Discussing the article: "Neural Networks in Trading: A Unified View of Space and Time (Conclusion)"

New comment
 

Check out the new article: Neural Networks in Trading: A Unified View of Space and Time (Conclusion).

The Extralonger framework demonstrates a unique ability to integrate spatial and temporal factors into a single model, ensuring high forecast accuracy. Its architecture allows it to adapt to different planning horizons and financial instruments while maintaining the system's transparency and manageability.

Model training is comprehensive preparation for trading. Before deploying it in the live market, we thoroughly backtested the strategy on historical data. The first stage — offline training — was conducted on a sample of the EURUSD currency pair on the H1 timeframe for the period from January 2024 to June 2025. This period proved to be intense and varied: calm phases of sideways markets alternated with sharp trending moves, while news releases triggered bursts of high volatility. This combination of conditions enabled the model to learn to distinguish a wide range of market scenarios and generate robust trading decisions without losing its bearings in complex situations.

Once the first phase of preparation was complete, we moved on to the second — online fine-tuning in the MetaTrader 5 Strategy Tester. Here, data arrived in real time, bar by bar, and the model learned the dynamics of operating on streaming data. It learned to maintain stability amid market noise, cope with low liquidity, and stay on track during sudden price spikes. This stage served as a sort of fine-tuning of the strategy. It did not change the framework built on historical data, but helped adapt it to real-world conditions and reduced the risk of overfitting.

The final test was conducted using data from July 2025 — this data had not been used previously and was completely new to the model. All parameters obtained in the previous stages were loaded without changes. This clean out-of-sample test made it possible to objectively assess the model's ability to generalize, without any fine-tuning or adjustments.

The test results are presented below.


Author: Dmitriy Gizlyk

New comment