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.
Metrics are not usually also Models; the metrics have to be fine-tuned / combined and built up into models. And executing this process usually depends alot on what type of business is being analyzed, and what kind of problem is targeted for a solution. So while it’s pretty simple to define a metric, creating a version of the metric that specifically addresses the challenge at hand can be a bit more difficult. Not hard, mind you; it mostly just takes a decent understanding of how the business works. Want some examples? Read on, O Fellow Driller …
Q: Is Latency, as a metric, out of the question when the spread of the number of days in a latency period is so wide that to average them out and call the resultant figure “Acceptable days to date of predicted purchase” would seem meaningless? I am thinking about the disparity in latency between customers who are Heavy, Moderate and Low users.
A: I’m not sure I have enough context to understand the question (what are you trying to accomplish by using the metric?) but Latency is what it is. In other words, you take your clue from the existing behavior itself. If the average Latency for a certain segment is 2 years, well, it is, and that’s not too long or too short, it just is. Whether you can act on that information is another story; it depends on what you are trying to accomplish.
For example, average Latency on major home appliances, depending on brand, is anywhere from 5 to 10 years. Is that too long of a “spread” to make the metric useful? No. It just is what it is, and you deal with it. Typically these ideas are used to reallocate marketing spend away from waste on unresponsive segments towards segments that will generate incremental profits.
Continue reading Modeling Defections – When is a Customer No Longer a Customer?