Category Archives: Analytics Education

Actionable Customer Retention Measurement

Jim answers questions from fellow Drillers

Topic Overview

Hi again folks, Jim Novo here.

Simple question below, not so simple answer. There’s a lot of conflicting ideas floating around on the subject of how to measure customer retention properly, and to be honest, it really does depend on the type of business we’re talking about. Further, in order to properly measure customer retention – in a way you can take action to improve retention / increase profits – you have to define it first, and that can be as much of a challenge as the actual measurement. Ready for a trip down into the depths of this area? Hang on, it’s quite a ride, you Driller you …

Q:  How do most companies measure customer retention?  Is there a formula?

A:  The short answer is not many companies outside of specific industries are very adept at customer retention – yet.  For traditional (not-online-born) companies, it is most commonly used in telecommunications, financial services (including insurance), direct marketing (catalogs / web sites, etc.), subscriptions / publishing, and the travel industry.

The reason for this concentration: these industries have traditionally collected detailed data on customer interactions as part of the offline business model.  Now that many other industries are collecting data on customer interactions online, the lessons learned in these “lead” industries are proving quite valuable for industries new to direct customer interaction.

A “standard” way to measure it, if you are looking to align your metrics with Wall Street and your financial statements for example, is “12 month active”.  Any customer you have had contact with in the past 12 months is still a customer, any customer with no contact in the past 12 months is a defected customer.

This is a retail / mail order oriented view, and if you sell products, then “contact” means “purchase”.  If you are in the services business, it could be any contact – phone call, e-mail, sales call, download.  Divide the number of 12 month active customers by the total number of customers and you have your retention rate.

There is no reason you can’t use “24 month active” or “36 month active” or “5 year active”.  The point is to define what retention is for your particular business and stick with it.  Get agreement on what makes sense for a measuring stick and try to improve.  Often your own data will tell you what the best “no activity cutoff” is for your business.

Retention is really a “continuum”, and retention rate is always “relative” to your perspective.  If you use a very “tight” definition like “12 month active”, you will lower your retention rate.  As you expand the time period, your retention rate rises.  The problem with most companies is they expand this cutoff time period to infinity, meaning every customer is still a customer unless they notify you they are not.  Is this a useful measurment? Doubt it…

Continue reading Actionable Customer Retention Measurement

Branding vs. Direct Marketing Metrics

Jim answers questions from fellow Drillers

Topic Overview

Hi again folks, Jim Novo here.

Oh dear. A marketer caught between branding and direct. Each approach has it’s own data and metrics that either can be important or not to the folks working with the other approach. Can the measurment of success using these two approaches be reconcilled? It’s possible, but does that make sense if the “success outcomes” are radically different? Gonna be a deep Drillin’…

Q:  We constantly try to quantify the value of web sites as a branding vehicle.  The thing that keeps gnawing at me is we will often report the average time spent on site.  This seems like it should have a value we could wrap into our ROI, but as it is, it stands largely on its own.  

Are you aware of, or have any thoughts on, how we might put an actual value to this?  Is it enough to show lift without respect to time, and to talk about return visits in terms of frequency models, or is there some way to drill down to a fundamental value of what a person-second on your site could be worth (obviously the content of the site will impact how much of that value you actually got)? 

A:  I’ve done a bunch of work like this and personally, I think you measure branding with branding metrics and direct with direct metrics.  If the CPG people understand the value of advertising in terms of brand affinity, recall, intent to purchase, and so forth, then it seems to me that is what you measure.  They have already made the “final connection” between these metrics and ROI, so it’s not really up to the marketer to make those connections.  They believe increasing intent to purchase = advertising worked.  And I’m not sure you really can make a connection, because the “units” you are measuring are different and the math ultimately fails.

Here’s why.  Traditional advertising has never been judged by the “value of the customer,” it is judged by the “value of the media.”  The customer is “reach” and has no individual value; individual customers are totally exchangeable as long as the reach is the same.  Any single person is irrelevant; it does not matter what they do or don’t do.  If there is no “customer,” I’m not sure how you would ever get to ROI.  It is assumed from reach comes sales, and this is proven using branding metrics, not ROI.

Q:  I’ve gone back and forth on this and approached it from a few different angles For example, determine cost of 1 second of TV advertising per person.  You could use this information to calculate how much it would have cost to communicate the total person-seconds you had on your site in a particular month, but this is fraught with problems as you might guess, and am looking for another point of view.

Continue reading Branding vs. Direct Marketing Metrics

Customer Segmentation: Tangible vs Intangible Cost, Let Data Define Segments

Jim answers questions from fellow Drillers

Topic Overview

Hi again folks, Jim Novo here.

This month in the newsletter we answer questions on the nitty gritty of the actual discovery work by taking a very deep look into the whys and hows of segmenting customers. Straight-up and to the point, put on those data shoes and Let’s do some Drillin’!

Q:  Hi Jim, I’m a great fan of your work!

A:  Well, thanks for your kind words.

Q:  I have a basic question for you.  We are an online retailer and thus use email as the primary marketing communication channel (we do use Direct Mail to our best customers around holidays).

A:  Those are smart choices.  I’ve seen some stats on using direct mail to drive lapsed online customers either back online or into a store that are very encouraging, real money-makers for retail.  Definitely worth testing, though in both cases, the product mix averaged higher ticket than your category typically does.

Q:  However, we don’t have a set customer segmentation technique and thus no specific customer segments.  One outside consultant, a statistician, had suggested looking at a new customer’s activity in the first 30 days and then classifying them into High Spender, Frequent Transactor, etc. segments.  Not sure how well it works.

A:  That’s quite unusual, I think.  It would work in the first 30 days, but I think you would have to re-classify every 30 days using a scheme like that.  Considering web-only behavior, the typical retail lifecycle beyond 2nd purchase (many buy only one time) is a ramping to a peak and then a more gradual, but still steep, falloff in purchases.  The model above would not take this into account, and while the initial label might be accurate, it soon would not be.  That’s not to say these kinds of models don’t work, but it usually takes years of testing and study to perfect them.  “Data miners” often believe the numbers will simply tell them things like this, but they don’t take into account the human behavioral and other mitigating factors which may not be in the data.  

For example, Recency and Latency are really “meta-data” about customer behavior; they are data created from other data.  You can’t just look at the first 30 days of transactions and give a customer a label; customers have LifeCycles and you drive the highest ROI when you take advantage of knowing these cycles and acting on them to increase profits.

Q:  I feel that we target our customers primarily by their category purchases, and not by any kind of behavioral model.

Continue reading Customer Segmentation: Tangible vs Intangible Cost, Let Data Define Segments