An introduction to econophysics: correlations and complexity in finance
An introduction to econophysics: correlations and complexity in finance
Hi-index | 0.00 |
We propose a system to select the best combination of technical indicators and their parameter values adaptively by learning the patterns from the tick-wise financial data. In this paper, we show that this system gives good predictions on the directions of motion with the hitting rate at 10 ticks ahead of the decision point as high as 70% for foreign exchange rates (FX) in five years from 1996 to 2000 and 8 different stock prices in NYSE market in 1993. Based on this fact, we conclude that the tick-wise price time series carry a long memory of the order of at least a few minutes, which is equivalent to 10 ticks.