Survey: Integrated use of Data Mining on Cloud Computing

摘要

Cloud computing is a method of computing where data is managed, stored as well as processed on a remote network of remote servers but can be accessed on personal computers instantly on demand. On the other hand data mining is used for extracting useful information from raw data. Various data -mining techniques are being used in our day- to- day activities nowadays. Data mining techniques help businesses to find their targeted customers. This paper emphasizes on integrated use of data mining techniques on cloud storage areas such as open source software Hadoop and MapReduce framework on which Hadoop is implemented, along with Apache Mahout which is Java machine learning library and a data mining framework used to manage big data. Nowadays various Mahout Machine learning algorithms are implemented for the Collaborative filtering, Clustering, Classification and Frequent item- set mining of the exponential amount of data around us. The combined use of data mining and cloud computing will be time reducing, highly reliable, high availability, cost effective and easy to manage.