Aiming at two pivotal difficulties involved by similarity data mining in time series, namely effective mining of time series data with arbitrary length and that have biggish stochastic volatility, an algorithm of similarity mining in time series data on the basis of grey Markov SCGM(1, 1) model is proposed in this paper. Grey SCGM(1, 1) model is applied to seek for available information from time series data themselves, and then general change trend has been researched. Markov chain is applied to reveal stochastic volatility regularity and entropy is applied to measure similarity degree of time series. So applicable data scope of similarity mining in time series data is extended and efficiency of data mining is improved.
展开▼
