Discussing the article: "Category Theory in MQL5 (Part 16): Functors with Multi-Layer Perceptrons"
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: Category Theory in MQL5 (Part 16): Functors with Multi-Layer Perceptrons.
This article, the 16th in our series, continues with a look at Functors and how they can be implemented using artificial neural networks. We depart from our approach so far in the series, that has involved forecasting volatility and try to implement a custom signal class for setting position entry and exit signals.
For this article though, we are more interested in the S&P 500 not just for its volatility as was the case in the last article(s), but its trends. We are looking to make forecasts on its short-term (monthly) trends and using those projections to open positions in our expert advisor. This means we will be dealing with the Expert Signal class and not the Expert Trailing class as has been the case so far in the series. So, implementing functor-based transformations on the graph of economic calendar data will result in the projected change in the S&P 500. This implementation will be achieved with the help of a multi-layer perceptron.
We did have a schematic representation of our simple hypothesis in the last article that links the four economic data points under consideration, however it was overly simplified and did not show it as a time series graph. The diagram below tries to achieve this:
Author: Stephen Njuki