Data Mining, Down Under » Industry

Reducing Churn Through Social Network Analysis

Shane Butler — Tue, 23 Feb 2010 09:33:16 +0000

Earlier in the month local data miner Tim Manns presented at the Sydney Data Miners group. Tim spoke on some work been doing at Optus around using mobile call patterns to establish social networks and using these networks to reduce customer churn. Interestingly, there are also applications in many other areas, including data cleansing, for example, where one person has purchased two mobile phones and given one to their spouse or child. Using this analysis we can try to determine which account is likely to be the actual account holder and infer the details (such as age) of the other customer.

For a full write up of Tim’s work, check out James Taylor’s PAW 2009 summary or head over to Tim’s data mining blog.

AusDM 09 & Analytic Challenge

Shane Butler — Tue, 07 Jul 2009 13:47:52 +0000

Australian Data Mining conference (AusDM09) will be held in Melbourne next December and Dr Phil Brierley of Tiberius Data Mining has put out the call for proposals for an analytic challenge to accompany the conference. Competitions are quite popular in data mining circles and provide a good training ground for new practitioners to get access to real data and solve real problems. They also often have surprising results, such as the team who used laptop with 2GB RAM to beat IBM’s mighty clusters.

For businesses, this is a great opportunity to find out what is available by having others suggest new ideas and methods, or even to test your internally deployed models against the best of the best. So if you’re a business who has data, please consider being invloved! For further details, see the competition webpage.

PMML 4.0 Released

Shane Butler — Thu, 18 Jun 2009 09:50:37 +0000

The DMG has released a new version of the PMML open format for representing predictive models. The new version includes support for ensembles, new model types and more built in functions to name just a few of the enhancements. For a detailed summary, see the Zementis blog.

SAS Forum (Australia) presentations available online

Shane Butler — Mon, 29 Sep 2008 23:30:52 +0000

The SAS Forum (Australia) was held in Sydney back in August. I was unable to attend but luckily the presentations have been put online. Here are some that I found interesting:

Make Sure Your Insight is Insightful: Analytical Marketing at NAB by Antony Ugoni (National Australia Bank)
Model Deployment and Management – The ATO Story by Warwick Graco (Australian Taxation Office)
Putting Cheques in Place to Identify Fraud by Dr Paul Bracewell (Offlode NZ) and Flavio Palaci (Marsh Australia)
Customer Value Creation Using Analytics by Arun VS (Satyam)
Analysing Performance and Tuning your SAS Application by Bill Gibson (SAS)

Data Mining the Financial Markets

Shane Butler — Fri, 25 Apr 2008 06:32:10 +0000

Thomas A. Rathburn has written a series of three articles on data mining the financial markets. Rathburn takes a detailed look into the success and failures of his efforts in the markets and with 10 year US bonds in particular. You can check it out here part 1, part 2, and part 3. The articles are also available as a podcast here: 1, 2, 3.

[via KDnuggets]

Experian Bolsters Data With Hitwise Acqusition

Shane Butler — Fri, 04 May 2007 07:06:23 +0000

Tim O’Reilly points to the news that Experian has made a significant move to improve the quality of their online and demographic data with the acqusition of Hitwise for US$240 Million. Hitwise collects user traffic from ISPs in several countries including Australia and uses that information to provide companies with insight into their online marketshare. Although not mentioned in the press release, the Hitwise data will likely be a huge boon for Experian’s marketing services, and will probably allow them to develop more accurate geo-demographic profiles.

Article: HCF gets a helping hand from predictive analytics

Shane Butler — Tue, 13 Jun 2006 03:43:59 +0000

From the ComputerWorld article:

Private health insurer HCF has implemented a predictive analytics suite to help weed out fraudulent claims, target individual members and streamline the monotonous labour of data analysis.

Future of Radio

Shane Butler — Tue, 28 Mar 2006 23:37:50 +0000

You may have listened to Internet radio before, but Pandora is a station of a different kind – totally personalised. Its a Flash based player that sits inside your browser, so no problems with firewalls. But the real innovation is that when you start it up, you tell it the artists you like, and it will attempt to determine what other songs you will like too, and play those to your personal audio stream. As time progresses you can give each song played the thumbs-up or thumbs-down which will further refine what music is played to you!! Its not bad, but they should some more advanced techniques like MusicMiner to better adapt to user tastes.

MusicMiner uses a Self-Organising Maps based technique (“Emergent SOM“) to determine and visualise music similarity:

The major advantage of MusicMiner is obviously you can use it on your own music collection and choose to play a particular song, whereas Pandora you can only define your interests and listen to see what is played. There is no guarantee Pandora will actually play that artist although usually it will eventually.

Revenue Science Gets $25 Mil. in Funding

Shane Butler — Thu, 23 Feb 2006 00:37:03 +0000

Looks like I missed this one back in December, but Revenue Science (formerly digiMine) has gained an additional USD$25 Million in VC funding. This brings total funding to $70 Million. digiMine was co-founded in 2000 by Usama Fayyad. Later the the consulting arm was spun off as the DMX Group and the company renamed to Revenue Science. I guess given Usama Fayyad now works as CDO for Yahoo its no surprise Revenue Science is working with Yahoo on building a new behaviour-based online advertising network.

e-Valuation: Find the value without the valuation?

Shane Butler — Tue, 14 Feb 2006 00:28:56 +0000

A new service has just launched in the U.S. that allows people to quickly and easily get a estimate of the value of any house in the country. Taking in moutains of data the website predicts the value based on tax record and historical data. While not a official valuation, it is a free service and will no doubt be useful to many home owners. I was amazed when I was able to zoom down to a house and see its value and the value of those surrounding it. Then by clicking you get detailed price estimate and associated accuracy as well as other information, like how many bedrooms the property has.

According to this report, Zillow has received USD $32 Million in venture capital funding. Not bad at all! It just goes to show that machine learning and data mining are going to be more and more important in the future. For further reading see John Cook’s blog for a good commentary on Zillow and it’s recent VC success.