The typical output of a model, usually called a “score,” is essentially a ranking or estimation of the most likely business outcomes, such as the most likely customer behavior in response to a stimulus (or the absence of a stimulus).

A score is not a decision. A decision is the proactive response of the business to the prospective customer behavior, usually involving the expenditure of resources and the monitoring of the performance of this decision. In a financial services setting, examples of these decisions include marketing, sales and service contacts with customers, debt recovery activities, and financial crime prevention decisions. Outside of the financial services industry, comparable examples of decisions are markdown and assortment in the retailing market, pricing and contract design in the telecommunications industry, preventive care program development, and outreach in the health care provider industry.

Lessons learned tying model results to decisions:
ƒƒ

• The best rules systems implement business rules based on judgment and experience, as well as rules that prescriptively advise the SME on the trade-offs between alternatives in pure dollars and cents terms.
  ƒƒ
• The best performing offers and treatments are not the ones you will issue tomorrow. Instead, they will be the offers that your organization has refined over multiple waves of disciplined, rigorous trials paired with conscientious measurement.
  ƒƒ
• Business teams that commit resources to decisions will require the most convincing about the veracity of the analytic model results. Ensure your analytic story about the findings and recommendations of the model are well suited to these groups. Explain the nuances of customer behavior in terms that resonate with your audience. Find a willing listener from that constituency to help you develop your explanations in advance of the big presentation.

Learn more by reading our Red Paper Model Deployment: The Moment of Truth.

1. Client recognition, matching and householding
2. Access to the complete view of the customer: including their products, transactions, and behavior
3. Next best offer analytics
4. Omnichannel marketing and sales orchestration

In the analytics media right now, “customer journeys” are cool and topical, but predictive customer journeys are even more inspiring, because they go well beyond telling you what’s already happened, into the zone of what’s likely for each of your customers to do next, and what you can do about it to present a timely strategy or treatment. This helps you improve offer timing, relevance and profitability.

You might have read some of our case studies in this area such as Five Lessons Learned From Predictive Customer Analytics or What Does a Predictive Customer Journey Look Like.

What you probably don’t know is, while customer journeys just became cool in 2017, we were building predictive customer journey strategies back in 2005 with a customer loyalty decision sciences program for one of the country’s prominent payment platforms.

Here’s how the program worked. The payments platform marketers selected a nationwide merchant for a sales stimulation offer, like $25 cash back at the point of purchase on a purchase of $100 or more. The strategy was that these could only be cardholders that hadn’t purchased anything using that card at that merchant’s stores anywhere in the country in the last six months. This dramatically increased the direct attribution of these offers towards cardholder response.

In terms of targeting, it would have been easy to simply contact those customers who had purchased at the merchant’s direct competitors, or had high RFM (recency, frequency, monetary) behavior in that merchant’s broader category (e.g., retail apparel, or airline travel, or small office/home office, or retail technology). Of course, we did use that sort of information as an input in our scoring and segmentation approach.

Looking back, we did something else that turned out to be even more powerful. We had access to 13 months of individual transactions for over 60 million cardholders. We built behavioral profiles of customers that ought to have purchased with that merchant (but didn’t), based on their purchasing similarity to other customers that actually had purchased from that targeted merchant. This meant looking at purchasing patterns across virtually every merchant category, the timing of those purchases, and the sequencing of relevant purchasing events by week and by month.

Using those advanced approaches, and comparing to several comparison approaches (i.e., using only purchasing history with the merchant’s direct competitors, or using random selection with the same cash-back incentive), we found our approach usually beat every other approach by a wide margin. Performance analytics revealed that most importantly, we could get the offer timing right based on who was primed for such a purchase.

We repeated this set of market tests for over 18 months, building more than a dozen of these major campaigns, improving the approaches, and generating tens of millions of dollars in increased spend incremental to the other test cells in our campaigns. We also leveraged this approach with some other credit card issuer clients of ours, seeing whether these approaches would work as well for customer retention tests as it did for sales stimulation (it did).

This is one of the client experiences that led us to create the Corios tagline, “We tell the story numbers can’t”, because we found we were literally telling a story about consumer purchasing patterns that perhaps nobody else had discovered yet. We were lucky to have access to such a massive repository of transaction data was so difficult to put in one place, given the technology capabilities of the time.

Since then, we’ve generalized the approach to go well beyond credit cards, and applied it in all sorts of other financial services, manufacturing and retail domains, for marketing, risk and financial crimes behaviors, and focusing on telling stories about the customer journey across the omni-channel experience.

Do you want to know more about predictive customer journeys? Send us a note to [email protected] to start your own journey.

Next best offers: As marketers we have many offers we can target and deliver, each to a large pool of customers. The question remains, what are the best offers to make, not only measured by what’s best for your company, but more importantly what’s best for your customers. To qualify as “best”, these offers should be customer-relevant at that time in your customer’s relationship, and address their unmet needs.

The most conventional (but least effective) approach to select the best offers relies on sorting by the most profitable products and executing those offers to the company’s best customers. A more effective approach is to sort and target the best customers first; this is better but far from the ideal strategy. We’ve found the ideal strategy in almost all situations is to target individual offers to individual customers through the customer’s preferred channel at the best time for that customer. Sure, this is analytically and operationally challenging, but the results we’ve seen in more than 80 cases with our clients has proven this to be the winning strategy. We’ve also found that the technical and operational challenges are really not the limiting factor. Instead, it’s the change management required inside the company to fundamentally alter the way offers and channels are prioritized, how success is measured, and to convert the organization from a product-centric mentality to a customer and contact strategy focus.

In order to overcome this cultural challenge, we’ve found it is the most fruitful to put this capability right in the hands of relationship managers in the sales field, because their top-line revenue contribution is vitally important and they are always willing to consider prudent ways to spend more time with the customers who are actually interested and in the market. Correspondingly, we converted our approach to next best offers to not focus only on the needs of marketers, but also to focus on sales management and relationship managers.

How did we do this? First, we delivered our next best offer strategies through CRM platforms like Salesforce and Dynamics, which are the most common platforms our clients use.

Second, we converted the format of each next best offer into the structure that relationship managers want to consume. Specifically we added a sales narrative to each next best offer. Sure, we still perform our selection of offers using sophisticated analytics approaches, but frankly, the details of those approaches aren’t that relevant to our relationship manager audience. Instead, what they find useful are business-friendly English descriptions about each customer’s profile and what makes them likely to prefer that offer. This aids the relationship manager by giving them a clear set of tips to start the conversation. For example, “how other customers like you use this product, and the value they get out of it” is better than having only information from the product manager’s perspective.