Until (relatively) recently, electric utilities pretty much had a single mission: the generation, transmission, and monetization of electrons. It was a simple business model. The customer flips a switch, or claps their hands, or yells across the room to Alexa to turn on the lights, and the fulfillment process happens, literally at the speed of light. For many years, that was enough. But what happened before is not what happens today. Instead, we live in an economic marketplace where cable service providers provide home security, phone companies provide video entertainment options, drivers with some spare time provide rides from the airport, and Amazon provides, well, everything. Utility companies learned that within a fairly narrow space, they too can compete for share of consumers’ share of wallets for products that most consumers would have traditionally sought elsewhere. The “narrow space,” at least today, tends to center on either 1) products and services directly related to the home, such as things like home warranties, appliance repair and maintenance, home management and efficiency systems, and yes, home security; or 2) optional, voluntary programs like community solar. Configuring and ultimately pricing these types of products is a well-established, tried and true exercise in product development research. Got ballpark pricing questions? Use Van Westendorp Price Elasticity research. Want to see what consumers will trade off for lower prices? Use conjoint analysis. Want to offer complex pricing models based on tons of optional add-ons and choices? Use adaptive conjoint. Want to pick a winner among some product finalists? Use a monadic experimental design. The limitation with all these methods is that they generally yield relative consumer adoption estimates, not absolute ones. Relative metrics reliably show which product will outperform the others but doesn’t help much in populating that top line in the product’s pro forma. And obviously, it helps to know how many people will sign up for a community solar initiative—and at what price—before a utility can reasonably estimate their investments in hardware, marketing, insurance, rolling trucks, regulatory compliance, and, importantly, impact on their brand. In research for consumer package goods, the transformation from relative adoption estimates to hard forecasts of adoption and dollars has relied on mountains of historical data that model specific products in specific categories (e.g. a new flavor of potato chips in the salty snacks category). For new concepts like community solar initiatives, however, this history doesn’t broadly exist. Fortunately, many utilities do have historical adoption rates for many analogous, if antiquated, products. In the final, monadic stage of product development, a key question is about purchase intent. Generally speaking, the concept with the highest PI wins. Producing a forecast from these outputs, while far from an elementary exercise, is founded on best-practice modeling and marketing science. Adoption of some original products can be treated as dependent variables is a logistic model, with things like household demographics, marketing outreach, seasonal factors, and other characteristics as predictors to that outcome. A similar process can then be applied to the “new product,” using an outcome of “definitely would purchase” as the binomial target result and the current values (or, in the case of marketing effort, estimated values) along with their previous coefficients as the predictors. The final data science application involves scaling the model’s results to the adoption levels of previous products. In a nutshell, the modeling application for these utility applications is similar to the large-scale efforts applied in CPG and other sectors, except that the process tends to be unique to each utility, based on their history, customers, and many other factors. This fact doesn’t allow for an easy, out-of-the-box solution, but it does allow for a scientific, empirical, and defensible approach to forecasting new product sales.
In my previous post, I talked about the effects of different sampling approaches on the proportion of web versus telephone completes on our newly multimode customer satisfaction program. Now let’s look at how the resulting survey data were impacted by the transition from a fully phone-only methodology to collecting some portion of the completes online.
I participate in many insurance industry meetings where the primary “pain” is the lack of new recruits for the field force. Just this week, one firm noted a 20 percent shortfall in year to date recruitment. Recruitment has many facets; in addition to a wide range of impacts on the financial outcomes for our marketing campaigns. I will merely touch on three areas where I spend the majority of my time assisting Audience Identification Omnichannel Campaigns Business Intelligence from CRM system Custom Audience The first flaw I normally observe is the lack of attention and effort to correctly build the audience for the insurance offering. Often, the responsibility is delegated to an individual agent—go get us a list of XXXX. It is assumed that this is an easy and unimportant task. Wow, it is the item with the most impact on the campaign’s success. Best practice audience creation requires: -the determination of the significant data points that drive a decision. May require market research data and intensive modeling of large scale data aggregation -the data collection, data integration and database to match the audience identified in step 1 Agents are very bright folks but they are not data or analytical experts. They may try to fulfill this role but they normally fail miserably and resent the firm that places them in that position. And the impact is a multiplier not a percentage. Our DDG target audiences pull 3.5 to 10X compared to the in -house mailing list because we use propensity and predictive modeling. Omnichannel Campaigns Even though most firms operate in a silo fashion the consumer data needs to be organized in a single view scheme. Then when consumers engage with our brand we have the ability to recognize them and respond in a personalized fashion. The consumer might: Mail an inquiry Email the customer service center Search the website for a quote Click a Facebook ad Walk in a brick and mortar location If she/he did walk right up to your desk, could you actually engage them: - using real data about them—turning 66 today -their current or previous policy ownership—term life with approval to convert to whole life, -the trigger event that caused them to walk in—purchased a new home using a jumbo mortgage Now normally, we are seeking to mail, email or call them as our system recognizes that a trigger such as birthday, marriage, move, child birth has occurred. Due to the scale of this effort we need automated campaign tools that implement our business rules on a 24/7 basis. Again, if you are forcing the individual agent to select his campaign tool, set business rules and manage this process the effort is approximately 99 percent doomed. The platform that DDG implements depends on your marketing scheme as they systems have very different strengths and weaknesses. Closed Loop Marketing I am purposefully using an old vernacular here. It is critical to build that an information process that tracks Consumer engagement-date and request Agent response-date and presentation Meeting date—did we meet face to face Sale details—closed for policy form with these premium dollars Many CRM tools exist today. The key for recruitment is the presence of a system to help agent time management. The ability to view the outcomes in business intelligence dashboards maintains the agent focus and morale. In addition, if the customer service center is utilizing the same system then you reduce churn and increase customer satisfaction. Conclusion An insurance firm that generates a constant flow of interested to buy/qualified to buy prospects, maintains a continuous stream of communication with those consumers and assists the agent in sales time management will not suffer a recruitment shortage.
Surprisingly, 2018 marks the 40th year of selling and marketing in my career. My original on the job training focused on sales methods and techniques. Naturally, I was introduced to the concept of center of influence for life insurance production. So, at the risk of boring you already here is a quick list of those original audiences recommended to me: Family, friends CPA/Lawyer Doctor/Dentist Business owners or leaders Government, school, church officials I observed many of my enthusiastic fellow newbies start building their networks of contacts. I also monitored the level of failure to reach the minimum goals. Most of the new recruits did not succeed. Luckily, I was tasked with a national direct mail effort by the CEO within 30 days of my recruitment. And it opened my eyes to the ability to reach out to highly qualified contacts who I did not know. In my small world, I was always the number 1 salesperson due to this knowledge. I normally state that if I had to depend on my center of influence that I would have failed miserably. I grew up in a rural area with lower socioeconomic conditions and very small population. There were 8 students in my grade throughout my K-12 education. In a job of numbers, that was very "slim pickins” Utilization of data, technology and analytics afforded me an infinite universe of influence by comparison. After careful consideration of my firm’s product, my product knowledge and the economic concerns at that moment in time, I could select the audience most likely to: a. need my services b. to listen to my presentation c. buy the policy and d. refer other buyers. Let me pause for a couple of different examples Challenge Agent, 22 years old. New BBA in Finance. No family/friend network. Life Insurance firm—Good Brand recognition, excellent disability policy and cash value life products. Method Selected the Surgeons in the radius area by the year graduated from Medical School. Used direct mail to present a major business issue for them—disability would cause a disruption in their cash flow which would possibly lead to loan defaults. Outcome The mailer produced a 1 percent response, 10 doctors inquired. All 10 set up appointments and purchased disability policy. Then each doctor offered a referral to their fellow doctors in their practice. In this case that was an average of 5. The agent had an ever- expanding circle of strong income professionals who would need his cash value solutions after the original loans for their medical school and practice were paid off. Challenge Agent, 30 years old. BBA in Marketing, making a career change. Senior market insurance services—Medicare supplement and retirement products Method Targeted the turning 62,63, 64, 65,66, years old audience in the radius area. Used direct mail to invite them to a seminar on Medicare. Medicare choices are extremely confusing to most consumers compared to their use of group health policies for most of their lives. Outcome 20 to 40 attendees per session. 50 percent would request a follow up meeting by submitting a complete financial profile stating their primary concerns. The close rate for Medicare Supplement policies is very high. And the same consumer also seeks the alternatives for their retirement funds—money management, cash value policy or annuity. The agent has an ever- expanding circle of satisfied seniors with retirement funds who eagerly recommend his services. Today, I have many more resources at my disposal to create a. custom audience b. write a personalized message c. conduct an omnichannel campaign d. predict the premium production I recommend that you build your center of influence by using data driven marketing. Direct Mail is the foundation of that effort as legislation has restricted initial contacts by phone or email. In the current digital age some young marketers dismiss the use of direct mail. I smile as I know that effective direct mail drives my digital flow of inquiries and initiates my center of influence. Happy Hunting, as my original sale manager used to say!
For the past twenty years, DDG has been collecting data for a massive, multi-utility customer satisfaction study. Because many of these utilities service residential customers in geographies that are heavily rural, where Internet access is not a guarantee, this study has heretofore been conducted using a telephone data collection methodology. However, as TCPA restrictions on the use of predictive dialers, decreasing penetration of land lines, and flagging telephone response rates have made meeting monthly targets more and more challenging, DDG undertook a significant redesign of the study to allow for multimode data collection. For the first time, online interviews would supplant some of the telephone interviews.
Over my 66 years, I have purchased many different forms of life insurance. My first policy was with Prudential, small whole life policy. I was newly married; we were struggling to pay our bills. I decided that I really wanted my wife to do more than just survive if I died and left her with all of our debt. I had lost my dad at 42 years of age, my brother at 22 in accidents. So unexpected death was very real to me. And for several years that was my only concern. One day, my wife and I were discussing “the cost of college educations”. Somewhere along the line, 3 children seemed to have moved into our house. After much deliberation, I purchased a Northwestern Mutual whole life policy. The cash value grew and grew as my flock aged into college. All three of them graduated from college without any college debt. As my business grew, I suddenly needed some form of assurance that my family could pay off my line of credit and my buy sell agreement with my partner. I purchased a large amount of term life from American General. Thank goodness, there has never been a need to use these policies. Knowledgebase Marketing became a much larger firm than I could have ever imagined. Thus when we sold the firm in 1999, my private client advisors recommended an IRIT. So I purchased a Manual Life policy to pay inheritance taxes for my children. As the estate tax laws changed I reevaluated and switched to a Penn Mutual policy. So, as I noted in recent email communication to those who work in the life insurance marketing arena, the individual consumer need drives the definition of an audience for that type of policy. It is important to know: What is the client’s financial profile? What are his/her concerns? What are they planning to do now? And at data decisions group we perform market research, collect and aggregate data then process analytics to define the answers to these questions. I am a fan of life insurance for many reasons. It has been a lengthy education: from the day I sat and listened to that first young agent until today; when I have transmitted millions of messages to individual consumers asking them if they wished to review their life needs. And processed millions of positive responses
Life insurance companies that utilize direct mail marketing have relied on traditional response models to more efficiently target consumers for whom their products are relevant, attractive, appropriate and affordable. The actuaries at life insurance companies have applied sophisticated data science for years to establish risk, premiums, marketing allowances and more. The actuaries at these companies learned a fundamental truth about consumers: people are different demographically, behaviorally and socio-economically. Women generally live longer than men. Smokers represent an extremely high risk. There are high risk activities that some consumers enjoy more than others. In terms of health outcomes heredity has a role, body mass index has a role, and overall lifestyle has a role. Of course, these factors can be unique to each consumer. Paradoxically, the same principles that insurers use to accurately underwrite or deny life insurance policies also apply to the marketing of those policies. Why? Both analytic processes are attempting to predict an outcome; in the case of direct mail marketing, the outcome is a positive response to a marketing campaign and ultimately a sale. Consumers’ responses to marketing are based on different factors. These factors reflect who they are, where they are, how they behave, their attitude toward the world around them, their family situation, and what comprises their overall lifestyles. This is why “one size fits all” or “out of the box” predictive analysis does not work well when it comes to predicting response behavior. There are methods that utilize multiple segment-based models to determine which models—or combination of models—yield the highest response for a given audience. This methodology is alternatively referred to as ensemble modeling, model stacking, or nested modeling. Each of these specific approaches has subtle differences that are meaningful to nerdy data scientists, but their outcomes are the same: build and combine models that yield the greatest lift across diverse, heterogeneous population by determining market segments or geographic segments and refine the modeling parameters within each of those. Today, we’re going to focus on a nested modeling methodology. Nested models are founded on the premise that different consumer characteristics—whether they be geographic, demographic, lifestyle, attitudinal or behavioral—result in different reasons why people respond or do not respond. The problem with this approach is that the more ingredients that get added to the model soup recipe, the more diluted the outcome of that recipe becomes. It’s like the old data science joke analogy about the fallacy of marketing to the average consumer: you’re standing in a bucket of ice water with your head stuck in a hot oven. On average, you feel just fine! Nested models use the same group of predictors, but instead reserve the most differentiating variables to effectively distribute the target audience into more homogeneous population cohorts. Each group is modeled independently, and then reassembled into a single target audience with optimum response propensity. As we said, variables with significant value differences across different groups make good candidates for nesting within the overall ensemble. In the example below, we see that consumers’ state of residence is a meaningful separating factor because of very different population attributes. In the example below, we are focusing on the 64+ population. Nesting is not necessarily limited to a single variable split; indeed, the modeler can further refine and tune the final model through multiple levels of nesting. This has become a far more feasible approach than in the recent past due to fast (usually cloud-based) computing resources and statistical software applications that facilitate builds like this. In our example, we find that we can leverage many of these demographic variables to optimize response for our life insurance direct marketing campaign. How does this approach work in reality? The effectiveness of response models is measured by lift, a statistic that demonstrates how much mailing efficiency the final model yields with actual response rates. In the chart below, “global model” is the application of a single, traditional response model. “Individual state models” refers to models constructed like the diagram above demonstrates, and “best model for each case” selects the higher of the two resulting propensity scores for each prospective consumer. The bottom line is that with a smart, thoughtful nested modeling approach, an insurance company would realize enormous savings in its direct marketing costs. Reach us to see how our approach can benefit your business.
First, the consumer will have from October 15th to December 7th, 2018 for AEP. Then from January 1st to March 31st, 2019 there will be an open enrollment period. What communication plan do you have to first indicate that you would like to be the healthcare provider and then insure they are satisfied with their choice? At DDG, we segment this audience into market segments*: Consumers who wish to become a Medicare Advantage Member: 1,049,182 Individuals who prefer to purchase Medicare Supplement Insurance: 1,255,367 Persons who desire PDP (Part D) only: 937,833 Dual Eligible individuals: 488,602 Special Needs Persons (SNP): 6,621,042 Turning 65** 3,342,487 Turning 66** 3,342,487 Turning 67** 3,236,222 Movers*** 1,305,457 These audiences are very useful in AEP campaigns—direct mail and Facebook. We call these custom audiences-dataFaces. However, OEP will present a different challenge. Our market(ing) research does indicate that many consumers can not accurately describe the form of Medicare coverage they possess. Do you have a Medicare Advantage Plan? Does it include prescription drug coverage? Did you purchase a Medicare Supplement policy? Are you dependent on only Medicare Part A and Part B? Thus, it is certainly understandable that the member can become very dissatisfied with their coverage during the following months. For example, did the individual consumer grasp that the PDP selected should match the prescription drugs that they are currently using? Does your customer service groups have training that enables them to assist the consumer in making the choice that optimizes their satisfaction? Or does your member learn that they had choices from their neighbor and thus becomes irate that your firm did not explain. To measure your risk of “members switching” you can consider both a. market research and b. churn analytics. Obviously, the goal of the two exercises is different but both can provide you with keen insight for member behavior in OEP.
In the extremely competitive world of healthcare acquisition, many firms seek a reduction in the cost per thousand mailed. In fact, if a procurement style of cost management is in place that is your KPI. For many years, this approach was sufficient for success. In today’s fragmented consumer marketplace, the focus must be on audience identification. Who wants to buy our policy? Not every consumer over 65 years old wants to buy our specific product-Medicare Advantage or Dental etc. The shift from Cost per M to Cost per Lead is often perplexing due to the increase in cost for the audience/mailing list. It seems illogical to spend more per thousand. However, it is required. Standard demographic mailing: List $20.00/M Total mail cost $350.00/M Response rate .006 Cost per lead=$58.33 (350/6) But if I raise the cost of the mailing list to $70.00/M or $50.00/M higher and get a response rate of 2.0 percent what is the outcome? Propensity based mailing: List $70.00/M Total mail cost $400.00/M Response rate .02 Cost per lead $20.00 each (400/20) The client that I mentioned reduced their mail volume by 3 million pieces and saved over a million dollars annually. By switching their KPI. If your organization has put procurement in charge of your marketing expenses then I recommend you stop and review their decisions. Efficient targeting is the key to lower cost per acquisition as opposed to lowest cost per thousand mailed.