Hosting for just $3.88/month! Find out MORE!

Data Mining: Understanding Alexa Reach Stats

Data Mining: Understanding Alexa Reach Stats

Monitor your website with is a free web monitoring service that has an excellent user interface and charting capability. And did I mention it is free!

Not only does it monitor you website to see if it is up and running, it provides a set of tools for web traffic analysis and resource utilization.

All the data are presented in nicely formated charts that looks really great.

An excellent tool to analyse your server uptime, traffic and server load.

Google Analytic is open

It has been close to 10 months since Google Analytics was released on an invite only basis.

Now it is open and you can sign up immediately. No need to wait for invitation email.

So, don’t wait. Go over to Google Analytics, sign up for a free account and start gaining insights on your web visitors.

Making sense of Adsense click through rate

I have neglected this blog for a while because I not could come up with solid content to fill it. Doing analytics is inherently time consuming, my plan is to post at least 1 to 2 analysis a month. The analysis will be based on what I am doing online and my own blogs.

In this article I want to look at Adsense click through rate (CTR) and how you can use this insight to change your ad layout and improve conversion.

Take a look at this report for August todate. The channels, all belonging to the same site, had been masked (We don’t really need that for this discussion anyway).

Adsense CTR

Continue reading ‘Making sense of Adsense click through rate’

AOL releases search queries of users

AOL released their user’s search data over a period of 3 months (01 March to 31 May 2006) [via SEO Portal (thanks for the tip off!)]

Tech Crunch called this release a screw up and staggering utter stupidity.

The original intention of the data was to be for the purpose of personalization, query reformulation and search research.

However the amount of personal information that can be gathered from the data is staggering. As some have discovered.

AOL search frequency data

The compress archive is 439Mb and expands to more than 2Gb.


  • 36,389,567 lines of data
  • 21,011,340 instances of new queries (w/ or w/o click-through)
  • 7,887,022 requests for “next page” of results
  • 19,442,629 user click-through events
  • 16,946,938 queries w/o user click-through
  • 10,154,742 unique (normalized) queries
  • 657,426 unique user ID’s

Imagine the kind of analysis and data mining can one do on this data!

On a related note, what tools can one use to analyse such data?