Crash forecasting in the Korean stock market based on the log-periodic structure and pattern recognition

Bonggyun Ko, Jae Wook Song and Woojin Chang

Physica A: Statistical Mechanics and its Applications, 2018, vol. 492, issue C, 308-323

Abstract: The aim of this research is to propose an alarm index to forecast the crash of the Korean financial market in extension to the idea of Johansen–Ledoit–Sornette model, which uses the log-periodic functions and pattern recognition algorithm. We discover that the crashes of the Korean financial market can be classified into domestic and global crises where each category requires different window length of fitted datasets. Therefore, we add the window length as a new parameter to enhance the performance of alarm index. Distinguishing the domestic and global crises separately, our alarm index demonstrates more robust forecasting than previous model by showing the error diagram and the results of trading performance.

Keywords: Log-periodicity; Price forecasting; Diffusion model; Pattern recognition; Non-linear time series; Financial market (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437117309664
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

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:eee:phsmap:v:492:y:2018:i:c:p:308-323

DOI: 10.1016/j.physa.2017.09.074

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().