Clustering and Regression Techniques for Stock Prediction. (2016)

• Record Type: Journal Article
• Authors: Bini, B.S.; Mathew, Tessy
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 1248
• Page End: 1255
• Publication Date: 2016
• Subjects: K-means -- EM -- Hierarchical -- Density based -- Model based -- Multiple regression; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.104
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: Stock market prices keep on varying day by day. It is very difficult to foresee the future value of the market by the sellers and buyers. In this paper, an analysis system which helps the people to identify the more profitable companies using data mining approaches is proposed. The clustering and regression are the two techniques of data mining used here, Validation index is used for analysing the performance of different clustering methods such as partitioning technique, hierarchical technique, model based technique and density based technique. Among the different clustering techniques experimented, partitioning technique and model based technique give high performance i.e.K-means and EM clustering algorithm respectively. For prediction of future stock price multiple regression technique is used which helps the buyers and sellers to choose their companies from stock.