XGBoost Classifier MT5: Free MT5 Expert Advisor

Overview

XGBoost Classifier MT5 enters trades based on classification probabilities and a minimum gap between prediction classes. The system features extensive risk controls, including stop loss and take profit levels calculated via Average True Range multiples. Additional filters include a trend-following EMA check on higher timeframes and a volatility filter based on ATR percentiles. It also incorporates a kill switch mechanism that monitors recent performance to automatically pause trading during periods of low win rates.

ONNX machine learning model integration

ATR-based dynamic volatility filtering

Performance-based automated kill switch

Trend filtering with EMA slope and distance

Timed trade exits based on bar count

Details

Author

alexandruchirita4192 on GitHub

Type

Trading robot

Platform

MetaTrader 5 (MQL5)

Strategy

AI / machine learning, Trend following

Markets

Any symbol

Timeframes

Any timeframe

Risk profile

No grid, martingale or hedging logic was found in its code or README. That says nothing about how it performs: backtest it first.

EA files

MT5_XGBoost_Classifier_ONNX_Strategy.mq5

Source

github.com/alexandruchirita4192/XGBoostClassifierMT5

Input parameters

Read from MT5_XGBoost_Classifier_ONNX_Strategy.mq5. Defaults are the author's; change them in the EA's Inputs tab.

Name	Type	Default	Description
`InpLots`	`double`	`0.10`	InpLots: Fixed lot
`InpEntryProbThreshold`	`double`	`0.60`	InpEntryProbThreshold: Minimum probability threshold for BUY/SELL
`InpMinProbGap`	`double`	`0.15`	InpMinProbGap: Minimum difference between the best class and the next one
`InpUseAtrStops`	`bool`	`true`	InpUseAtrStops: Use SL/TP based on ATR
`InpStopAtrMultiple`	`double`	`1.50`	InpStopAtrMultiple: SL = ATR * multiplier
`InpTakeAtrMultiple`	`double`	`2.00`	InpTakeAtrMultiple: TP = ATR * multiplier
`InpMaxBarsInTrade`	`int`	`8`	InpMaxBarsInTrade: Recommended to match horizon_bars from Python
`InpCloseOnOppositeSignal`	`bool`	`true`	InpCloseOnOppositeSignal: Close on opposite signal
`InpAllowLong`	`bool`	`true`	InpAllowLong: Allow BUY
`InpAllowShort`	`bool`	`true`	InpAllowShort: Allow SELL
`InpUseTrendFilter`	`bool`	`true`	InpUseTrendFilter: Enable trend filter
`InpTrendTF`	`ENUM_TIMEFRAMES`	`PERIOD_H1`	InpTrendTF: Trend timeframe

Show all 30 inputs

Name	Type	Default	Description
`InpTrendMAPeriod`	`int`	`100`	InpTrendMAPeriod: EMA period
`InpTrendRequireSlope`	`bool`	`true`	InpTrendRequireSlope: EMA must also have slope in signal direction
`InpUseTrendDistanceFilter`	`bool`	`false`	InpUseTrendDistanceFilter: Require minimum distance from HTF EMA
`InpTrendMinDistancePct`	`double`	`0.0010`	InpTrendMinDistancePct: Minimum distance from EMA (0.001 = 0.1%)
`InpUseAtrVolFilter`	`bool`	`true`	InpUseAtrVolFilter: Enable ATR filter
`InpAtrVolLookback`	`int`	`50`	InpAtrVolLookback: Number of bars for ATR distribution
`InpAtrMinPercentile`	`double`	`0.25`	InpAtrMinPercentile: Minimum ATR percentile in distribution (0..1)
`InpAtrMaxPercentile`	`double`	`0.85`	InpAtrMaxPercentile: Maximum ATR percentile in distribution (0..1)
`InpUseKillSwitch`	`bool`	`false`	InpUseKillSwitch: Enable kill switch
`InpKillSwitchLookbackTrades`	`int`	`8`	InpKillSwitchLookbackTrades: Last N trades analyzed
`InpKillSwitchMinWinRate`	`double`	`0.40`	InpKillSwitchMinWinRate: Minimum accepted win rate
`InpKillSwitchMinProfitFactor`	`double`	`0.95`	InpKillSwitchMinProfitFactor: Minimum accepted profit factor
`InpKillSwitchConsecutiveLosses`	`int`	`4`	InpKillSwitchConsecutiveLosses: Maximum consecutive losses
`InpKillSwitchPauseBars`	`int`	`96`	InpKillSwitchPauseBars: Pause in bars after activation
`InpKillSwitchFlatOnActivate`	`bool`	`true`	InpKillSwitchFlatOnActivate: Close the current position when activated
`InpMagic`	`long`	`26042026`	InpMagic: Magic number
`InpLog`	`bool`	`false`	InpLog: Main log
`InpDebugLog`	`bool`	`false`	InpDebugLog: Log on every new bar

How to install it

1Download the sourceUse "Download source (.zip)" above, or clone alexandruchirita4192/XGBoostClassifierMT5 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.

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

FxChartAI OpenEA

by abiodunaremu

FxChartAI OpenEA is an automated trading solution for MetaTrader 5 that executes trades based on signals retrieved from the FxChartAI platform. The system operates in two modes, allowing for live API integration or historical testing using CSV datasets. It utilizes multi-timeframe analysis across M10 and H1 intervals,

MT5 Trading robot AI / machine learningTrend following

Updated 1 year ago GPL-3.0 GitHub

Gold EA MT5 With OpenAI

by RobertN1D

This Expert Advisor for MetaTrader 5 is specifically designed for XAUUSD trading on the M1 timeframe. It utilizes a hybrid strategy combining classic technical indicators like RSI, Moving Averages, and ATR with an OpenAI API integration for signal validation. The robot features an on-chart dashboard for telemetry and i

MT5 Trading robot ScalpingTrend followingAI / machine learning

Updated 5 months ago None stated GitHub

AI Enhanced HFT

by Marco210210

This MetaTrader 5 expert advisor combines technical indicators with machine learning forecasts to trade the Forex market. It uses a trend-following approach based on Exponential Moving Average crossovers, filtered by the Average Directional Index and volume confirmations. A unique feature is its integration with extern

MT5 Trading robot Trend followingIndicator crossoverAI / machine learning High risk

Updated 1 year ago None stated GitHub

Code To Cash

by LUBANGAKENE

Code To Cash is an end-to-end algorithmic trading system for MetaTrader 5 that combines deep learning forecasts with technical breakout logic. It utilizes a ZeroMQ bridge to receive real-time market predictions from an external Python backend. The system enters trades using BuyStop or SellStop orders at recent price ex

MT5 Trading robot AI / machine learningBreakoutTrend following

Updated 1 year ago None stated GitHub

Heiken Ashi Complete Strats

by jsgaston

This MetaTrader 5 expert advisor provides a versatile framework for trading based on Heiken Ashi price action. It allows users to toggle between numerous built-in strategies, including trend following, moving average crossovers, Fibonacci levels, and various oscillators like RSI and MACD. The system includes an option

MT5 Trading robot Trend followingIndicator crossoverMean reversion

Updated 2 years ago None stated GitHub

MarketSync EA

by sajidmahamud835

MarketSync EA is an experimental MetaTrader 5 expert advisor designed to bridge algorithmic trading with external artificial intelligence. It functions by streaming real-time market and account data from the MT5 terminal to a local Node.js backend via HTTP requests. The external server processes this information using

MT5 Trading robot AI / machine learningGridTrend following High risk

Updated 8 months ago MIT GitHub