Modified Clustering based Outlier Detection Algorithm for Market Data Analysis Kalimuthu M.*, Dr. Sengottuvelan P.**, Dr. Karthik S.** *Department of Information Technology, Department of Computer Science and Engineering, SNS College of Technology, Coimbatore, Tamil Nadu, India **Department of Computer Science, Periyar University, Dharmapuri, Tamil Nadu, India Online published on 2 August, 2016. Abstract Data Mining is defined as the process of extracting information from huge sets of data. An outlier is a data entity which is considerably different from the remaining data. Clustering plays important role to find outlier detection in financial market data. The outlier discovery problem is sometimes difficult like classification process. Outliers are noisy objects; it may be affect the result more significantly because they are more different from the data points. Outlier regularly contains positive information about unusual distinctiveness of the systems and entities, which impact the data generation process. In this paper, we proposed new techniques Heuristics K-means filtering for outlier detection which finds the outliers by studying the behavior of projections from the data set. The proposed idea is in the direction to improve the clustering algorithms, to use the same procedure and functionality to solve both clustering and outlier discovery. Top Keywords Outlier detection, clustering, K-means, High dimensional, Market data. Top |