Scalable Massively Parallel Learning of Multiple Linear Regression Algorithm with MapReduce

Abstract

The large volumes of information emerging by the progress of technology and the growing individual needs of data mining, makes training of very large scale of data a challenging task. However, this information cannot be practically analyzed on a single machine due to the sheer size of the data to fit in memory. For this purpose, the process of such data requires the use of high-performance analytical systems running on distributed environments. To this end standard analytics algorithms need to be adapted to take advantage of cloud computing models which provide scalability and flexibility. This paper introduces a new distributed training method, which combines the widely used framework, MapReduce, for Multiple Linear Regression which will be based on the QR decomposition and the ordinary least squares method adapted to MapReduce. Our platform is deployed on Cloud Amazon EMR service. Experimental results demonstrate that our parallel version of the Multiple Linear Regression can efficiently handle very large datasets with different parameter settings (number, size and structure of machines).