Logo
BodyBGTop
Propensity Modeling: How to Predict Your Customer’s Next Move
Knowing what, when, and why your customers are going to buy may seem impossible—unless you use propensity modeling, and use it correctly.
Posted Nov 10, 2016
Page 1

Do you know what, when, and why your customers are going to buy? Many brands embark on an obsessive quest to find these answers, pouring valuable resources into data-driven campaigns and big-budget strategies—yet real results often remain frustratingly elusive.

Customer data is deemed to be a precious commodity, but its true value can only be determined once it’s been put to the test. Many brands have massive databases that look impressive, but on closer inspection contain out-of-date or irrelevant information. Furthermore, a lot of marketing communication misfires, targeting people with incorrect or untimely advertising.

This is why more marketers and salespeople are experimenting with a form of predictive analytics called propensity modeling. This tool is helping brands better understand and predict precise customer behaviour. We recently used it to help a leading car manufacturer determine the next model of car a prospect would buy—with 80 percent accuracy.  

Of course, there are some challenges to getting it right. Brands need to make sure that they don’t use too many (or too few) customer segmentation models. They also need to conduct regular data checks to ensure that the customer information is fresh and correct. 

What Is Propensity Modeling?

Essentially, propensity modeling correlates customer characteristics with anticipated behaviors or propensities. It tracks buying habits as well as other actions such as a customer’s propensity to open a marketing email, sign up to a loyalty program, or participate in feedback surveys.

Its success is underpinned by the quality of your customer data and how effectively it’s segmented. Say you’re a national retailer with physical stores and online channels. You have three customer segments defined by their shopping frequency and spending. Namely, the frequent shoppers, the slow-and-steady customers, and the at-risk customers.

Applying a propensity modeling predictive tool to each of these customer segments will allow you to develop a far more successful, long-term sales strategy—one that responds to growth opportunities with proactive and timely cross-selling and upselling campaigns.

For example, what is the retention probability of your frequent shoppers? Is the frequency between their shopping trips, or the amount of money they spend on each shop, increasing or declining—and if so, why? Why do your frequent shoppers prefer to shop with you, and how can you leverage this knowledge to influence your slow-and-steady and at-risk customers?

Armed with this knowledge, you can pursue far more effective selling techniques that build better customer relationships. You’ll be able to track how certain marketing and sales communications influence buying behavior over time and deliver highly targeted and personalized messages that hit home. Ultimately, your customer retention and acquisition strategies will see a faster and greater return on investment—saving your brand time and money in the long run.  

Segmenting Your Customers

Personalized customer communications can be tricky to get right for brands of any size. It’s all too easy to create too many customer segmentation models, breaking up your target audience into an impossibly diverse list of personas. Or, on the flip side, to create too few and use only a handful of overgeneralized stereotypes.

To make the most of your marketing budget, you need to focus on the customers who are going to spend the most on your brand. If a persona is unlikely to generate profit, then you need to either drop that persona or reduce your investment in that specific group.

Another common mistake is when marketing teams use their own experiences to reinforce their brand’s personas. Instead, they need to focus on analyzing and using the real customer data they have on hand.

Running Regular Data Checks

Data does not last forever. Out-of-date customer information will affect the quality of your models and end up costing you more money and time. A lot can happen to a customer in a short space of time; they could get married, move, have children, start studying, become a vegetarian—the list goes on. 

You have to continuously learn about your customers and update your data in real time. Every time you engage with them, use it as an opportunity to gather more information. Don’t just expect personal details to be handed over willingly—you need to offer something in return to make it worth your customers’ while, a value exchange that bonds them ever tighter to your brand.

Remember that not all data is valuable, so test and delete unprofitable data sets. To avoid getting into a situation where reams of useless customer information crowd out important, relevant data, it’s best to determine the accuracy of all your data at the source; effective value exchanges will help.

Technology is increasingly proving its worth as a valuable tool for marketers and salespeople alike. That said, it won’t do all the work for you. To get the most from the tools on offer, you need to apply some strategic thought—and really get to know your customers.


Jason Lark is managing director of Celerity, a data, marketing, and technology consultancy. He cofounded Celerity in 2002, and continues to lead the company’s vision, strategy and operational performance.

Page 1
To contact the editors, please email editor@destinationCRM.com
Every month, CRM magazine covers the customer relationship management industry and beyond. To subscribe, please visit http://www.destinationCRM.com/subscribe/.
Search
Popular Articles
 

BodyBGRight
Home | Get CRM Magazine | CRM eWeekly | CRM Topic Centers | CRM Industry Solutions | CRM News | Viewpoints | Web Events | Events Calendar
DestinationCRM.com RSS Feeds RSS Feeds | About destinationCRM | Advertise | Getting Covered | Report Problems | Contact Us