning | Comprehensive
Starts Oct. 29, 2018 (live online)

The Analytics Clinic
Citizen Data Scientists | Why Not DIY AI?
Nov. 8, 2018, 11 a.m. – 12:30 p.m.

Advancing the Analytics-Driven Organization
Jan. 28–31, 2019, 1 p.m.– 5 p.m. (live online)


CAP® Exam computer-based testing sites are available in 700 locations worldwide. Take the exam close to home and on your schedule:

For more information, go to