Stock Index Pattern Discovery via Toeplitz Inverse Covariance-based Clustering

Hongbing Ouyang, Xiaolu Wei () and Qiufeng Wu
Additional contact information
Hongbing Ouyang: School of Economics, Huazhong University of Science and Technology, Hubei Province, P.R. China
Xiaolu Wei: Corresponding author. Business School, Hubei University, Hubei Province, P.R. China.
Qiufeng Wu: School of Science, Northeast Agricultural University, Heilongjiang Province, P.R. China.

Journal for Economic Forecasting, 2020, issue 2, 58-72

Abstract: In this study, we attempt to discover repeated patterns of stock index through analysis of multivariate time series. Our motivation is based on the notion that financial planning guided by pattern discovery of stock index may be more effective. A two-stage architecture constructed by combining Toeplitz Inverse Covariance-Based Clustering (TICC) with betweenness centrality is applied for pattern discovery of stock index. In the first stage, TICC is used to discover repeated patterns of stock index’s multivariate time series. Then, in the second stage, betweenness centrality scores that reveal the relative “importance” of each influencing factor are plotted by Markov random field (MRF) which is derived from the first experiment. The Hangseng Stock Index and five influencing factors are used in the experiment. Empirical results show that six kinds of time-invariant patterns with flexible and long-term time periods are discovered in Hangseng Stock Index, and that different influencing factors have different betweenness scores in each cluster. This empirical research provides new ideas of stock index prediction and portfolio construction for scholars and investors. Moreover, the long-period repeated patterns that are discovered in this paper increase the possibility to reduce transaction cost for portfolio construction which then, maybe more applicable to the real financial markets.

Keywords: pattern discovery; Toeplitz Inverse Covariance-Based Clustering (TICC); multivariate time series; stock index; influencing factors; betweenness centrality scores (search for similar items in EconPapers)
JEL-codes: C38 C63 G17 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.ipe.ro/rjef/rjef2_20/rjef2_2020p58-72.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rjr:romjef:v::y:2020:i:2:p:58-72

Access Statistics for this article

Journal for Economic Forecasting is currently edited by Lucian Liviu Albu and Corina Saman

More articles in Journal for Economic Forecasting from Institute for Economic Forecasting Contact information at EDIRC.
Bibliographic data for series maintained by Corina Saman ( this e-mail address is bad, please contact ).