Michael Prescott Burney
- Trader/Developer at EAHQ
- United States
- 77990
|
2 years
experience
|
220
products
|
99
demo versions
|
|
0
jobs
|
0
signals
|
0
subscribers
|
I am a professional trader and Expert Advisor developer focused on building high-performance, risk-driven systems for MetaTrader 5.
My edge was forged through real market experience—enduring drawdowns, refining strategy, and developing a disciplined, repeatable framework that delivers under live conditions.
As the founder of Code Guardian, I create tools and education designed to help traders move with clarity and confidence.
As a father of five, my mission is rooted in building freedom through precision, consistency, and purpose.
I live by one core principle that has shaped both my trading and development: seek first the Kingdom of God, and everything else will follow—words from Jesus Christ, the greatest developer the world has ever known.
My edge was forged through real market experience—enduring drawdowns, refining strategy, and developing a disciplined, repeatable framework that delivers under live conditions.
As the founder of Code Guardian, I create tools and education designed to help traders move with clarity and confidence.
As a father of five, my mission is rooted in building freedom through precision, consistency, and purpose.
I live by one core principle that has shaped both my trading and development: seek first the Kingdom of God, and everything else will follow—words from Jesus Christ, the greatest developer the world has ever known.
Michael Prescott Burney
Lorentzian Classification EA for MetaTrader 5
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
Core idea behind the system
At the center of the EA is a Lorentzian Distance classifier. For each new closed bar, the system builds a feature vector from technical measurements such as RSI, WaveTrend, CCI, and ADX, then compares the current market state to historical data in order to find similar patterns. Based on how those similar patterns resolved in the past, the classifier produces a directional prediction score.
The Lorentzian Distance approach is used because it compresses large feature differences more gracefully than standard Euclidean distance. In practical terms, this makes the similarity calculation more resistant to outliers and volatility spikes that often distort financial data.
The KNN engine can scan up to 2,000 historical bars, evaluate neighbors using the Lorentzian metric, and generate a bullish or bearish vote based on the outcomes of the nearest historical matches. The resulting prediction score helps determine whether current conditions favor a long or short setup.
Kernel regression confirmation
To avoid acting on raw classification output alone, the EA includes a kernel regression confirmation layer. It uses Rational Quadratic and Gaussian kernel estimates to evaluate trend alignment and to confirm whether a KNN signal is supported by the current directional structure of the market.
If the kernel filter is enabled, long signals require bullish kernel alignment and short signals require bearish kernel alignment. This extra confirmation step is intended to reduce false signals, especially during ranging or unstable conditions.
The same kernel logic can also be used for dynamic exit management. When enabled, trades may be closed based on kernel crossover behavior instead of using only a fixed holding model.
Feature-driven market classification
The EA supports up to five simultaneous features in its classification model. The default configuration uses RSI, WaveTrend, CCI, ADX, and a second RSI with different settings so the algorithm can analyze momentum, deviation, cycle behavior, and trend strength from multiple angles.
Each feature is configurable, allowing the user to tailor the behavior of the classifier to different symbols and timeframes. This makes the EA suitable for traders who want to keep the default research-based structure while still being able to optimize the input profile for their own market selection.
Because the feature set is part of the similarity calculation, changing feature periods or types directly affects how the system interprets historical market states. This gives advanced users room to perform optimization and walk-forward validation without changing the overall architecture of the strategy.
Filter stack for trade quality
After the classifier generates a directional bias, the signal must pass through a configurable filter stack before a trade can be opened. Available filters include a volatility filter, regime filter, ADX filter, EMA trend filter, SMA trend filter, session filter, spread filter, and kernel filter.
The volatility filter is designed to block trades during abnormal spikes, while the regime filter helps distinguish trending conditions from flat market structure. The EMA and SMA filters can be used to keep trades aligned with the broader trend, and the ADX filter can restrict entries to periods with sufficient directional strength.
This layered structure is useful because one condition alone is rarely enough in live markets. The EA is designed so that classification, trend alignment, volatility control, and execution filters can work together rather than depend on a single trigger.
Trade management flexibility
Lorentzian Classification EA includes both basic and advanced trade management options. Users can select fixed lot sizing or risk-based sizing, choose ATR-based or fixed stop loss and take profit models, limit the number of open positions, and define a unique magic number for each chart instance.
Advanced controls include trailing stop, breakeven, partial close, and maximum spread protection. These options make it possible to configure the EA for more aggressive execution, balanced swing trading, or more conservative capital-preservation workflows.
The stop and target framework is designed to adapt to different environments. ATR-based stops can respond to changing volatility, while fixed-pip settings remain available for traders who prefer simple and fully deterministic trade management.
Included set file profiles
The EA is delivered with seven pre-configured set file profiles to provide structured starting points for different trading styles and time horizons. These profiles include M15 Scalping, M30 Intraday, H1 Swing, H4 Position, D1 Long-Term, H1 XAUUSD Gold Specialist, and H4 Conservative / Prop Account.
The H4 Position profile is the primary recommended starting point because the underlying Lorentzian framework was originally designed and tested around higher intraday to swing-style timeframes. The other profiles are intended for traders who prefer faster execution, gold-specific tuning, long-term trend participation, or lower-risk funded-account style operation.
These profiles are not presented as fixed final settings. They are designed as structured baselines that traders can further test and refine for their own broker conditions, symbols, and execution style.
How entries are generated
A buy setup requires a positive classification outcome and confirmation from all enabled filters. Depending on the current configuration, this can include trend alignment with EMA or SMA filters, acceptable spread conditions, valid trading session timing, and bullish kernel confirmation.
A sell setup follows the same logic in the opposite direction. The EA also checks that the signal is new rather than a continuation of the previous state, which helps prevent repetitive entries from the same directional bias.
Exits can be handled through fixed trade duration logic, kernel-based dynamic exits, stop loss, take profit, trailing stop, breakeven, or partial close behavior. This makes the execution model adaptable without requiring changes to the signal-generation engine itself.
Chart dashboard and visual tools
The EA includes an on-chart dashboard that displays the current signal state, prediction score, kernel trend status, filter pass/fail conditions, feature values, spread information, position details, and internal trade statistics tracked since startup.
Optional signal arrows can also be displayed on the chart to make historical entries easier to review visually. These elements are intended to help traders understand why a trade was or was not taken and to simplify testing, validation, and ongoing parameter review.
For VPS or optimization environments, the dashboard can be disabled to reduce visual overhead. The display layer is informational and does not change the trading logic itself.
Backtesting and optimization use
The EA was documented with backtesting and optimization in mind. It is intended to be tested in MetaTrader 5 using "Every tick based on real ticks" so that traders can evaluate the classifier, filters, and trade management logic under more realistic simulation conditions.
The manual also outlines a phased optimization workflow covering feature tuning, neighbor count, filter calibration, and ATR-based trade management refinement. This is especially useful for traders who want to adapt the EA to specific pairs without optimizing every parameter at once.
Walk-forward analysis is strongly recommended when refining settings. The goal is not simply to find attractive backtest results, but to identify parameter combinations that remain stable when tested on unseen market data.
Who this EA is built for
This Expert Advisor is suitable for traders who want a structured, research-driven system that blends machine-learning classification with practical market filters and configurable execution management. It can be used by traders who prefer automated operation, as well as by advanced users who want a framework they can study, optimize, and deploy across multiple pairs or timeframes.
The included profiles cover everything from lower-timeframe execution to higher-timeframe position trading, including a dedicated XAUUSD profile and a conservative funded-account style profile. This gives the product flexibility without forcing every user into the same setup.
Main features
Lorentzian Distance KNN classification engine for pattern-based directional analysis.
Kernel regression confluence using Rational Quadratic and Gaussian estimators.
Configurable feature pipeline with RSI, WaveTrend, CCI, and ADX inputs.
Multi-layer filter stack including volatility, regime, ADX, EMA, SMA, session, spread, and kernel filters.
ATR-based or fixed-pip stop loss and take profit management.
Optional trailing stop, breakeven, and partial close functions.
Risk-based lot sizing and support for multiple deployment profiles.
Seven pre-configured set files for different styles, symbols, and risk preferences.
On-chart dashboard with signal state, filter status, feature values, and trade statistics.
Designed for systematic backtesting, phased optimization, and walk-forward validation.
Important usage notes
The EA requires historical data to warm up the classification engine before signals can be generated.
Different brokers, spreads, execution speed, and symbol specifications can affect live behavior compared with tester results.
For lower timeframes and gold trading, broker quality and spread control are especially important.
Unique magic numbers should be used when running multiple instances on the same account.
Demo testing and forward validation are recommended before live deployment.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller#description
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
Core idea behind the system
At the center of the EA is a Lorentzian Distance classifier. For each new closed bar, the system builds a feature vector from technical measurements such as RSI, WaveTrend, CCI, and ADX, then compares the current market state to historical data in order to find similar patterns. Based on how those similar patterns resolved in the past, the classifier produces a directional prediction score.
The Lorentzian Distance approach is used because it compresses large feature differences more gracefully than standard Euclidean distance. In practical terms, this makes the similarity calculation more resistant to outliers and volatility spikes that often distort financial data.
The KNN engine can scan up to 2,000 historical bars, evaluate neighbors using the Lorentzian metric, and generate a bullish or bearish vote based on the outcomes of the nearest historical matches. The resulting prediction score helps determine whether current conditions favor a long or short setup.
Kernel regression confirmation
To avoid acting on raw classification output alone, the EA includes a kernel regression confirmation layer. It uses Rational Quadratic and Gaussian kernel estimates to evaluate trend alignment and to confirm whether a KNN signal is supported by the current directional structure of the market.
If the kernel filter is enabled, long signals require bullish kernel alignment and short signals require bearish kernel alignment. This extra confirmation step is intended to reduce false signals, especially during ranging or unstable conditions.
The same kernel logic can also be used for dynamic exit management. When enabled, trades may be closed based on kernel crossover behavior instead of using only a fixed holding model.
Feature-driven market classification
The EA supports up to five simultaneous features in its classification model. The default configuration uses RSI, WaveTrend, CCI, ADX, and a second RSI with different settings so the algorithm can analyze momentum, deviation, cycle behavior, and trend strength from multiple angles.
Each feature is configurable, allowing the user to tailor the behavior of the classifier to different symbols and timeframes. This makes the EA suitable for traders who want to keep the default research-based structure while still being able to optimize the input profile for their own market selection.
Because the feature set is part of the similarity calculation, changing feature periods or types directly affects how the system interprets historical market states. This gives advanced users room to perform optimization and walk-forward validation without changing the overall architecture of the strategy.
Filter stack for trade quality
After the classifier generates a directional bias, the signal must pass through a configurable filter stack before a trade can be opened. Available filters include a volatility filter, regime filter, ADX filter, EMA trend filter, SMA trend filter, session filter, spread filter, and kernel filter.
The volatility filter is designed to block trades during abnormal spikes, while the regime filter helps distinguish trending conditions from flat market structure. The EMA and SMA filters can be used to keep trades aligned with the broader trend, and the ADX filter can restrict entries to periods with sufficient directional strength.
This layered structure is useful because one condition alone is rarely enough in live markets. The EA is designed so that classification, trend alignment, volatility control, and execution filters can work together rather than depend on a single trigger.
Trade management flexibility
Lorentzian Classification EA includes both basic and advanced trade management options. Users can select fixed lot sizing or risk-based sizing, choose ATR-based or fixed stop loss and take profit models, limit the number of open positions, and define a unique magic number for each chart instance.
Advanced controls include trailing stop, breakeven, partial close, and maximum spread protection. These options make it possible to configure the EA for more aggressive execution, balanced swing trading, or more conservative capital-preservation workflows.
The stop and target framework is designed to adapt to different environments. ATR-based stops can respond to changing volatility, while fixed-pip settings remain available for traders who prefer simple and fully deterministic trade management.
Included set file profiles
The EA is delivered with seven pre-configured set file profiles to provide structured starting points for different trading styles and time horizons. These profiles include M15 Scalping, M30 Intraday, H1 Swing, H4 Position, D1 Long-Term, H1 XAUUSD Gold Specialist, and H4 Conservative / Prop Account.
The H4 Position profile is the primary recommended starting point because the underlying Lorentzian framework was originally designed and tested around higher intraday to swing-style timeframes. The other profiles are intended for traders who prefer faster execution, gold-specific tuning, long-term trend participation, or lower-risk funded-account style operation.
These profiles are not presented as fixed final settings. They are designed as structured baselines that traders can further test and refine for their own broker conditions, symbols, and execution style.
How entries are generated
A buy setup requires a positive classification outcome and confirmation from all enabled filters. Depending on the current configuration, this can include trend alignment with EMA or SMA filters, acceptable spread conditions, valid trading session timing, and bullish kernel confirmation.
A sell setup follows the same logic in the opposite direction. The EA also checks that the signal is new rather than a continuation of the previous state, which helps prevent repetitive entries from the same directional bias.
Exits can be handled through fixed trade duration logic, kernel-based dynamic exits, stop loss, take profit, trailing stop, breakeven, or partial close behavior. This makes the execution model adaptable without requiring changes to the signal-generation engine itself.
Chart dashboard and visual tools
The EA includes an on-chart dashboard that displays the current signal state, prediction score, kernel trend status, filter pass/fail conditions, feature values, spread information, position details, and internal trade statistics tracked since startup.
Optional signal arrows can also be displayed on the chart to make historical entries easier to review visually. These elements are intended to help traders understand why a trade was or was not taken and to simplify testing, validation, and ongoing parameter review.
For VPS or optimization environments, the dashboard can be disabled to reduce visual overhead. The display layer is informational and does not change the trading logic itself.
Backtesting and optimization use
The EA was documented with backtesting and optimization in mind. It is intended to be tested in MetaTrader 5 using "Every tick based on real ticks" so that traders can evaluate the classifier, filters, and trade management logic under more realistic simulation conditions.
The manual also outlines a phased optimization workflow covering feature tuning, neighbor count, filter calibration, and ATR-based trade management refinement. This is especially useful for traders who want to adapt the EA to specific pairs without optimizing every parameter at once.
Walk-forward analysis is strongly recommended when refining settings. The goal is not simply to find attractive backtest results, but to identify parameter combinations that remain stable when tested on unseen market data.
Who this EA is built for
This Expert Advisor is suitable for traders who want a structured, research-driven system that blends machine-learning classification with practical market filters and configurable execution management. It can be used by traders who prefer automated operation, as well as by advanced users who want a framework they can study, optimize, and deploy across multiple pairs or timeframes.
The included profiles cover everything from lower-timeframe execution to higher-timeframe position trading, including a dedicated XAUUSD profile and a conservative funded-account style profile. This gives the product flexibility without forcing every user into the same setup.
Main features
Lorentzian Distance KNN classification engine for pattern-based directional analysis.
Kernel regression confluence using Rational Quadratic and Gaussian estimators.
Configurable feature pipeline with RSI, WaveTrend, CCI, and ADX inputs.
Multi-layer filter stack including volatility, regime, ADX, EMA, SMA, session, spread, and kernel filters.
ATR-based or fixed-pip stop loss and take profit management.
Optional trailing stop, breakeven, and partial close functions.
Risk-based lot sizing and support for multiple deployment profiles.
Seven pre-configured set files for different styles, symbols, and risk preferences.
On-chart dashboard with signal state, filter status, feature values, and trade statistics.
Designed for systematic backtesting, phased optimization, and walk-forward validation.
Important usage notes
The EA requires historical data to warm up the classification engine before signals can be generated.
Different brokers, spreads, execution speed, and symbol specifications can affect live behavior compared with tester results.
For lower timeframes and gold trading, broker quality and spread control are especially important.
Unique magic numbers should be used when running multiple instances on the same account.
Demo testing and forward validation are recommended before live deployment.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller#description
· 2
Michael Prescott Burney
DeltaPulse Auto for MT5
DeltaPulse Auto is an Expert Advisor for MetaTrader 5 that trades structural divergence confirmed by the Quantum Delta Wave and manages exposure with built-in prop-firm risk controls.
What this Expert Advisor does
DeltaPulse Auto is the automated counterpart of the DeltaPulse Wave concept. It is designed for traders who want selective entries, hard-stop protection, and disciplined account management in one trading robot.
Automated divergence-based entries
Quantum Delta Wave confirmation
ATR-based stop-loss and take-profit management
Break-even and ATR trailing functions
Risk-based or fixed-lot position sizing
Built-in prop-firm protection rules
27 ready-to-load presets
Trading logic
The Expert Advisor evaluates the market on each closed bar. It rebuilds the Quantum Delta Wave, detects fresh structural divergence around recent pivots, and can require extreme-zone confirmation before allowing an entry.
Buy setup: bullish divergence, where price makes a lower low while the wave makes a higher low in oversold territory
Sell setup: bearish divergence, where price makes a higher high while the wave makes a lower high in overbought territory
Entry style: selective, rule-based, and designed to avoid overtrading
Trade management
Every trade is opened with a hard Stop Loss and Take Profit. The default configuration uses ATR-based exits, while fixed-point stop and target values are also available.
Hard Stop Loss on every trade
Hard Take Profit on every trade
Break-even trigger with profit lock
ATR trailing stop to protect gains
One trade per symbol by default
One entry per bar by default
Risk engine
DeltaPulse Auto includes a built-in risk engine intended for disciplined trading and challenge-style account rules. The default design focuses on capital preservation rather than aggressive exposure.
Risk % of balance sizing mode
Fixed lot sizing mode
Daily loss limit control
Maximum drawdown control
Optional profit target
Optional close-on-limit protection
The EA does not use martingale, grid, or averaging techniques. Each trade carries a defined stop, and the default setup is intentionally conservative for structured risk handling.
Included presets
DeltaPulse Auto includes 27 presets so users can start with a configuration that is already aligned with the target market and account style.
Forex presets for major pairs and intraday or swing use
Metals presets for instruments such as gold and silver
Index presets for session-aware index trading
Crypto presets for 24/7 markets with wider ATR settings
Broker account-type presets for Cent, Standard, ECN, and Large accounts
Prop-firm style presets for FTMO, FundedNext, The5ers, and generic one-step challenge workflows
Main inputs
The inputs are organized so traders can understand and adjust the main behavior of the system without changing the core strategy logic.
Strategy engine: Delta Wave lookback, smoothing, OB/OS boundaries, pivot spacing, extreme-zone confirmation
Sizing and stops: sizing mode, risk %, fixed lot, max lot, ATR or fixed SL/TP
Management and filters: break-even, ATR trailing, max positions, one-per-bar, session filter, spread filter, magic number
Guards: daily loss limit, maximum drawdown, optional profit target
Setup and workflow
For first use, load the preset that best matches your symbol, timeframe, and account type. Then forward-test on a demo account before moving to a live or funded environment.
Install the EA in the Experts folder of MetaTrader 5
Load the matching preset from the Inputs tab
Use a unique magic number per chart
Keep spread and session filters enabled when appropriate
Forward-test before live deployment
Dashboard
The live dashboard displays balance, equity, open trades, daily drawdown, maximum drawdown, and the current status of the EA. If trading is halted by a protection rule, the dashboard shows the reason.
Best use case
DeltaPulse Auto is intended for traders who want an automated divergence strategy with clear risk boundaries, structured trade management, and preset-based deployment across multiple market types.
https://www.mql5.com/en/market/product/180330?source=Site+Profile+Seller#description
DeltaPulse Auto is an Expert Advisor for MetaTrader 5 that trades structural divergence confirmed by the Quantum Delta Wave and manages exposure with built-in prop-firm risk controls.
What this Expert Advisor does
DeltaPulse Auto is the automated counterpart of the DeltaPulse Wave concept. It is designed for traders who want selective entries, hard-stop protection, and disciplined account management in one trading robot.
Automated divergence-based entries
Quantum Delta Wave confirmation
ATR-based stop-loss and take-profit management
Break-even and ATR trailing functions
Risk-based or fixed-lot position sizing
Built-in prop-firm protection rules
27 ready-to-load presets
Trading logic
The Expert Advisor evaluates the market on each closed bar. It rebuilds the Quantum Delta Wave, detects fresh structural divergence around recent pivots, and can require extreme-zone confirmation before allowing an entry.
Buy setup: bullish divergence, where price makes a lower low while the wave makes a higher low in oversold territory
Sell setup: bearish divergence, where price makes a higher high while the wave makes a lower high in overbought territory
Entry style: selective, rule-based, and designed to avoid overtrading
Trade management
Every trade is opened with a hard Stop Loss and Take Profit. The default configuration uses ATR-based exits, while fixed-point stop and target values are also available.
Hard Stop Loss on every trade
Hard Take Profit on every trade
Break-even trigger with profit lock
ATR trailing stop to protect gains
One trade per symbol by default
One entry per bar by default
Risk engine
DeltaPulse Auto includes a built-in risk engine intended for disciplined trading and challenge-style account rules. The default design focuses on capital preservation rather than aggressive exposure.
Risk % of balance sizing mode
Fixed lot sizing mode
Daily loss limit control
Maximum drawdown control
Optional profit target
Optional close-on-limit protection
The EA does not use martingale, grid, or averaging techniques. Each trade carries a defined stop, and the default setup is intentionally conservative for structured risk handling.
Included presets
DeltaPulse Auto includes 27 presets so users can start with a configuration that is already aligned with the target market and account style.
Forex presets for major pairs and intraday or swing use
Metals presets for instruments such as gold and silver
Index presets for session-aware index trading
Crypto presets for 24/7 markets with wider ATR settings
Broker account-type presets for Cent, Standard, ECN, and Large accounts
Prop-firm style presets for FTMO, FundedNext, The5ers, and generic one-step challenge workflows
Main inputs
The inputs are organized so traders can understand and adjust the main behavior of the system without changing the core strategy logic.
Strategy engine: Delta Wave lookback, smoothing, OB/OS boundaries, pivot spacing, extreme-zone confirmation
Sizing and stops: sizing mode, risk %, fixed lot, max lot, ATR or fixed SL/TP
Management and filters: break-even, ATR trailing, max positions, one-per-bar, session filter, spread filter, magic number
Guards: daily loss limit, maximum drawdown, optional profit target
Setup and workflow
For first use, load the preset that best matches your symbol, timeframe, and account type. Then forward-test on a demo account before moving to a live or funded environment.
Install the EA in the Experts folder of MetaTrader 5
Load the matching preset from the Inputs tab
Use a unique magic number per chart
Keep spread and session filters enabled when appropriate
Forward-test before live deployment
Dashboard
The live dashboard displays balance, equity, open trades, daily drawdown, maximum drawdown, and the current status of the EA. If trading is halted by a protection rule, the dashboard shows the reason.
Best use case
DeltaPulse Auto is intended for traders who want an automated divergence strategy with clear risk boundaries, structured trade management, and preset-based deployment across multiple market types.
https://www.mql5.com/en/market/product/180330?source=Site+Profile+Seller#description
· 1
Michael Prescott Burney
Core features for the buyer
PyroFlux EA v3 puts a lot of emphasis on execution quality and user experience:
A full‑chart heatmap and dark‑themed HUD give a clear visual explanation of what the EA “sees” when it trades, instead of hiding logic from the user.
Broker safety checks verify trading permissions, symbol trade mode, tick size, quote validity and stops levels before any trade is opened, helping avoid issues with restricted symbols, prop firm rules or misconfigured accounts.
Conservative entry filters check minimum profile range, maximum spread, POC alignment, slope direction and closed‑bar confirmation, so trades are not opened in thin, noisy or obviously conflicting conditions.
Flexible exit models (zone SL/TP, logic‑only, hybrid) and partial profit options allow the user to choose between more mechanical, more discretionary or more risk‑managed styles without rewriting the EA.
Position sizing supports both fixed lots and balance‑per‑0.01‑lot sizing, normalized to the symbol’s minimum, maximum and step volume, making it easier to adapt the EA to different account sizes and instruments.
All of this is packaged as a single EX5 file with Latin‑character inputs and no DLLs or hidden account limitations, in line with Market requirements and your own preference for simple, transparent end‑user experience.
Inputs and configurability
Inputs are grouped into logical sections: profile engine, thermal palette, geometry, TradingView‑style theme, HUD panel, core trading, position sizing, entry filters, stops and targets, broker safety checks, diagnostics and performance. Each group can be adjusted without touching code, and default values are chosen to be neither too aggressive nor too conservative for most liquid symbols and common intraday/swing timeframes.
Buyers can enable or disable automatic regime selection, tighten or relax filters for spread and profile range, enforce stricter risk‑reward floors, and choose whether the EA trades only on new bars or on every tick. This keeps configuration focused on clear, understandable concepts instead of obscure parameters, which is important for Market users who are evaluating multiple products and want to understand what knobs they are turning.
https://www.mql5.com/en/market/product/183750?source=Site+Market+My+Products+Page#description
PyroFlux EA v3 puts a lot of emphasis on execution quality and user experience:
A full‑chart heatmap and dark‑themed HUD give a clear visual explanation of what the EA “sees” when it trades, instead of hiding logic from the user.
Broker safety checks verify trading permissions, symbol trade mode, tick size, quote validity and stops levels before any trade is opened, helping avoid issues with restricted symbols, prop firm rules or misconfigured accounts.
Conservative entry filters check minimum profile range, maximum spread, POC alignment, slope direction and closed‑bar confirmation, so trades are not opened in thin, noisy or obviously conflicting conditions.
Flexible exit models (zone SL/TP, logic‑only, hybrid) and partial profit options allow the user to choose between more mechanical, more discretionary or more risk‑managed styles without rewriting the EA.
Position sizing supports both fixed lots and balance‑per‑0.01‑lot sizing, normalized to the symbol’s minimum, maximum and step volume, making it easier to adapt the EA to different account sizes and instruments.
All of this is packaged as a single EX5 file with Latin‑character inputs and no DLLs or hidden account limitations, in line with Market requirements and your own preference for simple, transparent end‑user experience.
Inputs and configurability
Inputs are grouped into logical sections: profile engine, thermal palette, geometry, TradingView‑style theme, HUD panel, core trading, position sizing, entry filters, stops and targets, broker safety checks, diagnostics and performance. Each group can be adjusted without touching code, and default values are chosen to be neither too aggressive nor too conservative for most liquid symbols and common intraday/swing timeframes.
Buyers can enable or disable automatic regime selection, tighten or relax filters for spread and profile range, enforce stricter risk‑reward floors, and choose whether the EA trades only on new bars or on every tick. This keeps configuration focused on clear, understandable concepts instead of obscure parameters, which is important for Market users who are evaluating multiple products and want to understand what knobs they are turning.
https://www.mql5.com/en/market/product/183750?source=Site+Market+My+Products+Page#description
· 1
Michael Prescott Burney
PyroFlux Liquidity Matrix EA v3 – Marketplace‑grade liquidity engine with full‑chart visuals and strict broker checks
PyroFlux Liquidity Matrix EA v3 is a MetaTrader 5 trading robot from Expert Advisor HQ (EAHQ) that combines a live price–volume profile “matrix” with an embedded heatmap and HUD to help traders see and trade the real liquidity structure behind each move. It is designed for users who want a visually transparent, rule‑based Expert Advisor rather than a black‑box system, with all critical logic exposed through on‑chart diagnostics and structured inputs.
PyroFlux continuously builds a tick‑volume profile across a configurable history window, identifies a Point of Control (POC) and high‑volume zones above and below price, and then classifies the current regime (range, trend, reversal, breakout) before deciding whether to trade. Entry logic can be set to automatic regime detection or locked to specific styles (reversal, breakout, POC reversion, continuation), while exits can be driven by zone‑based SL/TP, logic‑only closures, or a hybrid of both, giving the buyer enough flexibility to match the EA to their own risk and workflow without changing its core philosophy.
https://www.mql5.com/en/market/product/183750?source=Site+Market+My+Products+Page#
PyroFlux Liquidity Matrix EA v3 is a MetaTrader 5 trading robot from Expert Advisor HQ (EAHQ) that combines a live price–volume profile “matrix” with an embedded heatmap and HUD to help traders see and trade the real liquidity structure behind each move. It is designed for users who want a visually transparent, rule‑based Expert Advisor rather than a black‑box system, with all critical logic exposed through on‑chart diagnostics and structured inputs.
PyroFlux continuously builds a tick‑volume profile across a configurable history window, identifies a Point of Control (POC) and high‑volume zones above and below price, and then classifies the current regime (range, trend, reversal, breakout) before deciding whether to trade. Entry logic can be set to automatic regime detection or locked to specific styles (reversal, breakout, POC reversion, continuation), while exits can be driven by zone‑based SL/TP, logic‑only closures, or a hybrid of both, giving the buyer enough flexibility to match the EA to their own risk and workflow without changing its core philosophy.
https://www.mql5.com/en/market/product/183750?source=Site+Market+My+Products+Page#
· 1
Michael Prescott Burney
Published product
PyroFlux Liquidity Matrix EA v3 – Marketplace‑grade liquidity engine with full‑chart visuals and strict broker checks PyroFlux Liquidity Matrix EA v3 is a MetaTrader 5 trading robot from Expert Advisor HQ (EAHQ) that combines a live price–volume profile “matrix” with an embedded heatmap and HUD to help traders see and trade the real liquidity structure behind each move. It is designed for users who want a visually transparent, rule‑based Expert Advisor rather than a black‑box system, with all
· 1
Michael Prescott Burney
Version 2.02 — Stability & Performance Update
Released: June 2026
This update addresses several rendering, stability, and performance issues reported after timeframe and symbol switching. The core engine has been hardened with bounds protection, smarter redraw gating, and a layout cache system that significantly reduces CPU overhead.
Bug Fixes
Fixed: Array out of range errors in the profile engine
All bin index operations inside BuildProfileWindow are now clamped against the actual allocated array size rather than the global bin count. This eliminates the runtime crash that could occur immediately after a timeframe switch or during rapid symbol changes when internal state had not yet fully re-synchronized.
Fixed: Heatmap and HUD not drawing on certain timeframes
The indicator previously exited silently when bar history was not yet available after a timeframe switch. The HUD panel now renders independently of profile readiness, and the engine retries automatically on subsequent ticks until data is confirmed available.
Fixed: POC box and heatmap rendering outside the visible chart area
All canvas draw coordinates are now clamped to the chart bounds before any FillRectangle or TextOut call. The POC label box is now sized dynamically relative to chart width, preventing it from overflowing into the price scale.
Fixed: Stale canvas objects persisting across symbol or timeframe reloads
Bitmap label objects are now explicitly deleted before being recreated on initialization, preventing ghost overlays from appearing when the indicator reloads.
Performance Improvements
Heatmap layout cache
A layout validity check now gates the full heatmap repaint. If the chart width, height, first visible bar, visible bar count, and current bar time have not changed since the last draw, the expensive full-canvas rebuild is skipped entirely. This dramatically reduces CPU on stable charts.
Smarter redraw throttle
A g_needFullRedraw flag bypasses the refresh interval when a forced repaint is genuinely required (timeframe switch, chart resize, history load), while routine ticks continue to use the configurable minimum interval. This prevents both stale renders and unnecessary repaints.
Canvas resize guard
The heatmap and HUD canvases are only resized when the chart dimensions actually change, eliminating the repeated CCanvas::Resize calls that were visible in profiling as a top CPU consumer.
HUD decoupled from heatmap
The branded HUD panel now updates independently of the heatmap render pass. This means the panel remains visible and current even while the heatmap is waiting for history to load on a new timeframe.
Hard data guard in OnCalculate
The indicator now checks bar availability before entering the render path, preventing wasted work and suppressing spurious errors during the brief window after a timeframe switch when data is still synchronizing.
Notes
No input parameters were changed. All existing settings are fully compatible.
Visual output is identical to v2.01 on stable charts.
Users on lower-end systems or trading many symbols simultaneously should see the most noticeable improvement in responsiveness.
https://www.mql5.com/en/market/product/179802?source=Site+Profile+Seller
Released: June 2026
This update addresses several rendering, stability, and performance issues reported after timeframe and symbol switching. The core engine has been hardened with bounds protection, smarter redraw gating, and a layout cache system that significantly reduces CPU overhead.
Bug Fixes
Fixed: Array out of range errors in the profile engine
All bin index operations inside BuildProfileWindow are now clamped against the actual allocated array size rather than the global bin count. This eliminates the runtime crash that could occur immediately after a timeframe switch or during rapid symbol changes when internal state had not yet fully re-synchronized.
Fixed: Heatmap and HUD not drawing on certain timeframes
The indicator previously exited silently when bar history was not yet available after a timeframe switch. The HUD panel now renders independently of profile readiness, and the engine retries automatically on subsequent ticks until data is confirmed available.
Fixed: POC box and heatmap rendering outside the visible chart area
All canvas draw coordinates are now clamped to the chart bounds before any FillRectangle or TextOut call. The POC label box is now sized dynamically relative to chart width, preventing it from overflowing into the price scale.
Fixed: Stale canvas objects persisting across symbol or timeframe reloads
Bitmap label objects are now explicitly deleted before being recreated on initialization, preventing ghost overlays from appearing when the indicator reloads.
Performance Improvements
Heatmap layout cache
A layout validity check now gates the full heatmap repaint. If the chart width, height, first visible bar, visible bar count, and current bar time have not changed since the last draw, the expensive full-canvas rebuild is skipped entirely. This dramatically reduces CPU on stable charts.
Smarter redraw throttle
A g_needFullRedraw flag bypasses the refresh interval when a forced repaint is genuinely required (timeframe switch, chart resize, history load), while routine ticks continue to use the configurable minimum interval. This prevents both stale renders and unnecessary repaints.
Canvas resize guard
The heatmap and HUD canvases are only resized when the chart dimensions actually change, eliminating the repeated CCanvas::Resize calls that were visible in profiling as a top CPU consumer.
HUD decoupled from heatmap
The branded HUD panel now updates independently of the heatmap render pass. This means the panel remains visible and current even while the heatmap is waiting for history to load on a new timeframe.
Hard data guard in OnCalculate
The indicator now checks bar availability before entering the render path, preventing wasted work and suppressing spurious errors during the brief window after a timeframe switch when data is still synchronizing.
Notes
No input parameters were changed. All existing settings are fully compatible.
Visual output is identical to v2.01 on stable charts.
Users on lower-end systems or trading many symbols simultaneously should see the most noticeable improvement in responsiveness.
https://www.mql5.com/en/market/product/179802?source=Site+Profile+Seller
· 1
Michael Prescott Burney
Hamunaptra is a free automated trading system for GBPUSD on the H1 chart, built around 50 internal strategies and a fixed 1:1 risk-reward structure on every trade.
This new build gives Hamunaptra an all-new look and feel, combining structured trade execution with a cleaner, more modern on-chart experience. It is designed for traders who want a free GBPUSD system with diversified logic, balanced trade construction, and a more professional live-chart presentation.
Core trading model
Hamunaptra is optimized for GBPUSD H1 and now uses 50 built-in strategies working inside one EA framework. This multi-strategy structure is designed to create broader market coverage while keeping all execution inside a single organized system.
All fifty strategies now operate with a 1:1 risk-reward model, meaning each trade is opened with an equal distance between stop loss and take profit. This gives the EA a cleaner and more disciplined trade-management structure, with consistency across all internal strategy logic.
The system is intended for traders who prefer a more balanced approach to automated trading rather than exaggerated target distances or unstable trade handling. By standardizing the risk-reward model across the full strategy stack, Hamunaptra is built to deliver more uniform execution behavior on GBPUSD H1.
All-new look and feel
One of the biggest upgrades in this version is the complete visual refresh. Hamunaptra now features a redesigned on-chart interface with a more advanced TradingView-style appearance, helping your live charts feel cleaner, sharper, and more premium while the EA is running.
The new dashboard style replaces plain chart text with a richer visual layout that presents important information in a much more modern way. This gives the system a more polished presentation on live charts and makes it easier to monitor activity at a glance.
New visual features
The latest build also includes the new interface additions introduced in the updated visual framework. These include a collapsible dashboard panel, live display toggles, a per-strategy breakdown section, clickable strategy-row highlighting, and enhanced trade projection visuals directly on the chart.
The collapsible panel allows you to switch between a full dashboard view and a compact minimized bar, giving you more flexibility over chart space. The settings controls make it possible to show or hide visual sections in real time, so the display can be adjusted without needing to remove and reload the EA.
The per-strategy breakdown helps you see which strategy components are currently active, while clickable rows make it easier to connect dashboard activity to the exact position shown on the chart. Together, these additions turn Hamunaptra into a more interactive and user-friendly trading tool rather than just a background automation system.
Free system for GBPUSD H1
Hamunaptra is offered as a free EA for traders who want to explore a diversified GBPUSD H1 trading system with modern chart visuals and a fully updated presentation. It combines 50 strategies, a fixed 1:1 risk-reward structure, and an all-new dashboard experience in one complete package.
If you are looking for a free GBPUSD robot with a fresh interface, organized trade logic, and a more professional chart-side experience, Hamunaptra is built to deliver exactly that.
https://www.mql5.com/en/market/product/125260?source=Site+Profile+Seller#
This new build gives Hamunaptra an all-new look and feel, combining structured trade execution with a cleaner, more modern on-chart experience. It is designed for traders who want a free GBPUSD system with diversified logic, balanced trade construction, and a more professional live-chart presentation.
Core trading model
Hamunaptra is optimized for GBPUSD H1 and now uses 50 built-in strategies working inside one EA framework. This multi-strategy structure is designed to create broader market coverage while keeping all execution inside a single organized system.
All fifty strategies now operate with a 1:1 risk-reward model, meaning each trade is opened with an equal distance between stop loss and take profit. This gives the EA a cleaner and more disciplined trade-management structure, with consistency across all internal strategy logic.
The system is intended for traders who prefer a more balanced approach to automated trading rather than exaggerated target distances or unstable trade handling. By standardizing the risk-reward model across the full strategy stack, Hamunaptra is built to deliver more uniform execution behavior on GBPUSD H1.
All-new look and feel
One of the biggest upgrades in this version is the complete visual refresh. Hamunaptra now features a redesigned on-chart interface with a more advanced TradingView-style appearance, helping your live charts feel cleaner, sharper, and more premium while the EA is running.
The new dashboard style replaces plain chart text with a richer visual layout that presents important information in a much more modern way. This gives the system a more polished presentation on live charts and makes it easier to monitor activity at a glance.
New visual features
The latest build also includes the new interface additions introduced in the updated visual framework. These include a collapsible dashboard panel, live display toggles, a per-strategy breakdown section, clickable strategy-row highlighting, and enhanced trade projection visuals directly on the chart.
The collapsible panel allows you to switch between a full dashboard view and a compact minimized bar, giving you more flexibility over chart space. The settings controls make it possible to show or hide visual sections in real time, so the display can be adjusted without needing to remove and reload the EA.
The per-strategy breakdown helps you see which strategy components are currently active, while clickable rows make it easier to connect dashboard activity to the exact position shown on the chart. Together, these additions turn Hamunaptra into a more interactive and user-friendly trading tool rather than just a background automation system.
Free system for GBPUSD H1
Hamunaptra is offered as a free EA for traders who want to explore a diversified GBPUSD H1 trading system with modern chart visuals and a fully updated presentation. It combines 50 strategies, a fixed 1:1 risk-reward structure, and an all-new dashboard experience in one complete package.
If you are looking for a free GBPUSD robot with a fresh interface, organized trade logic, and a more professional chart-side experience, Hamunaptra is built to deliver exactly that.
https://www.mql5.com/en/market/product/125260?source=Site+Profile+Seller#
· 1
Michael Prescott Burney
Lorentzian Classification EA for MetaTrader 5
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
· 1
Michael Prescott Burney
Core Trading Concept
The logic of the EA begins with the SuperTrend indicator, which uses ATR-based volatility bands to identify bullish and bearish market phases. A lower factor creates tighter bands and faster reactions, while a higher factor creates wider bands and slower but more selective signals. The main challenge with a traditional SuperTrend is that one fixed factor rarely performs well in all market conditions.
To solve this, SuperTrend AI Clustering calculates a full range of SuperTrend variations using user-defined factor values. Each variation is tracked with a performance score that reflects how effectively that factor has aligned with recent price movement. These performance scores are then processed through a K-Means clustering model, which separates them into three groups representing weaker, average, and stronger recent performance.
The EA then selects the target cluster and calculates an adaptive factor from that group. This adaptive factor drives the final SuperTrend used for trade logic, trailing behavior, and dashboard display. In practical terms, the Expert Advisor is always trying to work with the SuperTrend sensitivity that best matches the current market environment.
https://www.mql5.com/en/market/product/180711?source=Site+Market+My+Products+Page#description
The logic of the EA begins with the SuperTrend indicator, which uses ATR-based volatility bands to identify bullish and bearish market phases. A lower factor creates tighter bands and faster reactions, while a higher factor creates wider bands and slower but more selective signals. The main challenge with a traditional SuperTrend is that one fixed factor rarely performs well in all market conditions.
To solve this, SuperTrend AI Clustering calculates a full range of SuperTrend variations using user-defined factor values. Each variation is tracked with a performance score that reflects how effectively that factor has aligned with recent price movement. These performance scores are then processed through a K-Means clustering model, which separates them into three groups representing weaker, average, and stronger recent performance.
The EA then selects the target cluster and calculates an adaptive factor from that group. This adaptive factor drives the final SuperTrend used for trade logic, trailing behavior, and dashboard display. In practical terms, the Expert Advisor is always trying to work with the SuperTrend sensitivity that best matches the current market environment.
https://www.mql5.com/en/market/product/180711?source=Site+Market+My+Products+Page#description
· 1
Michael Prescott Burney
Published product
SuperTrend AI Clustering Expert Advisor for MetaTrader 5 SuperTrend AI Clustering is an adaptive trend-following Expert Advisor for MetaTrader 5 designed to adjust itself to changing market conditions. Instead of using one fixed SuperTrend multiplier, the EA evaluates multiple factor values at the same time, measures their recent performance, applies K-Means clustering, and selects the factor group that is currently performing best. This creates a dynamic SuperTrend model that can respond to
· 1
Michael Prescott Burney
SuperTrend AI Clustering Expert Advisor for MetaTrader 5
SuperTrend AI Clustering is an adaptive trend-following Expert Advisor for MetaTrader 5 designed to adjust itself to changing market conditions. Instead of using one fixed SuperTrend multiplier, the EA evaluates multiple factor values at the same time, measures their recent performance, applies K-Means clustering, and selects the factor group that is currently performing best. This creates a dynamic SuperTrend model that can respond to different volatility regimes and market structures without requiring constant manual reconfiguration.
The system is built for traders who want an automated approach to trend-following with a strong focus on adaptability, structured risk control, and transparent on-chart information. It can be used on forex pairs, metals, indices, cryptocurrencies, commodities, and other symbols available in MetaTrader 5. The Expert Advisor is compatible with multiple timeframes, from lower-timeframe intraday trading to higher-timeframe swing and position trading.
https://www.mql5.com/en/users/michael4308/seller
SuperTrend AI Clustering is an adaptive trend-following Expert Advisor for MetaTrader 5 designed to adjust itself to changing market conditions. Instead of using one fixed SuperTrend multiplier, the EA evaluates multiple factor values at the same time, measures their recent performance, applies K-Means clustering, and selects the factor group that is currently performing best. This creates a dynamic SuperTrend model that can respond to different volatility regimes and market structures without requiring constant manual reconfiguration.
The system is built for traders who want an automated approach to trend-following with a strong focus on adaptability, structured risk control, and transparent on-chart information. It can be used on forex pairs, metals, indices, cryptocurrencies, commodities, and other symbols available in MetaTrader 5. The Expert Advisor is compatible with multiple timeframes, from lower-timeframe intraday trading to higher-timeframe swing and position trading.
https://www.mql5.com/en/users/michael4308/seller
· 1
Michael Prescott Burney
Filter stack for trade qualityAfter the classifier generates a directional bias, the signal must pass through a configurable filter stack before a trade can be opened. Available filters include a volatility filter, regime filter, ADX filter, EMA trend filter, SMA trend filter, session filter, spread filter, and kernel filter.
The volatility filter is designed to block trades during abnormal spikes, while the regime filter helps distinguish trending conditions from flat market structure. The EMA and SMA filters can be used to keep trades aligned with the broader trend, and the ADX filter can restrict entries to periods with sufficient directional strength.
This layered structure is useful because one condition alone is rarely enough in live markets. The EA is designed so that classification, trend alignment, volatility control, and execution filters can work together rather than depend on a single trigger.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
The volatility filter is designed to block trades during abnormal spikes, while the regime filter helps distinguish trending conditions from flat market structure. The EMA and SMA filters can be used to keep trades aligned with the broader trend, and the ADX filter can restrict entries to periods with sufficient directional strength.
This layered structure is useful because one condition alone is rarely enough in live markets. The EA is designed so that classification, trend alignment, volatility control, and execution filters can work together rather than depend on a single trigger.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
· 1
Michael Prescott Burney
Lorentzian Classification EA for MetaTrader 5
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position.
The system was built for traders who want a more adaptive, data-driven approach than fixed-rule indicators alone. Instead of relying on a single signal source, the EA evaluates a multi-feature market state, compares it to historical patterns, and uses confluence logic to reduce weak or low-quality entries.
https://www.mql5.com/en/market/product/180639?source=Site+Profile+Seller
· 1
Michael Prescott Burney
Risk Management
Reversion Apex EA includes a full risk-control engine rather than simple signal execution. It supports automatic risk-% position sizing, fixed-lot mode, ATR-based or fixed stop loss and take profit, break-even protection, trailing stop management, and optional RSI cross-back exits. It also includes daily loss protection, maximum drawdown guards, profit target control, spread filtering, session filtering, and one-entry-per-bar logic for more disciplined live trading.
https://www.mql5.com/en/market/product/180327?source=Site+Market+My+Products+Page#description
Reversion Apex EA includes a full risk-control engine rather than simple signal execution. It supports automatic risk-% position sizing, fixed-lot mode, ATR-based or fixed stop loss and take profit, break-even protection, trailing stop management, and optional RSI cross-back exits. It also includes daily loss protection, maximum drawdown guards, profit target control, spread filtering, session filtering, and one-entry-per-bar logic for more disciplined live trading.
https://www.mql5.com/en/market/product/180327?source=Site+Market+My+Products+Page#description
· 1
Michael Prescott Burney
Included set file profiles
The EA is delivered with seven pre-configured set file profiles to provide structured starting points for different trading styles and time horizons. These profiles include M15 Scalping, M30 Intraday, H1 Swing, H4 Position, D1 Long-Term, H1 XAUUSD Gold Specialist, and H4 Conservative / Prop Account.
The H4 Position profile is the primary recommended starting point because the underlying Lorentzian framework was originally designed and tested around higher intraday to swing-style timeframes. The other profiles are intended for traders who prefer faster execution, gold-specific tuning, long-term trend participation, or lower-risk funded-account style operation.
These profiles are not presented as fixed final settings. They are designed as structured baselines that traders can further test and refine for their own broker conditions, symbols, and execution style.
https://www.mql5.com/en/market/product/180639?source=Site+Profile#
The EA is delivered with seven pre-configured set file profiles to provide structured starting points for different trading styles and time horizons. These profiles include M15 Scalping, M30 Intraday, H1 Swing, H4 Position, D1 Long-Term, H1 XAUUSD Gold Specialist, and H4 Conservative / Prop Account.
The H4 Position profile is the primary recommended starting point because the underlying Lorentzian framework was originally designed and tested around higher intraday to swing-style timeframes. The other profiles are intended for traders who prefer faster execution, gold-specific tuning, long-term trend participation, or lower-risk funded-account style operation.
These profiles are not presented as fixed final settings. They are designed as structured baselines that traders can further test and refine for their own broker conditions, symbols, and execution style.
https://www.mql5.com/en/market/product/180639?source=Site+Profile#
· 1
Michael Prescott Burney
Feature-driven market classification
The EA supports up to five simultaneous features in its classification model. The default configuration uses RSI, WaveTrend, CCI, ADX, and a second RSI with different settings so the algorithm can analyze momentum, deviation, cycle behavior, and trend strength from multiple angles.
Each feature is configurable, allowing the user to tailor the behavior of the classifier to different symbols and timeframes. This makes the EA suitable for traders who want to keep the default research-based structure while still being able to optimize the input profile for their own market selection.
Because the feature set is part of the similarity calculation, changing feature periods or types directly affects how the system interprets historical market states. This gives advanced users room to perform optimization and walk-forward validation without changing the overall architecture of the strategy.
https://www.mql5.com/en/market/product/180639?source=Site+Profile#
The EA supports up to five simultaneous features in its classification model. The default configuration uses RSI, WaveTrend, CCI, ADX, and a second RSI with different settings so the algorithm can analyze momentum, deviation, cycle behavior, and trend strength from multiple angles.
Each feature is configurable, allowing the user to tailor the behavior of the classifier to different symbols and timeframes. This makes the EA suitable for traders who want to keep the default research-based structure while still being able to optimize the input profile for their own market selection.
Because the feature set is part of the similarity calculation, changing feature periods or types directly affects how the system interprets historical market states. This gives advanced users room to perform optimization and walk-forward validation without changing the overall architecture of the strategy.
https://www.mql5.com/en/market/product/180639?source=Site+Profile#
· 1
Michael Prescott Burney
Lorentzian Classification EA for MT5: A Machine Learning Trading System Built for Smarter Market Decisions If you are looking for an Expert Advisor that goes beyond fixed indicator rules and instead learns from historical market behavior, the Lorentzian Classification EA was built for that purpos...
· 1
177
Michael Prescott Burney
Kernel regression confirmation
To avoid acting on raw classification output alone, the EA includes a kernel regression confirmation layer. It uses Rational Quadratic and Gaussian kernel estimates to evaluate trend alignment and to confirm whether a KNN signal is supported by the current directional structure of the market.
If the kernel filter is enabled, long signals require bullish kernel alignment and short signals require bearish kernel alignment. This extra confirmation step is intended to reduce false signals, especially during ranging or unstable conditions.
The same kernel logic can also be used for dynamic exit management. When enabled, trades may be closed based on kernel crossover behavior instead of using only a fixed holding model.
https://www.mql5.com/en/market/product/180639?source=Site+Market+My+Products+Page#description
To avoid acting on raw classification output alone, the EA includes a kernel regression confirmation layer. It uses Rational Quadratic and Gaussian kernel estimates to evaluate trend alignment and to confirm whether a KNN signal is supported by the current directional structure of the market.
If the kernel filter is enabled, long signals require bullish kernel alignment and short signals require bearish kernel alignment. This extra confirmation step is intended to reduce false signals, especially during ranging or unstable conditions.
The same kernel logic can also be used for dynamic exit management. When enabled, trades may be closed based on kernel crossover behavior instead of using only a fixed holding model.
https://www.mql5.com/en/market/product/180639?source=Site+Market+My+Products+Page#description
· 1
Michael Prescott Burney
Core idea behind the system
At the center of the EA is a Lorentzian Distance classifier. For each new closed bar, the system builds a feature vector from technical measurements such as RSI, WaveTrend, CCI, and ADX, then compares the current market state to historical data in order to find similar patterns. Based on how those similar patterns resolved in the past, the classifier produces a directional prediction score.
The Lorentzian Distance approach is used because it compresses large feature differences more gracefully than standard Euclidean distance. In practical terms, this makes the similarity calculation more resistant to outliers and volatility spikes that often distort financial data.
The KNN engine can scan up to 2,000 historical bars, evaluate neighbors using the Lorentzian metric, and generate a bullish or bearish vote based on the outcomes of the nearest historical matches. The resulting prediction score helps determine whether current conditions favor a long or short setup.
https://www.mql5.com/en/market/product/180639?source=Site+Market+My+Products+Page
At the center of the EA is a Lorentzian Distance classifier. For each new closed bar, the system builds a feature vector from technical measurements such as RSI, WaveTrend, CCI, and ADX, then compares the current market state to historical data in order to find similar patterns. Based on how those similar patterns resolved in the past, the classifier produces a directional prediction score.
The Lorentzian Distance approach is used because it compresses large feature differences more gracefully than standard Euclidean distance. In practical terms, this makes the similarity calculation more resistant to outliers and volatility spikes that often distort financial data.
The KNN engine can scan up to 2,000 historical bars, evaluate neighbors using the Lorentzian metric, and generate a bullish or bearish vote based on the outcomes of the nearest historical matches. The resulting prediction score helps determine whether current conditions favor a long or short setup.
https://www.mql5.com/en/market/product/180639?source=Site+Market+My+Products+Page
· 1
Michael Prescott Burney
Published product
Lorentzian Classification EA for MetaTrader 5 Lorentzian Classification EA is a machine-learning-based Expert Advisor for MetaTrader 5 designed to classify market conditions and automate trade execution using a structured confirmation process. It combines Lorentzian Distance K-Nearest Neighbors (KNN) classification with kernel regression trend confirmation, then applies multiple market filters and configurable trade management rules before opening a position. The system was built for traders who
· 1