165: Get more granular with your user data

Aggregated opt-out data might be hiding the important stuff

Many years ago I read a science fiction book about a political organization that recruited people from key demographic groups to wear a special watch that would allow them to see and hear all of a politician’s public statements. The watch also measured the wearer’s reactions and fed that back to the control room, where they could see in real time how people were reacting to different statements.

That organization’s candidate had some implant in his brain that allowed some technician sitting in the control room, watching all these monitors, to turn dials one way or another based on this feedback, and change what the candidate was saying. The tech would turn up the empathy dial, or the law and order dial, or whatever was necessary.

That’s science fiction, but isn’t that what political parties would do if they could?

That kind of real-time data is far more valuable than some after the fact “did you like that speech?” questionnaire, because sometimes it’s just one thing in a 45-minute speech that turns somebody off. You need to know what that one thing is.

This morning on LinkedIn I saw a post that was so stupid that I unfollowed that person. I don’t know if that person would care, but assuming he did, wouldn’t it be useful to know which post triggered that action? Let’s say this person posts 10 things in a week. Does a weekly average unfollow rate really help, if 90 percent of the unfollows were in response to a particular post?

With more granular data you can isolate the particular topic, or theme, or style that’s making people leave.

In a similar way, there are themes that show up in some TV shows that are immediate turn offs for me and my wife. As soon as they go that direction, we stop watching. Wouldn’t it be good for the network to know that?

In yet another application, I write books, and some of them are available on Kindle. I want to know a lot more than just whether someone bought the book or liked it. I want to know if they made it all the way through, and if not, where they stopped. That kind of feedback could help me craft better books. In fact, I’d like to know on a page by page basis whether the reader is enjoying the book.

Amazon doesn’t give me that information, by the way.

Now let’s apply this to your email marketing. If you look at aggregated opt-out numbers – over the course of a month, say – you might miss an important signal. Maybe most of the people who opted out did so because of one particular email. Maybe it was too political, or you used a new kind of image, or a new from address.

You need to get granular if you want to find out what’s driving your customers’ actions. Look at opt outs on an email by email basis and not just on an aggregated basis.

You can do something similar with your web-based content. There are services that can tell you how far down the page people get before they leave.

That sort of detail can help you craft a better product.