|
Thanks for visiting the
original Drilling Down web site! Get
the book at Booklocker.com
Customers Speak Up on Book & Site Workshops,
Project Work: Retail Metrics & Reporting,
High ROI Fresh
Customer High
ROI Customer LifeTime
Value and Intro to
Customer Customer
Model: Measuring
Retention CRM
Analytics: Pre-CRM
Testing for See Customer
|
Drilling DownTurning Customer Data into Profitswith a SpreadsheetSite and Book topic: Maximizing marketing ROI with customer behavior analysis
Learn
Methods, Metrics |
Drilling Down Newsletter # 17 - February 2002Drilling Down - Turning Customer Get the Drilling Down Book! Prior Newsletters:
If you would rather jump to certain topics, use the "In this Issue" links below. The first issue of the year brought a lot of responses from you to
my request for changes to the newsletter format and content.
Here are the top 3 requests with my responses to them: Request: Clarify the content of newsletter versus the website; how do subscribers keep up with "what's new?" Response: Virtually all new content goes in the newsletter before it goes on the web site, either as a full text version or a direct link to the new article. If you read the newsletter each month, you are exposed to all the new content available. I consider newsletter subscribers, who to a great extent have purchased my book (Thanks!) my primary customers, and they get all new content first. Then the content goes up on the web site. Request: Provide more "how to" examples and less vague theory. Response: Oh, you hurt me so! It's difficult to provide meaningful examples without providing the backbone theory that helps a reader understand the examples. That said, what I will do is scale back on the theory and provide more examples for each concept. So instead of 70% theory; 30% examples, we flip it over and go with 30% theory and 70% examples. In effect, this change means we will cover each topic more deeply and completely, but not cover as many topics in a year. This tracks with the general comments I have received over the past year on the newsletter, so I think people will dig it. As usual, comments on format and content are appreciated! Best of the Best Customer Retention Articles This section flags "must read" articles moving into the paid DM News archives before the next
newsletter is delivered. If you don't read these articles by the date listed, you will have to pay
$25 to DM News to read them from the archives. The URL's are too long for the
newsletter, so these links take you to a page with more info on what is in the article
Note to web
site visitors: These links may
Attitudinal Data: CRM’s Crystal Ball ------------------------------- Recall the events of Part 1 (Measure) - the owner of Salon B used a simple spreadsheet to look at the last visit date of best customers, and found these issues with them:
The owner of Salon B has Measured the Customer Retention situation, and thinks: I must be crazy for not looking at this before. I would make more money by not cutting hair for a couple of hours a week if I used that time to get even one of these high value customers to start making appointments again. Now that I have Measured this effect and know how much money it is costing me to not address the tardy Angela customers, I need to Manage this situation. Over at Salon A, the owner knows the names of best customers who "have not been in for a while". But this owner has no system, no way to measure what the dynamics of the situation are. How long is "a while"? But at Salon B, the owner knows the average time between best customer visits is 40 days, and there are customers in this group who have not had an appointment in over 6 months. How can the owner get this business back? The owner thinks: I'll just mail all these best customers who have not had an appointment in over 6 months a postcard offering them a discount. The postcards will say, "Since you are a best customer, you are entitled to a 15% discount if you come in for a visit within the next two weeks". They will come in and I will start a new relationship with them, and find out why they have not been in. The owner of Salon B prepares the targeted postcards, mails them out, and awaits appointments from these best customers. The appointments never come. A bunch of the postcards come back as "undeliverable", and the owner gets several phone calls from customers saying "I now go to Salon A, take me off your mailing list". Undaunted, the owner of Salon B reasons: Clearly there is something wrong with this approach. Best customers who have not had an appointment for 6 months must already be "defected" customers. They obviously do not want to come back to me, and feel the relationship is broken already. They have moved on and established new relationships with new vendors. I will try a new approach with the postcards, and will use the same offer. But this time, I will mail the postcards out as soon as the best customer has not been in for over 40 days. Since the average best customer comes in every 40 days, a best customer who fails to do so is not acting like a best customer should act. So each week I will use my spreadsheet to identify best customers who have not been in for 40 days, mail the discount postcard out to them, and track the results. After a month of mailing the weekly 40 day postcards to best customers, the owner of Salon B sat down to analyze the program. Of all the best customers mailed to, 25% had made new appointments, and 75% had not. So in the short term, the owner had cut the 20% best customer defection rate to 15%, because 1/4 of the best customers called to make appointments at $150 each - minus the discount. But even with the discount, the additional profits from these customers paid for the postcard mailing many times over. Despite this success, two things bothered the owner of Salon B. The first was what customers who responded said when making their discounted appointments. The second was the 75% of best customers who did not respond. The owner thinks: Half the customers who responded said to me, "I'm so glad you mailed me a discount, I was planning on making an appointment in the next week and would have made one anyway, so it was great to get the discount". So I gave up margin and profits I did not need to give up. And how is it possible that so many of my best customers never responded to my offer? I wonder if there is a way to address these two issues? If I could reduce the number of "would have come in anyway" customers who got a discount, and increase the overall response rate, I would be really making a ton of money on my best customer retention postcard program. I have Measured my best customer defection, and am Managing it with this program. I wonder if there is a way to Maximize, to make it even more profitable? Next month, we'll check back in with the owners of Salon A and Salon B and see what happens. Will Mary Lou ever show up at Salon A? Is there a way to make more money in this program? Only the data knows for sure... Go to Part 3 of the Hair Salon Example -------------------------------
Questions from Fellow Drillers Q: I am reading your eBook (up to page 67) and I am trying to relate the material to work. A: That's a good idea! Especially if work paid for the book. If you paid for it, then work is lucky to have you.... Q: I am involved in Data Warehousing and I am looking at defining some datamarts for our Sales people. A: Perfect application for the book, will give you a "common ground" to work from across anything you develop. Q: Could you please help me with a question that has been
nagging me...Over what period of time should we calculate Frequency? A: If I can imply from your e-mail address that you work for (large casino and sports betting organization), and the business we are talking about is the casino / sports bet business.... Well, they all are useful, in their own way. Generally, you want to use long cycle models with long cycle events and short cycle models with short cycle events. For example, retail purchases are pretty short cycle events, with supermarket probably the shortest of them all. Enterprise Software and heavy duty truck purchases are long cycle events. But within both of these long cycle events, there are short cycle events, such as software upgrades, replacing tires and exhaust systems, etc. One way to "pin" the cycles down is to look at inter-event Latency - the average number of days or weeks between the events. If you are profiling casino visits and they happen on average twice a year, the "cycle" or Latency is 6 months. Running an RF model at 30 days doesn't get you much traction with a 6 month cycle. I would run it over 12 months, or twice the cycle rate. The closer you get to the actual latency in the cycle, the more accurate the model can become, but the more erratic it can get over disparate groups. This begs a question: can you split the population and RF model each segment by itself? Sure! Say you have a top 20% group, and these people visit on average every 2 months. Then you have everybody else, who visit on average 1x a year. So the model for best customer would be over 4 months (twice the cycle time) and the model for the others over 2 years (twice the cycle time). That way you adjust the model to hang more closely with the behavior, and increase the overall accuracy of the models. Q: P.S. Like your book. A: Great, that's good to know. A little surprising, but IT people like the book quite a bit. From what I gather, the book helps IT people "get" database marketing enough to work on requirements, and provides a tangible platform to discuss behavior modeling issues with marketing folks. Hope I answered your question, and feel free to keep asking -
you're a customer now! ------------------------------- Any comments on the newsletter (it's too long, too short, topic suggestions, etc.) please send them right along to me, along with any other questions on customer Valuation, Retention, Loyalty, and Defection here. 'Til next time, keep Drilling Down! - Jim Novo What would you like to
do now?
Get
the book with Free customer scoring software at: Booklocker.com
Amazon.com Barnes
& Noble.com Find
Out Specifically What is in the Book Learn Customer
Marketing Models and Metrics (site article
list) |
The Drilling Down Project. All rights reserved.