Big data Predictive Analytics for Apache Spark using Machine Learning

Abstract

In today's digital world data is producing at a rapid speed and handling this massive diverse data become more challenging. The environment of big data is capable of handling data efficiently from data warehouses and in real-time. In Big data environment, Apache Spark is cluster-based, open-source computing technology explicitly designed for bulky data handling. Apache spark services are to perform composite Analytics through in-memory processing. This plays an active role in making meaningful exploration through machine learning and processes a large amount of data. Machine learning API is known as Mllib. It is highly prominent and efficient for big data platforms also offers excellent functionalities. In this paper, we have performed an experiment to look at the analytical qualities of Mllib in the apache spark environment. Likewise, we have highlighted the modern tendencies of Machine learning in big data studies and provides an understanding of upcoming work.