Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
7376564 | Physica A: Statistical Mechanics and its Applications | 2018 | 40 Pages |
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
Related Topics
Physical Sciences and Engineering
Mathematics
Mathematical Physics
Authors
Bonggyun Ko, Jae Wook Song, Woojin Chang,