Parallel balanced team formation clustering based on mapreduce

For effective cooperative learning grouping student is important. Grouping students can be generalized to the problem that clustering objects into some clusters from a computer science point of view. The large datasets, expensive task of clustering computationally and high dimensionality makes clustering of very large scale of data a challenging task. To effectively process very large datasets for clustering, parallel and distributed architectures have developed. MapReduce is a programming model that is used for handling large volumes of data over a distributed computing environment in parallel. In this paper, we present a Parallel Balanced Team Formation (PBTF) clustering algorithm for the MapReduce framework. The purpose of PBTF is to find partitions with high homogeneity in a group and high heterogeneity between groups in parallel.