Abstract
Financial markets give a large number of trading opportunities. However, over-complicated systems make it very difficult to be effectively used by decision-makers. Volatility and noise present in the markets evoke a need to simplify the market picture derived for the decision-makers. Symbolic representation fits in this concept and greatly reduces data complexity. However, at the same time, some information from the market is lost. Our motivation is to answer the question: What is the impact of introducing different data representation on the overall amount of information derived for the decision-maker? We concentrate on the possibility of using entropy as a measure of the information gain/loss for the financial data, and as a basic form, we assume permutation entropy with later modifications. We investigate different symbolic representations and compare them with classical data representation in terms of entropy. The real-world data covering the time span of 10 years are used in the experiments. The results and the statistical verification show that extending the symbolic description of the time series does not affect the permutation entropy values.
Highlights
In the age of information, the main difficulty is not to obtain data, but rather to extract the most important and, at the same time, the non-redundant information
On the one hand, these parameters met the conditions for calculating permutation entropy (PE), and on the other hand, they corresponded to the periods of analysis of financial time series used by investors
We investigated what was the impact of the proposed symbolic time series representation on the entropy values
Summary
In the age of information, the main difficulty is not to obtain data, but rather to extract the most important and, at the same time, the non-redundant information. While the time needed to make a decision is shortened, more noise is observed This is especially visible in the case of very volatile instruments like cryptocurrencies or the foreign exchange market [3]. Every new proposition is tested on historical data with the assumption that the same modus operandi will work for the future. In opposition to this approach, our proposition is to measure the method with entropy to answer what is the gain/loss of information question compared to another one. As for every measure or indicator, we can calculate its own entropy; we can further compare different methods and indicators using its entropy to answer the question of which of them carries more or less amount of information about the primary system (an instrument on the market)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have