Dmitriy Gizlyk / Profil

We are pleased to present the final part of our series on GinAR — a neural network framework for time series forecasting. In this article, we analyze the results of testing the model on new data and assess its robustness under real-market conditions.

We invite you to explore a new implementation of the key components of the GinAR framework — an adaptive algorithm for working with graph-structured time series. This article provides a step-by-step breakdown of the architecture and the algorithms for the forward pass and error backpropagation.

We invite you to explore an innovative approach to forecasting time series with missing data using the GinAR framework. The article demonstrates the implementation of key components using OpenCL, which ensures high performance. In our next publication, we will take a detailed look at how to integrate these solutions into MQL5. This will help understand how to apply the method in practice in trading.

We invite you to learn about the K²VAE framework and how the proposed approaches can be integrated into a trading system. You will learn how the hybrid Koopman–Kalman–VAE approach helps build adaptive and interpretable models. The article concludes with practical results from using the implemented solutions.

We invite you to explore a new approach that combines classical methods and modern neural networks for time series analysis. The article provides a detailed explanation of the architecture and operating principles of the K²VAE model.

We invite you to explore the original implementation of the K²VAE framework — a flexible model capable of linearly approximating complex dynamics in latent space. This article demonstrates how to implement key components in MQL5, including parameterized matrices and how to manage them outside standard neural network layers. This material will be useful for anyone looking for a practical approach to building interpretable time-series models.

We invite you to dive into the exciting world of LightGTS — a lightweight yet powerful framework for time-series forecasting, where adaptive convolution and RoPE encoding are combined with innovative attention mechanisms. In our article, you will find a detailed description of all components — from creating patches to the complex mixture of experts in the decoder — ready for integration into MQL5 projects. Discover how LightGTS takes automated trading to a whole new level!

We invite you to embark on an exciting journey through the world of adaptive analysis of financial time series and learn how to turn complex spectral analysis and flexible convolution into real trading signals. You will see how LightGTS listens to the market rhythm, adapting to its changes through a variable-window stride, and how OpenCL acceleration can turn computation into a fast track to profitable decisions.

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.

The article provides a fascinating look at how SwiGLU embedding reveals hidden market patterns, and how a sparse Mixture of Experts within a Decoder-Only Transformer makes forecasts more accurate at reasonable computational cost. We take an in-depth look at the integration of Time‑MoE into MQL5 and OpenCL, and provide a step-by-step guide to configuring and training the model.

We invite you to explore the practical implementation of a sparse mixture of experts block for time series in the OpenCL computing environment. This article provides a step-by-step explanation of how masked multi-window convolution works, as well as how gradient-based training is organized in the presence of multiple information streams.

Wir laden Sie ein, das moderne Time-MoE-Framework kennenzulernen, das für Zeitreihenprognosen angepasst wurde. In diesem Artikel werden wir die wichtigsten Komponenten der Architektur Schritt für Schritt umsetzen und dabei Erläuterungen und praktische Beispiele geben. Mit diesem Ansatz können Sie nicht nur verstehen, wie das Modell funktioniert, sondern diese Prinzipien auch auf reale Handelsszenarien anwenden.

The article focuses on the practical implementation of the TimeFound model for time series forecasting. The key stages of implementing the framework's main approaches using MQL5 are examined.

In this article, we build the core of the TimeFound intelligent model step by step, adapting it to real-world time series forecasting tasks. If you are interested in the practical implementation of neural network patching algorithms in MQL5, you have come to the right place.

Das Mantis-Framework transformiert komplexe Zeitreihen in informative Token und dient als zuverlässige Grundlage für einen intelligenten Handelsagenten, der in Echtzeit agieren kann.

Mantis is a versatile tool for in-depth time series analysis that can be flexibly scaled to accommodate any financial scenario. Learn how a combination of patching, local convolutions, and cross-attention enables a highly accurate interpretation of market patterns.

Lernen Sie Mantis kennen – ein leichtgewichtiges Foundation-Model für die Zeitreihenklassifizierung auf Basis einer Transformer-Architektur mit kontrastivem Vortraining und einem hybriden Attention-Mechanismus, der eine rekordverdächtige Genauigkeit und hohe Skalierbarkeit ermöglicht.

The article will show you how Mamba4Cast turns theory into a working trading algorithm and lays the groundwork for your own experiments. Do not miss this opportunity to gain a full range of knowledge and inspiration for developing your own strategy.

Wir setzen unsere Bekanntschaft mit dem Mamba4Cast-Framework fort. Heute werden wir uns mit der praktischen Umsetzung der vorgeschlagenen Ansätze befassen. Mamba4Cast wurde nicht für eine lange Anpassungsphase bei jeder neuen Zeitreihe entwickelt, sondern für den sofortigen Einsatz. Dank des Konzepts des Zero-Shot-Forecastings kann das Modell hochwertige Prognosen auf realen Daten ohne zusätzliches Training oder Hyperparameter-Tuning erstellen.

In diesem Artikel stellen wir das Mamba4Cast-Framework vor und betrachten eine seiner Schlüsselkomponenten genauer: die zeitstempelbasierte Positionskodierung. Der Artikel zeigt, wie das Time-Embedding unter Berücksichtigung der Kalenderstruktur der Daten gebildet wird.