Roffild Library is an extensive framework and collection of expert advisors for MetaTrader 5 that bridges MQL5 with modern data science tools. It provides functional implementations for machine learning models, specifically Multilayer Perceptron neural networks and Random Forests via the AlgLib library. The project fac
Framework & template · MT5
MQL5 Neural Network Library
This MetaTrader 5 expert advisor provides a comprehensive framework for training and deploying deep learning models natively within the MQL5 environment.
GitHub stars5
Forks1
Last update8 weeks ago28 Jul 2026
LicenceNone stated
Latest releasev0.0.11 year ago
Overview
MQL5 Neural Network Library bypasses external dependencies by implementing Multilayer Perceptron, Recurrent Neural Network, and Long Short-Term Memory architectures directly in the platform. The system features a two-phase workflow: a training mode that optimizes model weights based on historical price deltas and RSI, and an inference mode for live trade execution. Weights are saved in binary format for persistent storage. The provided implementation focuses on price movement forecasting for automated decision-making.
- Native MQL5 training and inference
- Support for MLP, RNN, and LSTM architectures
- Weight serialization to binary files
- Integrated RSI feature engineering
- Automated price delta forecasting
Details
Author
4SIGHTalgo on GitHub
Type
Framework & template
Platform
MetaTrader 5 (MQL5)
Strategy
AI / machine learning
Markets
Any symbol
Timeframes
Any timeframe
Risk profile
- Trades without a fixed stop loss
EA files
Topics
algorithmic-tradingmachinemql5neuralnetworkquantitative-financequanttrading
Input parameters
Read from WorkFlow_test.mq5. Defaults are the author's; change them in the EA's Inputs tab.
| Name | Type | Default | Description |
|---|---|---|---|
ModelToUse | ENUM_MODEL_TYPE | MODEL_LSTM | Which neural network model to use? |
TrainMode | bool | true | Set to true for initial training, false for deployment. |
TargetMAE | double | 0.02 | Train until the average error is below this value. |
MaxTrainingEpochs | int | 100 | Safety break for training loop. |
PredictionBars | int | 1 | How many bars into the future to predict. |
SequenceLength | int | 60 | Fixed lookback window for the model. |
RsiPeriod | int | 14 | RSI Period for the new indicator feature. |
How to install it
- 1Download the sourceUse "Download source (.zip)" above, or clone 4SIGHTalgo/MQL5-Neural-Network-Library from GitHub, and unzip it.
- 2Open the data folderIn MetaTrader choose File, then Open Data Folder, and go to MQL5/Experts.
- 3Copy the filesCopy the .mq5 file into Experts, and any .mqh files into the Include folder the code expects.
- 4Compile in MetaEditorOpen the file in MetaEditor and press Compile. Fix any missing includes the compiler reports.
- 5Test before you tradeRun it in the Strategy Tester, then attach it to a demo chart and allow algorithmic trading.
Third-party code. ForexR did not write, test or endorse this EA, and the summary above was generated automatically from its README and code. ForexR lists only repositories with readable source code and never hosts files. Read the code, backtest it and use a demo account first; automated trading can lose money quickly.
Similar expert advisors
Neural Network Tester Improved is a MetaTrader 5 expert advisor designed as a framework for integrating machine learning models into automated trading. The repository includes a main tester file that references an external neural network library. Currently, the source code provides a basic structure for initialization
This MetaTrader 5 expert advisor serves as a modular framework for building high-performance trading systems with external connectivity. It utilizes a three-pillar architecture: a bridge interface for REST API communication with external backends, a multi-agent logic system for AI-driven signal generation, and a risk m
This MetaTrader 5 framework integrates artificial intelligence models into trading strategies through the OpenRouter API. It provides a structured set of libraries for managing multiple AI providers, handling API fallback logic, and parsing natural language outputs into executable trade commands. The included demo expe
This MetaTrader 5 framework provides tools for integrating machine learning models with algorithmic trading. It features scripts designed to generate training data by exporting price action and technical indicators like RSI, MACD, and Stochastics into CSV formats. The system interfaces with external neural network mode
This repository provides a framework for integrating machine learning and quantum physics models with MetaTrader 4 and 5. It aims to implement a Quantum Genetic Algorithm and Support Vector Machine for feature selection and price classification. The system utilizes a ZeroMQ bridge to connect Python 3.8 with the trading
Need a broker for MT5?
Compare regulated brokers that support MetaTrader, with spreads, minimum deposits and leverage side by side.
Compare brokers