Wednesday, December 16, 2009

Meetup for Sydney Data Miners (11th February 2010)

Last month I attended a gathering of Sydney based data miners.

There are lots of parallels to IAPA (Institute of Analytics Professionals of Australia, but the audience seemed to be more hands-on analysts. Being based at Google it had quite a few web based analysts too.

The next meet-up is 11th February 2010. I'll be there having a chat and a few beers.


Anonymous said...

Hey Tim-

Can you share with us your educational background?

Tim Manns said...

Academic or educational? It is not necessarily the same thing :)

I studied a stats and biology focused psychology degree as an undergraduate. I got good grades, but had no intention of continuing life as a poverty stricken student.

Joined SPSS in 1999 shortly after they acquired ISL, developers of Clementine. My role was as a tech support specialist, so I had a lot of direct interaction with Clementine and by proxy many platforms, databases, and data mining problems.

After 5 years working along side the Clementine development team in UK I moved to Sydney, Australia and worked as an SPSS Data Mining consultant for a few years.

Whilst working on a project in a telecommunications company I got offered a permanent position as an data miner and accepted.

For the past 4 years I've been responsible for customer analysis such as building churn models etc.

In total I've 10+ years using SPSS tools (mostly Clementine) and several working on practical data mining projects in industry.

Does that answer your question?



Anonymous said...

What does a typical work day or week look like for a data miner? Is there lot of programming involved?

Tim Manns said...

I would say these days many business analysts dont write much code. It depends what you consider as programming. Nearly all software vendors provide advanced User Interfaces that allow the user to 'point and click' and behind the scenes code will be writen automatically.

Some analysts still perfer to qrite code, and for example in some cases you may be working on something that requires loops or steps that are dynamic. In those cases programming is often the best (or only) option.

Anyhow, the code for analytics is often much easier than you'd expect. SQL for example is often used and isn't that tricky to learn.