Discussing the article: "Reimagining Classic Strategies (Part 14): High Probability Setups"
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 14): High Probability Setups.
High probability Setups are well known in our trading community, but regrettably they are not well-defined. In this article, we will aim to find an empirical and algorithmic way of defining exactly what is a high probability setup, identifying and exploiting them. By using Gradient Boosting Trees, we demonstrated how the reader can improve the performance of an arbitrary trading strategy and better communicate the exact job to be done to our computer in a more meaningful and explicit manner.
It is widely accepted, by most members of our community, that traders should actively seek to trade high probability setups. However, there are few formal definitions of what exactly constitutes a high probability trading setup. How do we empirically measure the probability associated with any particular trading setup? Depending on who you ask, you will get different definitions of how you can identify such opportunities and take advantage of them responsibly.
This article seeks to address these issues by proposing an algorithmic framework that allows us to depart from old definitions, and lean towards numerical definitions that are evidence based, so that our trading strategies may be able to identify and trade them profitably, all by themselves in a consistent manner.
We desire to model the relationship between our particular trading strategy and any Symbol we have chosen to trade. We can achieve this by first fetching market data that fully describes the market, and all the parameters that make up our trading strategy, all from the MetaTrader 5 terminal.
Afterward, we will fit a statistical model to classify if the strategy is going to produce signals that are profitable, or if the signal being generated by our strategy is most likely going to be unprofitable.
The probability estimated by our model, becomes the probabilities we associate with that particular signal. Hence, we can now start talking about "high probability setups" in a more scientific and empirical way, that is reasoned from evidence and relevent market data.
This framework essentially allows us to write trading strategies that are "goal aware", and explicitly instructed to only take actions they expect to be favorable. We are beginning to formalize the necessary components needed to write algorithmic trading strategies, that try to estimate, the the most probable consequences of their actions. This can be correctly conceptualised as reinforcement learning ideologies, being approached in a supervised fashion.
Author: Gamuchirai Zororo Ndawana