customer analytics

12月 182014
For a long time, master data management (MDM) practitioners boasted about their ability to build a 360° view of customers by aggregating and proactively managing information coming from various business applications such as CRM systems, ERP applications, and other operational systems. But was it really a 360° view? What about […]
10月 032014

The Big Data MOPS Series with Tamara Dull

“Big Brother?! Ha! I’m not afraid of what the government knows about me. I’m more afraid of the internet and what it will expose about me. Heck, I’m even more afraid of people on the street with their smartphones who can take my picture without my permission and post it anywhere. I’ve been so diligent about living a private life, but now I live in fear.”

An attendee who went by the name of “Dee” at a technology public sector event in May 2014

The big data privacy reports. On the heels of Edward Snowden’s proclamation about the U.S. government’s misuse of consumer data, President Barack Obama asked his counselor, John Podesta, in January 2014 to conduct a 90-day study on big data privacy with recommendations on how to move forward as a country. In May, two reports were publicly released:

Both reports are a good discussion starter about balancing the effective use of big data with the intrusions of privacy and discrimination, and they aptly demonstrate that the government understands the big data questions on the table – from both a policy standpoint and a technological standpoint. However, they didn’t go far enough to address tough, but common, privacy concerns, like the ones expressed by “Dee” in the quote above.

What needs to happen next? The public and private sectors need to come together and make some hard decisions about managing the government’s complex data, modernizing its infrastructure, and constraining snooping and surveillance, while building consensus on how much efficiency we’re willing to forego in the name of privacy, and vice versa.

Why this matters. One key issue that I was pleased to see highlighted in these White House reports is the de-identification (or anonymization) and re-identification of individuals’ identities. It’s important to understand this one.

You’re probably familiar with the concept of de-identifying or anonymizing data. In simple terms, it means removing any information from a data set that could personally identify a specific individual; for example, the person’s name, a credit card number, a social security number, home address, etc. Companies that sell consumer data, such as data brokers, typically only sell anonymized, and often aggregated, data. So what’s the big deal?

With today’s big data technologies, it’s becoming easier to re-identify individuals from this anonymized data. Programming techniques have been and continue to be developed to pull these anonymized pieces back together from one or more data sets. In addition, there is growing concern by what analysts call the “mosaic effect” whereby a person’s identity can be derived or inferred from data sets that don’t even include personal identifiers. So if a company says it anonymizes your data before passing it onto others, be aware that your identity could still be revealed through advanced re-identification techniques.

In our organizations, as we continue to learn more about our customers by integrating big data, such as social media, with our CRM data, we may discover stories about them they never intended or wanted us to know. We need to respect these new insights and respect our customers’ privacy.

Questions to think about. Where does your organization stand when it comes to data privacy? Consider these questions:

  • Does your organization have a privacy policy? Make sure you understand and adhere to your company’s privacy policies, especially with regard to data, before a customer complaint or lawsuit beats you to the punch.
  • Do you tell your customers when a request is made for their data – from the government or otherwise? Do you publish periodic transparency reports? If this isn’t part of your process, is this a practice your organization could consider?
  • Is your company willing to fight for your customers’ privacy rights in court? How about Congress? This isn’t just a fight for the big boys like Google and Facebook. It’s for any company who values its customers and wants to protect their privacy from intrusive entities and/or activities.

One final thought. “Dee” (from above quote) readily admits that she’s a bit paranoid. But what if her fears are valid and some of us just aren’t paranoid enough? Dee’s concern really isn’t with Big Brother as much as it is with “Big Companies” (read “not the government”) who are collecting big data on her through her social media channels, FitBit, phone records, internet browsing, car GPS, and the list goes on. Moving onto the national stage, we’ve witnessed Edward Snowden going public with the link between Big Brother and Big Companies, and more recently, the White House has issued two reports addressing these same Big concerns.

Yet the question still remains: What are we doing – in our companies and in our private lives – about privacy issues brought on by big data and big data technologies? Do we even care? In a future post, I will share some industry statistics and trends on this subject. In the meantime, stay safe. It’s a big data world out there.

Originally written for and published on Smart Data Collective as part of the Big Data MOPS Series.

Editor's note:

This post pertains to the "P" (Privacy) in Tamara's "Big Data MOPS Series." Like all of these MOPS topics, privacy is not a trivial matter for marketers because it has the potential to wreak havoc with customer relationships, especially as we apply customer analytics to the data. For that reason, I am pleased to offer this "Friday Feature" on our blog - it's food for thought as we all become more digital in our marketing and pursue the opportunities of big data. To explore more topics in big data, I'd suggest you start with our Big Data Insights page.

tags: big data, Big Data MOPS Series, customer analytics
8月 192014

digital_baseballLast weekend, I took my nine-year-old son to a batting cage to get ready for his upcoming baseball season. He's a natural athlete, but soccer has been his full-time sport of choice for the last two years, so he needed some reps swinging the bat to switch gears to baseball.

As he stepped into the cage, I stood on the outside and started noticing all the little things I thought he was doing wrong, and began offering "helpful" suggestions:

  • "You're standing too close to the plate. Back up some."
  • "You need to step towards the pitcher, not third base."
  • "Keep your back foot planted."
  • "Choke up on the bat."

Well, after about five minutes in the cage, I succeeded in one thing -- thoroughly confusing him! But I also learned two valuable parenting lessons from that experience -- first, he's only nine... he'll figure it out; and second, he's really close to being a very good batter. He just needs to focus on making a few small adjustments.

And in all areas of our lives, switching gears from one type of an activity to another involves some changes. For marketers that are making the transition from traditional to digital, the same two lessons apply:

First, you're not alone -- many of your colleagues in other organizations are "figuring it out." Each organization is different and each has its own set of hurdles to overcome to be more digital. And each marketer, with enough time in the cage, will figure it out.

Second, you might be closer than you think. Are there some small adjustments you can make to see a big impact on your digital efforts? I bet there are. And like a budding batter, there are easy ones you can try to get yourself started.

Here are three steps you can take today to improve your digital marketing:

1. Start with search. In a digital world, content is king. But even if you write a Pulitzer-worthy blog post, if no one is searching for it, it won't impact your demand gen metrics. Google Keyword Planner is a great tool that can show you search traffic for a set of words and phrases. Plan your content around hot terms that will get more eyeballs.

photo2. Content is your friend. One trap I've fallen into many times in my career is not leveraging a marketing activity as much as I should have. Start with a piece of content, then look for ways to digitally amplify it, share it socially and repurpose it for other uses. The result will be more touch points your customers can find online. The diagram to the right might illustrate it more clearly for you.

Let's say you have a killer webinar that educates and also shows how your company can meet the needs of customers. You'll get some registrations for it, but imagine what you can accomplish if you amplify it:

  • Turn it into a blog post and a thought leadership article.
  • Pull out a short product demo that you can serve up on-demand.
  • Plug in social media by tweeting and posting links to the original webinar, the blog post, the article and the demo.

Now, instead of one asset, you have four -- and lots of ways to promote it. Make sure you put multiple version of the content on your corporate website to tie back in organic search traffic.

3. Measure then tweak. One of the great things about digital marketing is the ability to try things, measure them and pivot. People and industries respond differently to various types of marketing outreach. Find out what works and keep doing it. Find out what doesn't work and stop doing it.

Batter up!
When my son stepped back into the batting cages the second time, I told him to just focus on one thing -- moving his stance away from the plate a little bit. He quickly saw the results of the small change. The barrel -- not the neck -- of the bat started making contact with the ball, and the ball began jumping off the bat. That little change made a big difference.

You can see a similar difference in your marketing campaigns when you make some small digital changes. Focus on one at a time, then build from there. Before you know it, you'll be hitting it out of the park!

tags: content marketing, customer analytics, customer intelligence, digital marketing, search marketing
6月 192014

One interesting outcome of regulatory reform in health care is seeing the use of the word "customer" filter into the dialogue in the industry.

This letter is not from a health plan or provider, but clearly shows me the love as a customer.

Someday letters from health plans and providers will look more like this.

The context for that development in the United States’ health care industry is upheaval not seen in any sector of the economy since the government-mandated breakup of the monopoly Bell Telephone System in the mid-1980s.

At the same time, technology is radically transforming health care, and the precedent in communications is how the Bell System breakup coincided with the commercialization of innovations such as voice mail, mobile telephones and the internet, to name a few. So will this upheaval in health care also usher in great innovations? I think it’s quite likely – and one big question is, “Who will do the innovating?”

In times of change, the organizations that thrive are the ones that adapt, often ending up operating alongside new players that might do things that were previously unimaginable.  I imagine the same will hold true in health care as it evolves.

We’ve already seen adaptation taking place among health insurance plans in fundamentally strategic ways, and two standouts include Blue Cross Blue Shield of North Carolina and Florida’s GuideWell Connect (GWC) - an affiliate of FloridaBlue. The most striking changes have involved the ways they engage with their customers, essentially orienting their organizational direction more toward individual members’ needs and desires and not so much as a consequence of regulatory requirements.

As a health insurance customer, I could not be more excited. As a marketer, I could not be more intrigued.

Industry Complexity

I’ve written before about how complex the buying process is for health care, and operating an organization in the health care ecosystem is equally complex. One element of that complexity is that for almost as long as health insurance plans have been around, working-age adults and their families in the United States have predominantly received health insurance coverage through their employer. According to a report by the Economic Policy Institute, 69.2% of Americans under the age of 65 had access to employer-sponsored health insurance in the year 2000, and that rate fell to 58.4% in 2012. During that same period, the rate of non-elderly Americans without any health insurance rose from 14.7% to 17.7%.

The Affordable Care Act (ACA) is part of the upheaval that's changing the health care ecosystem in many ways, but the interesting outcome from a marketing perspective is the emergence of the individual as the customer. Most health plans’ largest customers are employers and the individual employees are typically referred to as “members.”

The ACA includes incentives for individuals, as well as disincentives for organizations to be active in the health insurance equation. One outcome of the ACA already has been to increase the number of individuals seeking and receiving health insurance, and that dynamic provides impetus for health plans to engage with their individual members as customers. And that’s where the North Carolina and Florida health plans provide some interesting lessons.

GuideWell Connect: Get insights and use them.

Raj Vavilala, Senior Director at FloridaBlue's GuideWellConnect.Florida’s GWC aggregates services for consumers, who can then create a free account and have access to a personalized wellness plan, motivation to reach their goals, an online community and product recommendations to help meet their wellness goals. The goal is to connect the people and the resources that are needed to manage their health. So why has it been so complicated, asks Raj Vavilala, Senior Director at GWC?

He explains with an analogy to Apple’s iPad – it’s not the device, per se, that people desire. It’s really the apps available on that device that consumers value. And health insurance is not too different – it's possible to offer consumers a nice, shiny plan but the real value is derived in understanding what they are using it for.

It’s an interesting analogy, and not surprising coming from an executive affiliated with an innovator like Florida Blue - one of the first health plans to roll out retail centers, swipe cards and other innovations. They provide an interesting example of how to become customer-oriented. Their organization is already an established user of analytics in their marketing, so Vavilala believes getting data is not the issue – it’s getting the insights that are needed for action that presents the most urgent challenge.  For GWC, it starts with segmentation based on publicly available information, and builds from there.

Improving the onboarding process has been a priority, so customer-friendly changes were built around the steps mandated by regulation, which resulted in impressive gains. For instance:

  • Providing a one-pager with 10 bullet points and then the required contractual language is provided on a flash drive. They’ve found a 2% increase in retention rate among customers who receive their welcome kit versus those who do not.
    That’s good!
  • Distributing member cards with an activation sticker (like for credit cards) and 70% of their welcome kit recipients activate that way. Knowing that enables them to focus on the other 30% of their customers. They’ve found a 10% increase in retention rate among people that actually call and engage with them.
    That’s great!
  • Giving people tools and services at the time of their need in the channels where they are engaged. They know mobile is not just a fad, so they put a lot of effort into making sure their mobile app is ready and easy to use.
    That’s putting their insights to use!

 Vavilala’s point is to get all of the players to work together and instead of solving for big, systemic problems, approach it by tackling the small problems. Simple things, such as getting people to a doctor. Almost 50% of their members did not have an attributable primary care physician, which means the first time they had a condition they would find the highest cost, most expensive form of treatment – not an ideal scenario for anyone involved, but relatively easy and impactful to address.

BCBSNC: Drive value with a data-driven strategy.

When the ACA became law, BCBSNC already provided health insurance options to individuals, so it provided a challenge to retain their existing base of customers, while pursuing the opportunity presented by the Act’s individual mandate. The retention challenge alone represented a multimillion-dollar risk for the health plan, so doing nothing was not an option.  Like many health plans, BCBSNC found that absolutely none of their addressable market was neutral about the changes from the ACA – they were either happy or horrified.

Michael Parkerson is Vice President of Marketing at Blue Cross Blue Shield of North Carolina.And no health plan could specifically answer individuals’ questions about how much their health insurance cost was going to change, but that was the looming question That fear of the unknown was the first fear, and the second fear was wondering what the best choice might be. In order to be proactive, BCBSNC needed to go deeper than high level demographics.

Michael Parkerson, Vice President of Marketing at BCBSNC offers an interesting example of the pitfalls of relying too much on demographics for marketing. Consider the case of an individual profiled as follows:

Male, 64 years old, English,
Affluent, 2 adult children

That demographic either describes the Prince of Wales or Ozzy Osbourne – and there’s no way their needs will be the same. That’s why the power of the data is so important – you can turn it into information that’s then actionable and can be used to drive value.

From the impact of the ACA, BCBSNC needed to consider the rate impact of the government subsidy – as an individual, would it be the savior or not? Then, channel options – are they buying direct or through an agent? Then, consumer segment preferences. Lastly, it’s the pivotal question of what would the customer value – and how could they address that value for the customer. Their analysis showed their customers fell into five segments:

  1. Maintain the status quo (not deeply impacted positively or negatively)
  2. Happy recipients (pretty significant decrease based on subsidies),
  3. Frustrated seekers(the horrified few whose costs were going up no matter what),
  4. Subsidy required(they will be okay if we could get them to their subsidy),
  5. High utilizers,

Their strategy was to focus on the segments that would have the most to gain from meaningful interaction – numbers 3 and 4, representing about half of the population. They developed a three-step strategy to get them to enroll:

  • Reconnect – They had to engage customers about reform and position their organization as a trusted expert on reform since so many of the customers didn’t always have an agent to help them through the process.
  • Advise – Their goal was to make reform relevant and personalized, and promote a strong call to action by going beyond just educating, so the customers would be equipped and confident enough to take action.
  • Enroll – Customers needed to conclude that signing with BCBSNC was an easy, smart and valuable decision.

To engage their market among those three steps, BCBSNC developed BlueMap – designed to be way more than an application, and more of an experience for the customer. And because of the wide degree of preferences of their customers, BlueMap was rolled out with a multi-faceted outreach:

  • A multi-piece direct mail stream,
  • Member services customization,
  • Custom landing pages,
  • Outbound phone calls,
  • Channel integration with brokers, and
  • Special events, such as sporting events and even the State Fair.

In the summer of 2013, they also did something quite innovative - they rented out movie theaters across North Carolina and gave out free tickets to a newly released movie in return for the opportunity to hear a 15 minute presentation about the ACA. At each theater, they had ipads lined up enabling people to surf through and figure out what they needed and even email their spouse with their findings. These events sold out across the state in hours.

The results from the roll-out of BlueMap is impressive, particularly in how they maintained about half of the market they expected to be at risk of attrition by increasing their persistency from a projected 70% to an actual 85%. By all measures, BlueMap has helped BCBSNC to deliver on their brand promise by getting their members/customers to rely on them for the confidence, understanding and stability that they’re looking for to “live fearless.”

Parkerson describes it as part of their mission and their vision for the kind of organization they can become as they redefine their business model from one that traditionally has been focused on products to one where they now consider their products, services and consumer touch-points from the perspective of the customer. The goal is to find ways for them to create unique, differentiated value for customers at each touch point so it builds loyalty. That’s not an easy task considering their products are intangible, and customers receive benefits outside their company walls, but it seems like they’re up to it.

For so many years, health insurance plans have referred to individual users as “members,” and what’s more impressive is how both of these leading health insurance plans have reoriented their focus on the individual customer that uses and benefits from their services.SAS's Sarah Rittman moderated a panel discussion with BCBSNC's Michael Parkerson and FloridaBlue's GuideWellConnect's Raj Vavilala. The examples of these two leading health plans are useful roadmaps for how to respond to the evolution of the health care ecosystem, and particularly to the emergence of the health care customer.


Raj Vavilala and Michael Parkerson participated on a panel discussion at the 11th annual SAS Health Analytics Executive Conference in Cary, NC, which was moderated by Sarah Rittman, Principal, SAS Health & Life Sciences Practice, and also available on-demand as a virtual conference.

tags: customer analytics, customer centricity, health analytics, health insurance plans, healthcare, strategy
5月 152014

The health and life sciences industries affect all other industries on two levels – our employers and governments are heavily involved as influencers in payment systems, and as individuals we all engage directly with health care organizations. Because of those two reasons, people in all industries have a stake in how the healthcare ecosystem evolves in the face of change.

Big changes

Kecia Serwin, Vice President and General Manager of SAS Health Care & Life Sciences.

Kecia Serwin, SAS

And talk about change! Kecia Serwin, Vice President and General Manager, SAS Health and Life Sciences sums it up this way. The three greatest drivers of change in the healthcare ecosystem right now are:

  • Technology and innovation
  • Government mandates
  • Empowered consumers

And each of those three change drivers have such a compelling mix of challenges and opportunities that how organizations respond to them will determine who will matter in the future – and who will not.  So Kecia asks, what can really move the needle? What’s working? How can we transform our organizations the way we need to?

It’s no longer about payers – providers – pharma; it’s now about the whole health care ecosystem. New models involve greater collaboration and shared risks/rewards. And perhaps most signigicantly, new strategies are emerging to deal with the new empowered consumer.

How Health Analytics moves the needle

What does Health Analytics really mean? The broadest definition is that it’s the collection of enabling technologies and skills that can be used to generate insight to support strategic decision-making.  Health Analytics makes extensive use of data – data collection for meaningful use, data sharing for collaboration and health information exchanges, and data analyses to inform and to allow predictions.

Traditionally, analyses have been retrospective, so the focus was primarily on explaining and describing. As in the case of caring for an individual health condition – the diagnosis is fundamental. But what really matters is the treatment plan that drives the best outcome. So to move the needle, it comes from the power of forward-looking predictive analytics. It’s the ability to conduct accurate what-if simulations and include qualitative data that enables the consideration of what could and should happen, and most importantly – knowing the best thing that can happen.

Health Analytics is key to the treatment plan

Dr. Farzad Mostashari, Visiting Fellow at Brookings Instituion.

Dr. Farzad Mostashari, Brookings Institution

So of those three drivers of change that Kecia identifies, is there a common thread? Dr. Farzad Mostashari, visiting fellow at the Brookings Institution says that the biggest underlying reason is that health care “costs too damn much and we’re not getting enough value for it.” And he sees all the changes holistically coming in the shift from “volume” to “value” of care, were quality will be measured and rewarded, as will be total cost. And both safety and appropriateness will matter.

As the health care ecosystem evolves, health plans will be sharing risk with providers on the total cost of care. In the United States, we’ve seen a similar shift with the advent of managed care – which heralded a new era of cost-containment that never quite materialized. Dr. Mostashari believes that’s what’s different now is that we now have the ability to predict. Based on data, we can predict hospitalizations, Emergency Room visits and other events.

Envisioning individual patient benefits is a powerful way to understand the impact of health analytics’ ability to produce accurate predictions. Just imagine:

  • Reaching quicker and more accurate diagnoses – knowing sooner what’s wrong and getting better earlier.
  • Using data-driven treatment plans of drugs, therapies and behavior modification tailored to patient preferences and demonstrated past efficacies.
  • Getting adherence to prescription regimens based on relevant rewards.

If each scenario results in fewer sick days, or reduced traffic accidents, and/or overall higher quality of life, then imagine the economic impact at a population level. To be sure, what’s different now is our ability to predict, but what’s also different is that we now have empowered consumers.

Caring for the patient as a consumer

Patients show up in waiting rooms and hospitals with specific conditions that need attention. The organizations engaged in the care of the health of that patient have traditionally focused on the condition at hand. Frequently, how they receive care is determined by the condition and the payment parameters set by the applicable health insurance plan. But the patient shows up as a whole person with needs, desires and expectations from living in a technology-driven online-all-the-time social savvy world.

And with the shift in the overall market toward more individual participation in health insurance coverage from the affordable health care act, the patient will become choosier – and will have the ability (and desire) to make choices more easily.

As electronic medical records have become more prevalent, so has the ability to use data to care for patients as consumers. And all these changes will translate into care improvements and the potential cost savings we all have a stake in achieving. Dr. Mostashari lays out a few ways to pursue that path:

  • Find ways to get feedback loops to pursue continuous improvement. In doing that, look for ways to collect data in ways that are accurate but not individually-identifiable.
  • Embrace testing and experimentation. Science and medicine invented the randomized trial, for goodness’ sake, so this should be a natural.
  • Prepare for operating based on improved outcomes. Currently, the economics of health care are oriented toward numbers of patients and numbers of procedures. That is quickly changing.
  • Engage the patient and his/her family as key players in the care of the individual. Most treatment regimens and outcomes happen at home and not in the clinical environment, and other factors matter, such as nutrition, hygiene and mobility.
  • Make the easy thing to do the right thing to do. As Dr. Mostashari puts it, “there’s too much friction in the health care ecosystem.”

By friction, he means all the different obstacles that patients face in getting care – from bad waiting rooms, unnecessarily complex claims payment & processing, to having to deal with outsourced procedures that the physician needs to complete the diagnosis or the treatment.

As a non-medical “lay person,” what I am hearing from all that is the need to become more customer-centric. Along with that, of course, the role of customer analytics and health analytics is to enable the decision-making process so all players can make decisions on an informed basis, and to center their thinking – and operating – around the idea that it’s all about the patient/consumer. That’s like music to this marketer’s ears!

One additional piece of advice from Dr. Mostashari applies to any industry:

Don’t ever surprise your Board or your Customers.

And so the good Doctor has spoken.


Kecia Serwin and Dr. Farzad Mostashari presented the Welcome Address and Keynote Presentation at the 11th Annual SAS Health Analytics Executive Conference in Cary, NC on May 14, 2014.

tags: analytics, customer analytics, health analytics, health insurance plans, healthcare, Life Sciences
3月 242014

When you are making a big, important purchase there are few things more helpful than seeing how well things are going somewhere else. It's better than merely "kicking tires" because it's really happening somewhere else and in their own way, that other organization is putting customers at the center of their strategy.

To that end, I've compiled a little list of customer successes that do a great job of telling the story of why SAS customers get it right for marketing. Take a peek at how some of these organizations are leading the way using SAS. They have recognized that the best way to differentiate is by delivering unique customer experiences based on a solid, connected business strategy driven by analytics.

Click on any one of those links below to open the full success story in a new window and read about what may be possible for your organization. I promise you won't be disappointed.

Tripled the success rate of previous campaigns and won lapsed customers back.

Targeted lists yield higher growth rates and lower costs for customer acquisition with immediate results.

Use of real-time pricing data results in multiple percentage point increase in conversions.

Achieves a 360-degree view based on big data resulting in a 20 percent ROI across campaigns.
Reduced churn rate by 20 percent and saved more than $500,000 in full-time employee productivity.

Orlando Magic
Customizes fan experiences and has seventh-largest revenue stream for ticket sales out of 30 NBA teams.

ROI in excess of 100 percent, and customer contact policy gives the bank a competitive edge.

137 percent rate of return with more personalized offers for increased cross-selling and up-selling.

Retains influencers and reduces churn rate by 25 percent.

Produced a 360-degree view of customers in less than three months and improved close rates by 250 percent.

As always - thank you for following!

tags: Campaign Management, customer analytics, customer intelligence, marketing analytics, marketing optimization
3月 242014

Leading your organization to faster, better decisions requires skill, agility, resourcefulness and above all -  analytics. In marketing, that combination allows the CMO to put the customer squarely in the center of strategy, and align operational execution around the customer focal-point.

It's no coincidence that leading organizations, such as the world's biggest retailer, media conglomerates and large telecommunications operators, all use SAS for marketing excellence.

Executives from these organizations and from business publications leader Harvard Business Review will be presenting their perspectives at the 2014 SAS Global Forum Executive Conference in the following sessions:

These sessions will provide you with viewpoints that explain how to put your customer at the center of your strategy. If you are not attending SAS Global Forum Executive Conference, you can follow developments on Twitter at the #SASEC14 hashtag.

As always, thank you for following!

tags: #SASEC14, customer analytics, hbr, leadership, marketing, marketing analytics, strategy
1月 212014

Recency, Frequency, and Monetary Analysis (or RFM) is a popular customer segmentation technique employed by database marketers everywhere. Marketers use RFM to identify which customers are most likely to respond to a direct marketing campaign. The model takes into account three simple metrics:

  • How recently did the customer buy from you?
  • How frequently does the customer buy something from you?
  • How much money does the customer spend on your products?

Each metric receives a value of 1 through 5. The result is 125 "bins" of customers (because 125 is 53). Those with higher RFM scores are considered more likely to respond to a campaign...potentially.

For years, SAS customers have used special tools like SAS Enterprise Miner to compute RFM. With SAS 9.4, the RFM algorithms are built into Base SAS, and there's an easy-to-use task in SAS Enterprise Guide. (The task is also available in the SAS Add-In for Microsoft Office.) You can find the task in the menus at Tasks->Data Mining->Recency, Frequency, and Monetary Analysis.

Note: To use the task, you must have SAS 9.4 and SAS Enterprise Guide 6.1 (or SAS Add-In for Microsoft Office 6.1). Despite the "Data Mining" category, this task does not require SAS Enterprise Miner.

As an example, suppose you have transaction data that looks like the following. You need only the 3 fields -- a customer ID, a transaction date, and a transaction amount (value):

From this, RFM calculates "scores" for each customer. The customers with the highest scores will probably be those that spent the most with you, across the most recent and frequent dates. The idea behind RFM is that a minority of customers are responsible for a majority of your business. RFM scores provide visibility into who those valuable customers are. Here's an example of the scored data, summarized at the customer level:

The RFM task supplies several useful charts. Here's a "monetization map", which summarizes the monetary values for each combination of frequency and recency scores. You might use this to help identify a "sweet spot" of customers that you want to target.

Next, let's look at a paneled bar chart of the Frequency by Recency segments. The bar on the lower right corner indicates that there are a handful of customers who made several purchases in the past (high frequency), but that was a long time ago (not recent). Perhaps that's a good target segment for a "Come back and see us -- we miss you" campaign. Contrast this with the bar on the upper right, which shows the 60 superfans: the customers who bought lately and often. You can decide whether to "go back to the well" with this group in the next campaign, or save the campaign expense as they might buy from you anyway, without prompting.

RFM scores are just one small part of planning a campaign. The "Recency, Frequency, and Monetary Analysis" task is a good start, but eventually you might want to factor in other criteria.

After all, direct marketing has many nuances, such as cross-referencing with opt-out lists and taking steps to avoid "overmarketing" to any one segment. Tracking response rates, testing campaigns, and the actual campaign workflow are also essential elements. When you're ready, SAS Customer Intelligence offers an integrated set of applications for all of these aspects.

tags: customer analytics, direct marketing, RFM, SAS 9.4, SAS Enterprise Guide