An Implementations of Clustering Technique in Data Mining to Analyse Big Data in Finance

Abstract

This research work is proposed to manage Big Data in Finance using Clustering and optimization mechanism. There are different knowledge discovery techniques, applications and process models that are applicable to deal with big data. There are several researches related to Big Data in Finance. A review of existing researches is stated here. Different researches are proposed research considering K-different clustering mechanism. These algorithms have been applied to various real-life applications running in serial, parallel, and high-performing computing environments. But these researches and traditional data mining techniques have their own limitations. The aim of researches is to judge the efficiency of different data mining algorithms on dataset and determine the optimum clustering algorithm. The performance analysis depends on many factors encompassing test mode, distance function and parameters. There are several researches which used K-MEAN clustering and optimization mechanism. The issues related to Kmean clustering would be resolved in this research. Research has introduced the more effective cluster mechanism to classify the data set. Therefore it is essential to propose a data mining technique to deal with big data in Finance. This research work would be helpful to known about data mining of big data. Data related to Equity and Mutual fund is considered in proposed model. After getting data, it is classified in to different clusters. Same data is stored in a cluster. Each cluster has different type of data set but the data within a cluster have similarly. There are different factors such as face value, market cap, promoters holding , fi holding, domestic holding, 52 week low, 52 week high , dividend, P/E are considered to analyze the better result in future. Using this proposed module, it will be possible to determine the shares or funds that will provide more profit.