Introduction to feature selection (part 2)
September 28, 2007 by Sandro Saitta · 6 Comments
Filed under: dimensionality reduction, feature selection, search techniques, wrapper
This post continues the previous one about feature selection. I now give some examples of wrapper-based techniques for feature selection.In wrapper techniques, using the classification algorithm as a black box, any search strategy can be used in combination. This makes wrapper approaches universal. The accuracy of the classification algorithm may be used as the objective function of the search strategy. As with any classification algorithm, wrapper feature selection techniques… Continue reading... | 6 CommentsFiled under: dimensionality reduction, feature selection, search techniques, wrapper
Introduction to feature selection (part 1)
September 25, 2007 by Sandro Saitta · 1 Comment
Filed under: dimensionality reduction, embedded, feature selection, filter, wrapper
Feature selection is a technique used to reduce the number of features before applying a data mining algorithm. Irrelevant features may have negative effects on a prediction task. Moreover, the computational complexityof a classification algorithm may suffer from the curse of dimensionality caused by several features. When a data set has too many irrelevant variables and only a few examples, overfitting is likely to occur. In addition, data are… Continue reading... | 1 CommentFiled under: dimensionality reduction, embedded, feature selection, filter, wrapper
RSS Feed and email notification
September 21, 2007 by Sandro Saitta · Leave a Comment
Filed under: RSS feed, blog update, email notification
Hi there,As you may have noticed, you can now easily subscribe to the RSS Feed of Data Mining Research. This way, you don't need to check every time for new posts. Your news reader will automatically do the job for you. This subscription is valid for several news readers through the use of FeedBurner. You can also receive posts by email. I hope these two additional features help… Continue reading...Filed under: RSS feed, blog update, email notification
The future of data mining
September 20, 2007 by Sandro Saitta · Leave a Comment
Filed under: data mining challenges, data mining issues, data mining trends, future trends
People sometimes ask me what are future trends in data mining. This was by the way the topic of an older post. I recently read a paper on this topic by Kriegel et al. (1). As clearly stated in the paper title - Future trends in data mining - this work points out future directions in data mining. After basic definitions about data mining and knowledge discovery, authors… Continue reading...Filed under: data mining challenges, data mining issues, data mining trends, future trends
Data mining for predicting electricity consumption
September 14, 2007 by Sandro Saitta · 3 Comments
Filed under: data mining application, electricity consumption
Filed under: data mining application, electricity consumption
Since I'm close to finishing my PhD, I'm looking around to find a new job in data mining. Actually, this is a nice opportunity to discover possible application areas for data mining methods. Indeed, I was recently invited by Girsberger Informatik AG (Switzerland) for an interview. They have a small sized company that proposes to… Continue reading... | 3 CommentsSearch box on Data Mining Research
After a few days (weeks?) of tuning, the Google search box is now working. You can easily find posts and comments about specific topics. Simply enter your search query, e.g. cluster validity or data mining people and select the "dataminingblog.com" option. After clicking on the search button, you will be redirected on a page containing all related pages on DMR. I hope this improves the usability of this… Continue reading...Data Mining Research
Visitors
Networks
For 15% discount use pass: SSDC10
T-shirts, Mugs & Mousepads
