International win for clever dataminer
university-of-waikato
Mon Aug 17 2009 12:00:00 GMT+1200 (New Zealand Standard Time)
International win for clever dataminer
Monday, 17 August 2009, 1:28 pm
Press Release: University of Waikato
Media Release
August 17, 2009
International win for clever dataminer
If you’ve ever wondered why certain types of junk mail make a beeline for your letterbox, it’s all because of clever datamining. Datamining pulls out useful and pertinent information from a whole mass of information, and from it can make predictions about patterns of behaviour – so if you’re getting junk mail about tropical holidays or power tools, it’s because the model has put you in the top 10% of most likely consumers.
A Waikato Masters student in computer science and former web developer, Quan Sun, is certainly a clever dataminer; he’s just won first place in an international competition using the award-winning Weka datamining software developed at the University of Waikato.
Quan was placed first in the ‘hard’, graduate/post-doctoral section of the annual University of California San Diego Student Datamining Competition, which attracted more than 300 entries from top universities in North America, Europe, Asia and Australasia.
The competition was in four sections – with ‘easy’ and ‘hard’ options for both undergraduate and graduate/post-doc students. All competitors were set the task of predicting anomalies in some e-commerce transaction data.
Quan says figuring out the answer took him about a month, working on the data for two to four hours a day and brainstorming ideas with his wife, who’s a PhD student in engineering at Waikato.
“I couldn’t have done it without Weka,” he says. “Weka is like the Microsoft Word of datamining, and at least half of the competitors used it in their entries.”
Advertisement - scroll to continue reading
In 2005, Weka software won the Data Mining and Knowledge Discovery Service Award from the Association for Computing Machinery’s Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD). The open-source software has been downloaded by more than one and a half million users worldwide.
Quan's MSc supervisor, Associate Professor Eibe Frank, says the win provides yet more evidence that the University of Waikato's Computer Science Department is a good destination for students. "Quan's success demonstrates the benefits of studying at a department that produces internationally competitive open-source software such as Weka. Here at Waikato we not only write widely-used software; we also teach our students to become expert practitioners."
Quan, who also did his first degree at Waikato, says his previous work as a web developer has given him good attention to detail, which is essential for datamining. He’s planning to continue on to doctoral study when he completes his Masters degree later this year.
ends
Advertisement - scroll to continue reading
a.supporter:hover {background:#EC4438!important;} @media screen and (max-width: 480px) { #byline-block div.byline-block {padding-right:16px;}}
Using Scoop for work?
Scoop is free for personal use, but you’ll need a licence for work use. This is part of our Ethical Paywall and how we fund Scoop. Join today with plans starting from less than $3 per week, plus gain access to exclusive Pro features.
Join Pro Individual Find out more
Find more from University of Waikato on InfoPages.