Pervasive

The process of stellar discovery has long made its home at High Performance Computing (HPC) systems. HPC systems have evolved into clusters of "fat" multicore nodes. Applications must take advantage of parallelism across nodes and at the node level to maximize scalability and performance/watt. The complexity of multicore programming ...

  Fraud Detection and “Finding a needle in a haystack” Benford’s law has been promoted as providing auditors with an automated tool that is simple and effective for fraud detection.  The law of anomalous numbers was published in 1938 by Frank Benford [1].  Benford noticed that if a number is chosen at random from a large ...

The DataRush team just returned from attending the HIMSS 2010 conference in Atlanta (March 1-4th).   HIMSS is traditionally a large conference. As massive as the Atlanta convention center is, this year once again HIMSS filled the venues. Total attendance on March 2nd was recorded at 27,451 with 13,530 as exhibitors. This years’ theme was ...

Digital video has become the face of television, the internet and mobile devices.  According to an official blog post (May 2009), about 20 hours of video are introduced to the YouTube site every minute of real time.  This is equivalent to Hollywood releasing over 114,000 new full-length movies into the theaters each week! But digital ...

  Watch Video Lecture on Pervasive Parallelism in Data Mining, click here  UT Austin presents at PAW on using DataRush parallelism for fast and accurate prediction of customer behavior: 4:55pm-5:40pm Track 2: Telecommunications Room: Walnut A&B KDDcup 2009 Competition Results: Orange Labs (France Telecom) Churn, Baby, Churn: ...

We recently published a recommender system built on collaborative filtering principles. While collaborative filtering proved effective in predicting ratings of movies by users based on historical community movie ratings, we would like to consider a content-based filtering approach to enhance the accuracy of the recommendations.  This blog ...

Data Mining and the knowledge discovery process seeks to find patterns in data.  A common approach to pattern recognition is clustering.  In recently published work (KDD2009), a dataflow implementation of kmeans and later two dimensional kmeans (co-clustering) identified like-minded customer rental patterns of Netflix movies.  But ...

The Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’09) in Paris, France was last week. The annual ACM SIGKDD conference is the premier international forum for data mining researchers and practitioners from academia, industry, and government to share their ideas, research results and experiences. ...