Абстрактный

Predictive Analysis Using Hadoop: A Survey

Shreyas Kudale, Advait Kulkarni, Asst. Prof. Leena A. Deshpande

Current buzzword in the IT industry is of Big Data. But what exactly is “Big data”? Any amount of data which becomes difficult to process by using traditional RDBMS can be referred to as Big Data. Data is being considered to be the future asset of today’s organizations. Organizations from the public and private sector are making a strategic decision to use this data generated to gain competitive advantage. The main hurdle is to process this huge data efficiently for analytics purpose. Analysis of such huge data to obtain information out of it by the traditional relational database model (RDBMS) is costly as well as inefficient. The use of Hadoop framework can be made for cost effective and faster data processing, which would enhance the prediction process. Through this paper, we suggest the use of Hadoop Framework and the ET- L process for Hadoop for performing predictions based on the datasets. Basic introduction on use of Apriori algorithm on Hadoop for data analysis is also presented.