金融时间序列指标判别框架：以特质波动率为例

摘要

This paper presents a new method--TBUD to partition the inflection points into col-lections for time series of the stock price.Analyzing the relation among the collections,this paper builds a discrimination framework which is applied to Idiosyncratic Volatility,as a case.The re-sult suggests that Idiosyncratic Volatility can not be divided the inflection points set and is there-fore unable to make an accurate prediction on the future trends of the stock price.%基于拐点集合判别的TBUD方法主要思路是分析拐点集合间的关系，并在高维空间进行划分，从而搭建判别模型，并将分析框架应用在特质波动率等若干指标上，利用实证数据得到结论。应用 TBUD判别框架可以发现，特质波动率等指标无法对拐点集合进行清晰划分，因而并不具有预测能力。