Discussing the article: "Neural Networks in Trading: Adaptive Periodic Segmentation (LightGTS)"

[MetaQuotes]

Check out the new article: Neural Networks in Trading: Adaptive Periodic Segmentation (LightGTS).

We invite you to learn about the innovative technique of adaptive patching — a method for flexibly segmenting time series while taking their internal periodicity into account. We will also look at an efficient encoding technique that preserves important semantic characteristics when working with data at different scales. These methods open up new possibilities for the accurate processing of complex, multiscale data characteristic of financial markets and significantly improve the stability and reliability of forecasts.

What makes time series unique is their rhythm. Unlike in text, where a token is a word, scale and periodicity are important here. Some data arrive once an hour, while others arrive every 15 minutes. Some show daily or weekly seasonality, while others show quarterly or annual seasonality. All of this affects what is known as the internal period — a recurring pattern in the data that is critical for high-quality forecasting. Moreover, when the scale changes, the cycle length changes as well — and if the model cannot handle this, its generalization ability drops sharply.

The problem is that most existing models use fixed tokenization. They simply divide the data into segments of equal length, without taking into account the scale or structure of the periods. As a result, some tokens are overloaded with data, while others are almost empty. Information becomes blurred, and recurring patterns are disrupted. This is particularly noticeable when a model trained at one scale is applied to data at another scale — the accuracy of the predictions drops, the number of parameters must be increased, and, as a result, the time and cost of training go up.

The authors of the article "LightGTS: A Lightweight General Time Series Forecasting Model" decided not to rely on brute force, but to take a sensible approach — using the natural properties of time series: scale invariance and periodicity. Their work resulted in the LightGTS framework — a lightweight, efficient solution specifically tailored to real-world time series forecasting tasks. Its key idea is not to fight against scales, but to adapt to them.

Instead of rigid splitting into identical fragments, it was proposed to use periodic tokenization. The model adaptively divides the data into segments whose length corresponds to one complete cycle. This enables it to capture complete patterns regardless of scale — whether on a daily chart or a one-minute chart. The semantics within a token remain unchanged, which means that the feature representation becomes stable and transferable across tasks.

Author: Dmitriy Gizlyk