Discussing the article: "Self Optimizing Expert Advisors in MQL5 (Part 10): Matrix Factorization"
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 Advisors in MQL5 (Part 10): Matrix Factorization.
Factorization is a mathematical process used to gain insights into the attributes of data. When we apply factorization to large sets of market data—organized in rows and columns—we can uncover patterns and characteristics of the market. Factorization is a powerful tool, and this article will show how you can use it within the MetaTrader 5 terminal, through the MQL5 API, to gain more profound insights into your market data.
Matrix factorization is a mathematical technique used to decompose a large matrix into a product of smaller, simpler matrices. These techniques come with many benefits. However, before exploring those, let’s first understand the motivation behind them.
In everyday life, certain shared experiences transcend cultures. For example, I believe most readers are familiar with the idea that by talking to a child and listening to how they describe their parent, we can get an idea of what that parent might be like. These descriptions may even help us guess how the parent would act in situations the child hasn’t directly described. Similarly, matrix factorization breaks down a large matrix into smaller ones—its “children.” These child matrices each describe different aspects of the original matrix, helping us understand its underlying structure. Just as a child’s perspective can reveal the essence of their parent, these smaller matrices can reveal in-depth insights about the market we’re analyzing.
The results of matrix factorization often provide numerically stable solutions to the linear models we introduced earlier. In this article, we’ll also introduce a numerical library called OpenBLAS—short for Basic Linear Algebra Subprograms. OpenBLAS is an open-source fork of the BLAS library, redesigned to run efficiently on today’s computational architectures. BLAS was originally written in Fortran and hand-written assembly code.
Author: Gamuchirai Zororo Ndawana