Tag Archives: Customer State

LTV Not Just About Sales & Marketing Data: Check Service Problem Outcomes

Analytical Culture, Customer Experience, DataBase Marketing, Driller Q & A, Marketing thru Operations, Measuring Engagement, ,

Jim answers questions from fellow Drillers
(More questions with answers here, Work Overview here, Index of concepts here)

Topic Overview

Hi again folks, Jim Novo here.

Often we spend a lot of time talking about analyzing “customer data”, and the implication is we are looking at marketing or sales related information. That may be true for companies just beginning to use customer data; this data often is the easiest to understand and access. But true data-driven organizations have analysts who reach across the silos for data, looking for customer service or operational customer data that can impact the current and potential value of the customer. We have one such example from a Driller today.

Sound good? Then let’s do some Drillin’!

Q:  I work as a management consultant, currently working in a project where my client (Oil & Gas company) is trying to calculate and implement Lifetime Value into one of their businesses.  One of their business units (Industrial Lubricants) sells different kinds of lubricants and services to corporate customers such as Ford, Toyota, BMW, etc.  They have already done some customer profitability analysis and they are currently trying to calculate Lifetime Value.

A:  That’s a pretty interesting place to find a concern for analyzing LTV…

Q:  My questions:

1. What’s the best way to forecast future cash flows in a B2B scenario where models such as RFM are not relevant (Recency and Frequency do not really apply given that their customers have been with them for ages and are often in long-term contracts).  How can I project customer profit over time and how can I estimate the “lifetime” of individual customers?

A:  Well, it’s not that Recency and Frequency don’t apply, they probably apply in a different way.  In most businesses driven by contracts, service is the issue.  So you need to look for Recency and Frequency of “problems”, whatever that might mean in the industry.  I imagine “logistics” is an issue for these businesses – on time delivery, quality, “ease of use” (which could cover many factory / service issues), packaging, and so forth. This can take a lot of research, particularly if there are no “systems” capturing this kind of data. But usually, even in very old line companies, there is some place where this data resides. You just have to find it and get access to it.

Often in an environment like this it is easier to work backwards – first, identify defectors, then look for service issues or changes in behavior that imply service issues – declining order size / Frequency, expanding order Latency (weeks between orders) and so forth.

Continue reading LTV Not Just About Sales & Marketing Data: Check Service Problem Outcomes →

Creating Effective Retention Campaigns

Analytical Culture, Analytics Education, Customer Experience, DataBase Marketing, Driller Q & A, Marketing thru Operations, Measuring Engagement,

Jim answers questions from fellow Drillers
(More questions with answers here, Work Overview here, Index of concepts here)

Topic Overview

Hi again folks, Jim Novo here.

Have you ever offered a $100 off coupon to a new retail customer? I have. And guess what? There was no response, even though the average order size across all customers was $38!

So how is this kind of situation possible? Some products attract customers that are only interested in that product, and they are not going to buy again – period. Knowing this, the question for you: is this the kind of product you want to constantly feature / promote?

Guess that depends on the Drillin’, eh? Let’s get to it …

Creating Effective Retention Campaigns

Q:  Hi Jim,

Love your newsletters.  Do you have a tip jar I can use to donate to the cause?

A:  Hmmm…maybe I ought to start one…nah.  It all works out in the end!

Q:  Take a look at this chart I did of cumulative customer purchase Recency (actual numbers changed but the relationships are same): See below for explanation **

** Jim’s Note: How to read the chart:

“In the past 3 months, (“3” on horizontal axis), 30% of our customers have made a purchase (“30%” on vertical axis).  In the past 7 months, almost 40% of our customers have made a purchase.  Because the last category is “last purchase 36 months ago or longer”, the chart includes all customers – 100%.  

Since each customer can have only 1 “most Recent” purchase, each customer is on the chart only once.  Therefore, if 40% of customers have made a purchase in the past 7 months, 60% have not made a purchase.

Q:  What does this pattern (the % of total by group) tell one generally about the attrition in the business model?  It’s interesting, I’ve never looked at this kind of diagram before.  For our business (wine retailer with “club” option), I generally consider anyone with a transaction in the past 12 months to still be a customer.

Continue reading Creating Effective Retention Campaigns →

Analyzing Airline Customer Frequency Programs

Analytics Education, Customer Experience, DataBase Marketing, Marketing thru Operations, Measuring Engagement, ,

Jim answers questions from fellow Drillers
(More questions with answers here, Work Overview here, Index of concepts here)

Topic Overview

Hi again folks, Jim Novo here.

Recency and the RFM model are both very powerful predictive models of customer behavior, But they’re not always the BEST models to use, because the nature of some business activities do not create the kinds of behavior these models are good at predicting. For example, any business – or segment of the business – that is likely to have a rhythmic repeating behavior (event occurs every week, or every month, or every summer, or every Christmas, etc.) will not benefit much from Recency analysis. But it is ideal for Latency analysis – when to expect an event, did it happen or not? Great example of both ideas in a single business would be the airline business – you have random flyers, and you have frequent flyers. Use Recency for random flyers, Latency for frequents. You dig? Great, let’s Drill it !

Q:  Can you please direct me to specific information (in your site) regarding analyzing data in the Airline frequent flyer programs?

A:  There isn’t anything specific to airline frequent flyer programs on the site, so I’ll create something though with this reply!

Q:  Are there any “success methods” that proved to be the right way to define one flyer over the other?

A:  Not sure what you mean by “define”… the triggers I have seen used in these kinds of programs usually have to do with changes in rate balanced against the value of the flyer.  So, you look for slow-downs in frequency, for example, people who used to fly 3 times a week that now fly only 1 time a week.  Their “fly rate” has dropped significantly and could be a flag for potential defection.

Q:  I’m familiar with the RFM method, and wonder how to implement an RFM score considering that you have a: 

* Flyer that is true loyal and doesn’t have any interest in flying to other parts of the globe (expensive long mileage ones) and yet,

* due to the method of RFM you will not find him at the “top customers”.

Well, I’m not sure RFM would be the right model for this kind of program.  You want to look more at a “rate of change” kind of model since there are many levels of activity and Recency isn’t always a controlling factor.

So for example, you could create “Frequency buckets” based on deciles – divide customers into Top 10%, second 10%, third 10%, 4th 10% down to the bottom 10% based on their annual Frequency.  Then track people based on how they are moving between the buckets.  Somebody who was in the Top 10% that falls down to the third 10%, then falls lower in their annual rate would be a likely defector.

Continue reading Analyzing Airline Customer Frequency Programs →