Discussing the article: "Self Optimizing Expert Advisor With MQL5 And Python (Part V): Deep Markov Models"
Thanks for your efforts , It is helpful to have the video as well . please note your link to the previous article comes up with a 404 for me
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Self Optimizing Expert Advisor With MQL5 And Python (Part V): Deep Markov Models.
In this discussion, we will apply a simple Markov Chain on an RSI Indicator, to observe how price behaves after the indicator passes through key levels. We concluded that the strongest buy and sell signals on the NZDJPY pair are generated when the RSI is in the 11-20 range and 71-80 range, respectively. We will demonstrate how you can manipulate your data, to create optimal trading strategies that are learned directly from the data you have. Furthermore, we will demonstrate how to train a deep neural network to learn to use the transition matrix optimally.
The RSI is widely used by technical analysts to identify extreme price levels. Typically, market prices tend to revert to their averages. Therefore, whenever price analysts find a security hovering in extreme RSI levels, they would normally bet against the dominant trend. This strategy has been slightly altered into many different versions, that all stem from one source. The shortcoming of this strategy is that, what may be considered a strong RSI level in one market, is not necessarily a strong RSI level for all markets.
To illustrate this point, Fig 1 below shows us how the standard deviation of the RSI value evolves on 2 different markets. The Blue line represents the average standard deviation of the RSI in XPDUSD market, while the Orange line represents the NZDJPY market. It is widely known, by all seasoned traders, that the precious metals market is significantly volatile. Therefore, we can see a clear disparity between the changes in RSI levels between the two markets. What may be considered a high reading for the RSI on a currency pair, such as the NZDUSD pair, may be considered ordinary market noise when trading a more volatile instrument, such as the XPDUSD.
It soon becomes apparent that each market could have its own unique level of interest on the RSI indicator. In other words, when we are using the RSI indicator, the optimal level to enter a trade depends on the symbol being traded. Therefore, how can we algorithmically learn on which RSI level should we buy or sell? We can employ our transition matrix to answer this question for any symbol we have in mind.
Author: Gamuchirai Zororo Ndawana