Discussing the article: "Reimagining Classic Strategies (Part IX): Multiple Time Frame Analysis (II)"
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: Reimagining Classic Strategies (Part IX): Multiple Time Frame Analysis (II).
In today's discussion, we examine the strategy of multiple time-frame analysis to learn on which time frame our AI model performs best. Our analysis leads us to conclude that the Monthly and Hourly time-frames produce models with relatively low error rates on the EURUSD pair. We used this to our advantage and created a trading algorithm that makes AI predictions on the Monthly time frame, and executes its trades on the Hourly time frame.
For our test to be fair, we had to fetch the same amount of data from each time-frame. The limiting factor in this step was the number of bars available on the Monthly time-frame. Just 400 bars of monthly data is composed of roughly 33 years. There are only a handful of markets that old, which may bias our understanding of the best time-frame across all possible markets. However for the scope of our discussion, the EURUSD pair has rich data sets we can rely on.
We fetched 400 rows of monthly price quotes from the MetaTrader 5 terminal. We then fetched 400 corresponding rows of the future value of the EURUSD pair. This 2-step process was repeated over the remaining 10 time-frames. For this analysis, I selected:
I must admit, I was expecting to observe strong correlation levels, especially between time-frames that are periodically close to each other. However, there were only moderate levels of correlation shared across the sample. The only interesting correlation pairs that may deserve further analysis were:
Author: Gamuchirai Zororo Ndawana