Discussing the article: "Neural Networks in Trading: A Cross-Domain Time Series Forecasting Framework (TimeFound)"
Hello, Dmitry Gizlyk, I hope you’re doing very well.
In which file have you implemented the CNeuronTimeFoundPatching class?
I’m not sure – perhaps it’s already in one of the folders in the zip archive, or perhaps it’s something that hasn’t yet been uploaded as part of the files for this article.
This approach is very interesting; I hope to see the next instalments soon (in Spanish, my native language). Best wishes.
Could you (if possible) please specify in more detail which libraries the code depends on, as when I try to compile any file, many dependencies are missing
(only the ‘EXPERTS’ files are present, but other files may be missing, for example from the ‘include’ directory).
Hello Dmitry Gizlyk, I hope you’re doing very well.
In which file did you implement the CNeuronTimeFoundPatching class?
I’m not sure – perhaps it’s already in one of the folders in the zip file, or perhaps it’s something that hasn’t yet been uploaded as part of the files for this article.
This is a very interesting approach; I look forward to seeing the next instalments soon (in Spanish, my mother tongue). Best wishes.
Good afternoon, Miguel.
The CNeuronTimeFoundPatching class is included in the NeuroNet.mqh library.
Could you (if possible) please specify in more detail which libraries the code depends on, as when I try to compile any file, there are many missing dependencies
(only the ‘EXPERTS’ files are present, but other files may be missing, for example from the ‘include’ directory).
- dng
- forge.mql5.io
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
Check out the new article: Neural Networks in Trading: A Cross-Domain Time Series Forecasting Framework (TimeFound).
In the past, classical statistical models — such as ARIMA and exponential smoothing — were widely used. Come to think of it, even linear regression often proved useful. The arguments for why the model should be simpler sounded convincing — until deep neural networks entered the picture. Today, they do not merely bear fruit — they reap the harvest, impressing with their accuracy and speed in processing terabytes of historical data.
However, like any powerful weapon, deep models have their downsides. Training them requires a whole mine of labeled data for the specific task. Without this, the neural-network Big Brother simply won't work. But what should you do if you only have a limited amount of historical data, or if the market has just started trading? How can you predict the price of a newly issued token for which the broker's terminal has not yet accumulated any meaningful history? This is where the concept of Zero-Shot Forecasting comes in — an approach that allows the model to perform in settings where traditional methods are powerless.
Time-series researchers have drawn parallels with large language models (Large Language Models). LLMs are already highly successful with text: they translate, write poetry, and answer questions. Why not apply their ideas to forecasting price trends? That's how the boom in so-called Foundation Models for time series began. Imagine this: a single, universal model — and it does not matter whether it is predicting stock prices, electricity consumption, or the unemployment rate. The key is to train it properly using a diverse dataset.
Inspired by this idea of universality, the authors of the paper "TimeFound: A Foundation Model for Time Series Forecasting" introduced a new framework based on the Transformer architecture as a basis for time series forecasting: TimeFound. They took the best ideas from the world of NLP and adapted them for time series forecasting.
Author: Dmitriy Gizlyk