基于MS-GARCH模型的时间序列聚类

Time Series Clustering with MS-GARCH Mixtures

聚类是时间序列数据挖掘的重要任务之一。本文基于有限混合MS-GARCH模型,提出一种时间序列聚类方法。利用贝叶斯马尔科夫链蒙特卡洛模拟方法,克服路径依赖的困难,给出了模型参数的估计。最后,选取23家中国上市公司股票数据进行实证分析,验证了所提方法的有效性。

Clustering is one of the important tasks of time series data mining. In this paper, we propose a novel time series clustering method based on the finite mixture MS-GARCH model. By using Bayesian Markov chain Monte Carlo simulation methods to overcome the difficulty of full path dependence, we estimate the model parameters. Finally, the empirical analysis of stock data of 23 Chinese listed companies verifies the effectiveness of our proposed method.