Clustering and classification of time series using topological data analysis with applications to finance

作者：

Highlights：

• New methods for time series clustering (SOM-TDA) and classification (RF-TDA).

• RF-TDA outperforms other methods on the classification task.

• Dependence of stock price movements on sectors in NSE is revealed using RF-TDA.

摘要

•New methods for time series clustering (SOM-TDA) and classification (RF-TDA).•RF-TDA outperforms other methods on the classification task.•Dependence of stock price movements on sectors in NSE is revealed using RF-TDA.

论文关键词：Persistent homology,Time delay embedding,Takens theorem,Random forest,Self organizing maps

论文评审过程：Received 20 March 2020, Revised 12 July 2020, Accepted 7 August 2020, Available online 15 August 2020, Version of Record 10 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113868