Discussing the article: "Neural Networks in Trading: Robust Trading Signals in Any Market Regime (ST-Expert)"

[MetaQuotes]

Check out the new article: Neural Networks in Trading: Robust Trading Signals in Any Market Regime (ST-Expert).

In this article, we will explore the ST-Expert framework, which ensures the robustness of forecasts under market uncertainty by taking local and global dependencies in time series into account. Its flexible architecture promotes model adaptability and improves the accuracy of predictions.

We are used to thinking in terms of correlations. There is a stable relationship between the price of oil and the Canadian dollar exchange rate, between the Fed's interest rates and the technology sector, and between demand for gold and movements in the dollar. But as soon as external conditions change, these dependencies collapse. During the COVID-19 market crash of 2020, the usual correlations between stocks, bonds, and commodities ceased to reflect reality in a matter of weeks. Even milder regime shifts, such as cycles of Fed rate hikes and cuts, can drastically alter correlations and undermine models that once seemed reliable.

The crux of the problem is that modern algorithms are trained on relatively short and homogeneous data intervals. Under these laboratory conditions, they achieve impressive results, capturing subtle interrelationships between assets. But as soon as the market moves beyond its usual distribution, the accuracy of forecasts drops sharply. Essentially, the models perform very well during calm periods, but they are unable to cope with market phase transitions.

This situation is in many ways similar to urban transportation networks; using them as an example, the authors of the paper "Robust Traffic Forecasting against Spatial Shift over Years" proposed a new framework called ST-Expert. As long as the city remains unchanged, traffic forecasts work very well. But as soon as a new interchange is built or a large shopping center opens, the old routes become obsolete. In the financial environment, these drivers are regulatory decisions, sanctions, geopolitical conflicts, or the emergence of new technologies. The map of interconnections changes, and older models become ineffective.

To tackle this challenge, the authors of ST-Expert propose an original solution based on the Mixture of Experts approach. Its key idea is that the model learns not from a single rigid structure of dependencies, but from a set of graph generators known as graphons. Each of them reflects a specific type of market behavior. One identifies patterns under a sustained trend, another describes a phase of high volatility, and a third detects local correlations within industry sectors. When the market changes, the system does not break down; instead, it adaptively combines previously learned scenarios, creating new connections between instruments and maintaining forecast accuracy.

Author: Dmitriy Gizlyk