Business Intelligence Network business intelligence resources

Blog: Pete Loshin

« IBM virtual Linux environment beta program | Main | Windows Pricing: Economics of Competing Against Free »

Making Sense out of Data

Go read this article by Matthew Haughey: How Ads Really Work: Superfans and Noobs, and then think about how you can turn data into knowledge.

If that doesn't convince you to drop everything and go read the article, here's my quick summary:

In one sentence, what Matt (re-)discovered is the old 80/20 rule, also known as the Pareto Principle, or power law (this one's an article about power laws and blogs.

Matt was using Google Analytics and found that most of his ad revenue came from "noobs" (one-time visitors who are on the search for something), with most of his loyal visitors ("superfans") generating a disproportionately low volume of ad revenue.

So, what can you do with this data? Matt decided it made sense to give his loyal fans an ad-free experience because they didn't click on ads anyway. Win-win: he got a higher click-through rate because all the pages served to his superfans didn't actually have any ads AND he was able to give potential superfans an incentive to opt for premium membership.

Not really a big deal, just an example of using common sense when you're crunching numbers.

  Posted by Pete Loshin on June 1, 2007 6:00 AM |

Comments

Another simple analytic tool that could be used in these kinds of cases is Benford's Law: another spin on a power law that dictates the frequency distribution of the first digit of values within certain numeric data sets. I suspect that correlating the number of visits to identifiable individuals would reflect this law. This could then be used to better predict which of the "noobs" might have a chance of converting to being members based on the number of times their searches led them to the site.

Posted by: David Loshin | June 3, 2007 8:27 PM

Post a comment