Self learning expert - page 6

New comment
 

Self Optimizing Expert Advisors in MQL5 (Part 14): Viewing Data Transformations as Tuning Parameters of Our Feedback Controller

Self Optimizing Expert Advisors in MQL5 (Part 14): Viewing Data Transformations as Tuning Parameters of Our Feedback Controller

It is an important control knob in the pipeline that is often hidden away in the shadows of its bigger brothers. Commonly, optimizers or shiny model architectures mainly get the focus and research work, and large amounts of academia are poured into those directions. But little time is spent studying the effects of pre-processing techniques.

Silently, the pre-processing that we apply to the data at hand impacts model performance in ways that can be surprisingly large. Even small percentage improvements made in pre-processing can compound over time and materially affect the profitability and risk of our trading applications.

Self Optimizing Expert Advisors in MQL5 (Part 14): Viewing Data Transformations as Tuning Parameters of Our Feedback Controller
Self Optimizing Expert Advisors in MQL5 (Part 14): Viewing Data Transformations as Tuning Parameters of Our Feedback Controller
  • 2025.09.11
  • www.mql5.com
Preprocessing is a powerful yet quickly overlooked tuning parameter. It lives in the shadows of its bigger brothers: optimizers and shiny model architectures. Small percentage improvements here can have disproportionately large, compounding effects on profitability and risk. Too often, this largely unexplored science is boiled down to a simple routine, seen only as a means to an end, when in reality it is where signal can be directly amplified, or just as easily destroyed.
 

Self Optimizing Expert Advisors in MQL5 (Part 15): Linear System Identification

Self Optimizing Expert Advisors in MQL5 (Part 15): Linear System Identification

Trading systems are complex applications expected to operate in chaotic, dynamic environments — a challenge for even the most experienced developers. It’s nearly impossible to define every correct action a trading application should take, as market outcomes are virtually infinite. Maintaining control and ensuring consistent profitability under such uncertainty remains one of the greatest challenges in algorithmic trading.
Self Optimizing Expert Advisors in MQL5 (Part 15): Linear System Identification
Self Optimizing Expert Advisors in MQL5 (Part 15): Linear System Identification
  • 2025.10.15
  • www.mql5.com
Trading strategies may be challenging to improve because we often don’t fully understand what the strategy is doing wrong. In this discussion, we introduce linear system identification, a branch of control theory. Linear feedback systems can learn from data to identify a system’s errors and guide its behavior toward intended outcomes. While these methods may not provide fully interpretable explanations, they are far more valuable than having no control system at all. Let’s explore linear system identification and observe how it may help us as algorithmic traders to maintain control over our trading applications.
 

Self Optimizing Expert Advisors in MQL5 (Part 16): Supervised Linear System Identification

Self Optimizing Expert Advisors in MQL5 (Part 16): Supervised Linear System Identification

In our previous discussion on feedback controllers, we learned that these systems can stabilize the performance of trading strategies by first observing their behavior in action. We have provided a quick link to the previous discussion, here. This application design, allowed us to capture the dominant correlational structures that persisted across both winning and losing trades. In essence, feedback controllers helped our trading application learn how to behave optimally under current market conditions—much like human traders, who focus less on predicting the future and more on responding intelligently to the present.
Self Optimizing Expert Advisors in MQL5 (Part 16): Supervised Linear System Identification
Self Optimizing Expert Advisors in MQL5 (Part 16): Supervised Linear System Identification
  • 2025.10.31
  • www.mql5.com
Linear system identifcation may be coupled to learn to correct the error in a supervised learning algorithm. This allows us to build applications that depend on statistical modelling techniques without necessarily inheriting the fragility of the model's restrictive assumptions. Classical supervised learning algorithms have many needs that may be supplemented by pairing these models with a feedback controller that can correct the model to keep up with current market conditions.
123456
New comment