Articles on the MQL5 programming and use of trading robots

The article takes readers deep into the heart of the EV-MGRFlowNet framework, showing how its architecture is applied in a practical implementation for financial forecasting tasks. Step by step, we build a carefully designed combination of modules capable of detecting subtle temporal patterns and translating them into meaningful market signals.

Rolling lookback windows implicitly fix a probability vector over past bars. We implement entropy pooling in MQL5 to keep all historical scenarios, reweight them by conditioning on today's volatility under an effective‑scenarios budget, and add views on volatility, tails and correlation. A walk‑forward test, a chart indicator and an ES‑based sizing EA demonstrate how to calibrate risk forecasts and position size to the current regime.

The implementation of the EV-MGRFlowNet framework demonstrates its key advantages: modularity, resilience to market fluctuations, and the ability to develop strategies independently. These features make the framework a powerful tool for analysis, forecasting, and the development of autonomous trading strategies.

This article implements the Garman–Klass volatility estimator as an MQL5 indicator that uses OHLC data for higher statistical efficiency than close-to-close measures. A percentile-based squeeze/expansion detector produces breakout signals, and a companion Expert Advisor executes them via iCustom. Implementation details include series-aware indexing, recursive squeeze-state handling in indicator buffers, and a baseline-on-attach rule for the EA, giving a ready-to-use toolkit for volatility-regime trading.

The article presents an adaptation of the SDformerFlow spiking architecture for the task of dense analysis of price micro-movements. The spatio-temporal structure provides a high level of detail, while the spiking logic ensures computational efficiency and the ability to work with sparse, pulse-like data. As a result, traders gain access to a tool that detects even the slightest shifts in liquidity and provides the foundation for more accurate and consistent real-time decisions.

The article presents an adaptation of the SDformerFlow framework that achieves high adaptability by integrating spiking attention with multi-window convolution and weighted summation of query elements. The architecture allows each attention head to learn its own parameters, which improves the model's accuracy and sensitivity to the structure of the data being analyzed.