SPRINT: A Sclable Parallel Classifier for Data Mining












Jonh Shafer
Rakesh Agarwal
Manish Mehta
March 11, 1999

Abstract :

Classification is an important data mining problem. Most of the current classification algorithms require that all or portion of the entire dataset remain permanently in memory. This limits their suitability for mining over large database. In this paper, a new decision-tree based classification algorithm (SPRINT) is presented that removes all memory restrictions and is fast and scalable. The algorithm has also been designed to be easily parallelized to enhance scalability and speedup.