Scopus Indexed Publications

Paper Details

A Distributed Framework for Predictive Analytics Using Big Data and MapReduce Parallel Programming
, Dr. Shaikh Muhammad Allayear,

With the advancement of Internet technologies and the rapid increase of World Wide Web applications, there has been tremendous growth in the volume of digital data. This takes the digital world into a new era of big data. Various existing data processing technologies are not consistent and scalable in handling the complexity as well as the large-size datasets. Recently, there are many distributed data processing, and programming models have been proposed and implemented to handle big data applications. The open-source-implemented MapReduce programming model in Apache Hadoop is the foremost model for data exhaustive and also computational-intensive applications due to its inherent characteristics of scalability, fault tolerance, and simplicity. In this research article, a new approach for the prediction of target labels in big data applications is developed using a multiple linear regression algorithm and MapReduce programming model, named as MR-MLR. This approach promises optimum values for MAE, RMSE, and determination coefficient (R2) and thus shows its effectiveness in predictions in big data applications.

Not Available
Journal or Conference Name
Mathematical Problems in Engineering
Publication Year