Research of Outliers in Time Series of Stock Prices Based on D-nearest Neighbor Clustering

Abstract

How to detect the outlier of stock prices effectively has become an intense concern of scholars in many fields. In this paper, the thoughts of short-term trend clustering are introduced for researching the outliers in time series with cluster analysis. A method detecting the outlier of time series of stock prices based on d-nearest neighbor clustering is proposed. Study on the outlier of time series in stock market is dealt with in two stages. In the first stage, the breaking points where the short-term trend changes are used to be observing points. And then, clustering the short-term trend. In the second stage, the d-nearest neighbor clustering method is introduced to detect the outliers. Empirical study, based on the historical data of Shanghai stock exchange and Shenzhen stock exchange, proved that the method is feasible and effective.