Articles on machine learning in trading

In the latest installment of this series, we move beyond individual machine learning techniques to address the "Research Chaos" that plagues many quantitative traders. This article focuses on the transition from ad-hoc notebook experiments to a principled, production-grade pipeline that ensures reproducibility, traceability, and efficiency.

Since these articles are educational in nature and are not intended to show the implementation of specific functionality, we will do things a little differently in this article. Instead of showing how to apply factorization to obtain the inverse of a matrix, we will focus on factorization of the pseudoinverse. The reason is that there is no point in showing how to get the general coefficient if we can do it in a special way. Even better, the reader can gain a deeper understanding of why things happen the way they do. So, let's now figure out why hardware is replacing software over time.

In the article, an attempt is made to build a trading EA for predicting exchange rate quotes. The algorithm is based on classical classification models - logistic and probit regression. The likelihood ratio criterion is used as a filter for trading signals.

Self-supervised learning is a powerful paradigm of statistical learning that searches for supervisory signals generated from the observations themselves. This approach reframes challenging unsupervised learning problems into more familiar supervised ones. This technology has overlooked applications for our objective as a community of algorithmic traders. Our discussion, therefore, aims to give the reader an approachable bridge into the open research area of self-supervised learning and offers practical applications that provide robust and reliable statistical models of financial markets without overfitting to small datasets.

Machine Learning is a complex and rewarding field for anyone of any experience. In this article we dive deep into the inner mechanisms powering the models you build, we explore the intricate world of features,predictions and impactful decisions unravelling the complexities and gaining a firm grasp of model interpretation. Learn the art of navigating tradeoffs , enhancing predictions, ranking feature importance all while ensuring robust decision making. This essential read helps you clock more performance from your machine learning models and extract more value for employing machine learning methodologies.

We invite you to get acquainted with the Hierarchical Double-Tower Transformer (Hidformer) framework, which was developed for time series forecasting and data analysis. The framework authors proposed several improvements to the Transformer architecture, which resulted in increased forecast accuracy and reduced computational resource consumption.

Spurious regressions occur when two time series exhibit a high degree of correlation purely by chance, leading to misleading results in regression analysis. In such cases, even though variables may appear to be related, the correlation is coincidental and the model may be unreliable.

This article, the final in our series to tackle functors as a subject, revisits monoids as a category. Monoids which we have already introduced in these series are used here to aid in position sizing, together with multi-layer perceptrons.

In this article, we will get acquainted with the Anarchic Society Optimization (ASO) algorithm and discuss how an algorithm based on the irrational and adventurous behavior of participants in an anarchic society (an anomalous system of social interaction free from centralized power and various kinds of hierarchies) is able to explore the solution space and avoid the traps of local optimum. The article presents a unified ASO structure applicable to both continuous and discrete problems.