The Australian Census 2016 Controversy
I wax lyrical (with lots of links) about #CensusFail 2016 Read More
I wax lyrical (with lots of links) about #CensusFail 2016 Read More
Spare5 combines humans with machines to create an Intelligent Crowdsourcing Platform. Read More
Predicting the Hottest 100 for 2015 once again! Read More
Cloudera is a commercial bundle of Apache Hadoop and a few other related open source projects to create what Cloudera call an Enterprise Data Hub. Hadoop itself is a big collection of technologies that can work together, but in the same way that the Internet is a big collection of… Read More
The Tech Field Day site for Data Field Day 1 has my picture on it, so I guess it’s official: I’m going to Data Field Day 1 in San Francisco, from 13 to 15 May 2015. As this is the first Data Field Day, I’m not sure what to expect.… Read More
Today is the day for the Hottest 100 of 2014. Lots of eager listeners will be waiting to see if anything by Taylor Swift makes it into the countdown, including me. Sadly, work and other commitments have kept me away from the detailed statistics I’d have liked to run on… Read More
I leave the country for a few days, and look what happens! The whole country is up in arms (and down in legs) about whether or not a Taylor Swift song will get enough votes to be in the Hottest100 this year. As some of you may know, the past… Read More
Now that we have the official results, let’s take a look at how we did! All models are wrong, some are useful. Firstly, my model picked 85 songs as being in the top 100, so we missed 15. So did the Warmest 100 list. We got 4 exactly right, as… Read More
This is my last revised list for the Hottest 100. This list is generated using a more sophisticated method (yet again) after a discussion over Twitter I had with @chrisjrn about the kinds of bias there might be in the sample. I refined the list with three techniques. Firstly, I… Read More
I’ve done another couple of data matching runs, and I think I might have a more accurate one than the previous list. There are a couple of significant differences, which I think is due to the way the partial matching Nilsimsa hash works. Basically I’ve tuned the Nilsimsa hash cutoff… Read More