Fixing Gold Market Overfitting: A Predictive Machine Studying Method – Buying and selling Methods – 17 February 2026

Fixing Gold Market Overfitting: A Predictive Machine Studying Method with ONNX and Gradient Boosting

Case Examine: The “Golden Gauss” Structure

Writer: Daglox Kankwanda

ORCID: 0009-0000-8306-0938
Technical Paper: Zenodo Repository (DOI: 10.5281/zenodo.18646499)

Contents

1. Introduction
2. The Core Issues in Algorithmic Buying and selling
3. Methodology
4. System Structure
5. Function Engineering
6. Validation and Outcomes
7. Commerce Administration
8. Trustworthy Limitations
9. Conclusion
10. Implementation & Availability
11. References

1. Introduction

The algorithmic buying and selling house, notably in retail markets, faces a basic credibility drawback. The sample is predictable and pervasive: methods display spectacular backtest efficiency, adopted by speedy degradation in ahead testing, culminating in account destruction throughout dwell deployment. This failure mode stems from a single root trigger—optimization for in-sample efficiency with out rigorous out-of-sample validation.

The mathematical actuality is simple: given enough levels of freedom, any mannequin can “memorize” historic worth patterns. Such memorization produces spectacular backtest metrics whereas offering zero predictive energy for future market conduct. The mannequin has discovered the noise, not the sign.

Past overfitting, conventional indicator-based approaches undergo from a basic timing deficiency. Technical indicators, by development, are reactive—they course of historic knowledge to generate alerts after worth actions have already begun.

Core Thesis: A really helpful buying and selling system should determine the circumstances previous vital worth exercise, not the exercise itself. The aim is prediction, not affirmation.

This text presents a technique that synthesizes machine studying analysis insights right into a sensible, deployable buying and selling system for XAUUSD (Gold) markets, demonstrated by way of the “Golden Gauss” structure.

2. The Core Issues in Algorithmic Buying and selling

2.1 The Overfitting Disaster

The proliferation of “AI-powered” buying and selling methods in retail markets has created a credibility disaster, with most methods exhibiting catastrophic failure when deployed on unseen knowledge attributable to extreme overfitting.

Determine 1: Conceptual illustration of the everyday Skilled Advisor lifecycle. Fashions optimized for historic efficiency often fail catastrophically when deployed on unseen market circumstances.

2.2 The Latency Downside in Technical Evaluation

Technical indicators are inherently reactive:

• By the point RSI crosses the overbought threshold, the value has already moved considerably
• By the point a MACD crossover confirms, the optimum entry window has handed
• By the point a breakout is “confirmed,” stop-loss necessities have expanded considerably

Determine 2: Comparability of timing between reactive technical indicators and predictive machine studying approaches. Conventional indicators affirm strikes after optimum entry has handed, whereas predictive methods determine setup circumstances earlier than execution.

2.3 Literature Context

The applying of machine studying to monetary time-series prediction has developed considerably. A number of constant findings are related:

3. Methodology

3.1 The Predictive Labeling Methodology

Normal approaches to coaching buying and selling fashions label knowledge on the level the place worth motion happens. This creates a basic drawback: if the mannequin learns options calculated from the identical bars which can be labeled, it successfully learns to acknowledge strikes which can be already occurring somewhat than strikes which can be about to occur.

The Golden Gauss structure employs a technique that maintains temporal separation between function calculation and label placement:

• The labeling course of identifies worthwhile zones the place worth moved considerably in a particular path
• All options are calculated from market knowledge that occurred earlier than the labeled zone begins

Determine 3: Handbook labeling interface displaying XAUUSD worth motion with recognized directional zones. The labeled BUY and SELL areas characterize worthwhile strikes used as coaching targets; the mannequin learns to foretell these strikes utilizing options calculated from previous market knowledge.

Implications: This temporal separation ensures the mannequin learns to acknowledge preconditions—the market microstructure patterns that precede vital strikes—somewhat than traits of the strikes themselves.

3.2 High quality-Filtered Coaching Labels

Not all worth actions are significant or tradeable. Many are:

• Too small to beat transaction prices (unfold + fee)
• Too erratic to execute cleanly
• A part of bigger consolidation patterns with out directional follow-through

The labeling course of applies strict filtering standards, figuring out solely zones the place worth moved with enough magnitude and directional consistency. This ensures the mannequin learns solely from setups that exceeded minimal profitability thresholds.

3.3 Twin-Mannequin Directional Structure

Market dynamics exhibit basic asymmetry between bullish and bearish conduct:

• Accumulation patterns differ structurally from distribution patterns
• Worry-driven promoting sometimes executes sooner than greed-driven shopping for
• Help conduct differs from resistance conduct
• Quantity traits differ between advances and declines

To respect this asymmetry, the structure employs two unbiased binary fashions:

Every mannequin is a binary classifier detecting solely its respective directional setup. This prevents the confusion that happens when a single mannequin makes an attempt to be taught contradictory patterns concurrently.

3.4 Stroll-Ahead Validation Protocol

Normal machine studying cross-validation, which shuffles knowledge randomly, is inappropriate for monetary time-series attributable to temporal dependencies and lookahead bias dangers.

The system makes use of strict walk-forward validation with full chronological separation:

• Coaching knowledge extends by way of December 31, 2024
• All architectural selections, hyperparameters, and have engineering selections have been finalized utilizing solely this knowledge
• The mannequin was then frozen and validated on a 13-month out-of-sample interval (January 2025 by way of January 2026)

Determine 4: Temporal knowledge separation for walk-forward validation. Coaching knowledge extends by way of finish of 2024; all 2025-2026 analysis represents strictly out-of-sample efficiency on knowledge not used for coaching.

Crucial Guidelines:

• No shuffling of time-series knowledge
• Analysis interval evaluation solely in spite of everything mannequin selections finalized
• No iterative “peeking” at analysis outcomes to regulate parameters

4. System Structure

The system includes two distinct however built-in elements:

1. Coaching Pipeline — carried out in Python for mannequin improvement and validation
2. Execution Engine — carried out in MQL5 for real-time deployment inside MetaTrader 5

Determine 5: Excessive-level structure of the system. The coaching pipeline (prime) processes historic knowledge by way of function engineering and mannequin coaching, exporting by way of ONNX. The execution engine (backside) calculates options instantaneously, obtains likelihood scores, and applies commerce administration logic for place execution.

4.1 Mannequin Structure Choice

The selection of mannequin structure was pushed by empirical analysis towards standards particular to monetary time-series prediction:

Based mostly on in depth testing, Gradient Boosting Choice Timber (GBDT) have been chosen. This alternative aligns with constant findings within the machine studying literature that GBDT architectures outperform deep studying approaches on structured monetary knowledge.

Why Not Neural Networks?

Whereas “Neural Community” generates advertising attraction, the technical actuality for tabular monetary knowledge:

• GBDTs deal with function interactions naturally with out express specification
• GBDTs are extra strong to noise and outliers in monetary knowledge
• GBDTs require considerably much less coaching knowledge
• GBDTs present interpretable function significance rankings
• GBDTs practice sooner, enabling extra in depth hyperparameter search

4.2 ONNX Deployment

The mannequin is exported by way of ONNX (Open Neural Community Change) for platform-agnostic deployment, enabling Python-trained fashions to execute at C++ speeds inside MT5.

A vital requirement is training-serving parity: function calculations in MQL5 should be mathematically an identical to these carried out throughout Python coaching. Any discrepancy creates “training-serving skew” that degrades mannequin efficiency.

4.3 The MQL5-ONNX Interface

The bridge between Python coaching and MQL5 execution depends on the native ONNX API launched in MetaTrader 5 Construct 3600. The first engineering problem is making certain the enter tensor form matches the Python export precisely, and appropriately decoding the classifier’s dual-output construction.

Beneath is the structural logic used to initialize and run inference with the Gradient Boosting mannequin throughout the Skilled Advisor:

Mannequin Initialization

#useful resource "InformationBULLISH_Model.onnx" as uchar ExtModelBuy[]
lengthy g_onnx_buy;
const int SNIPER_FEATURES = 239;

bool InitializeONNXModels()
{
    Print("Loading ONNX fashions...");
    
    
    g_onnx_buy = OnnxCreateFromBuffer(ExtModelBuy, ONNX_DEFAULT);
    if(g_onnx_buy == INVALID_HANDLE)
    {
        Print("[FAIL] Did not load BUY mannequin");
        return false;
    }
    
    
    ulong input_shape_buy[] = {1, SNIPER_FEATURES};
    if(!OnnxSetInputShape(g_onnx_buy, 0, input_shape_buy))
    {
        Print("[FAIL] Did not set BUY mannequin enter form");
        return false;
    }
    
    Print("   [OK] BUY mannequin loaded efficiently");
    return true;
}

Likelihood Inference

The classifier outputs two tensors: predicted labels and sophistication possibilities. For probability-based execution, we extract the likelihood of the goal class:

bool GetBuyPrediction(const float &options[], double &likelihood)
{
    likelihood = 0.0;
    
    if(g_onnx_buy == INVALID_HANDLE)
    {
        Print("[FAIL] BUY mannequin not loaded");
        return false;
    }
    
    
    float input_data[];
    ArrayResize(input_data, SNIPER_FEATURES);
    ArrayCopy(input_data, options);
    
    
    
    
    
    lengthy output_labels[];      
    float output_probs[];      
    
    ArrayResize(output_labels, 1);
    ArrayResize(output_probs, 2);
    ArrayInitialize(output_labels, 0);
    ArrayInitialize(output_probs, 0.0f);
    
    
    if(!OnnxRun(g_onnx_buy, ONNX_NO_CONVERSION, input_data, output_labels, output_probs))
    {
        int error = GetLastError();
        Print("[FAIL] BUY ONNX inference failed: ", error);
        return false;
    }
    
    
    
    likelihood = (double)output_probs[0];
    
    return true;
}

Key Implementation Particulars:

• Twin-Output Construction: Gradient Boosting classifiers exported by way of ONNX produce two outputs—the expected label and the likelihood distribution throughout courses. The likelihood output is used for threshold-based execution.
• Class Mapping: Class 0 represents the goal situation (BULLISH for the BUY mannequin). The likelihood output_probs[0] immediately signifies mannequin confidence in an imminent bullish transfer.
• Form Validation: Strict form checking at initialization catches training-serving mismatches instantly somewhat than producing silent prediction errors throughout dwell buying and selling.

4.4 Execution Configuration

5. Function Engineering

The system processes 239 engineered options throughout a number of research-backed domains. These options have been developed by way of tutorial literature assessment, area experience in market microstructure, and iterative empirical testing with strict validation protocols.

5.1 Function Classes Overview

5.2 Key Driving Options

The next options constantly ranked among the many most influential based on world SHAP significance evaluation:

• ADX Development Power (14-period): Measuring development power, unbiased of path
• VWAP Volatility Deviation: Distance of worth from intraday VWAP, normalized by latest volatility
• Volatility Regime Classifier: ATR relative to its transferring common, indicating low-, normal-, or high-volatility states
• MACD Histogram Momentum: Capturing short-term momentum and potential reversals
• 60-minute Gold/DXY Rolling Correlation: Rolling correlation between XAUUSD and DXY returns
• 60-minute Gold/USDJPY Rolling Correlation: Rolling correlation between XAUUSD and USDJPY returns
• Directional Volatility Regime: Signed volatility function combining EMA-based development power with present ATR regime
• Order-Circulate Persistence: Proxy for the way lengthy directional strikes persist throughout latest candles
• EMA Unfold Dynamics: Distances and slopes between quick and gradual EMAs

The presence of well-known indicators (ADX, MACD) alongside proprietary regime and correlation options demonstrates that the mannequin enhances, somewhat than replaces, established market relationships with higher-resolution timing alerts.

5.3 Cross-Asset Intelligence

Gold (XAUUSD) doesn’t commerce in isolation. Its worth motion is influenced by:

• US Greenback Dynamics: Sometimes inverse correlation; greenback power typically pressures gold costs
• Secure-Haven Flows: Correlation with different safe-haven property throughout risk-off intervals
• Yield Expectations: Relationship with actual rate of interest proxies

The function set incorporates lagged returns from correlated devices, rolling correlations at a number of time scales, divergence detection, and regime change alerts.

6. Validation and Outcomes

The validation method follows a single precept: display generalization, not memorization. Any mannequin can obtain spectacular outcomes on knowledge it has seen. The one significant analysis is efficiency on strictly unseen knowledge.

6.1 Out-of-Pattern Efficiency

All 2025 efficiency represents true out-of-sample (OOS) outcomes. The mannequin structure, hyperparameters, and have set have been frozen earlier than any 2025 knowledge was evaluated.

Determine 6: Backtest fairness and steadiness curves from Jan 2021 to Jan 2026. The interval Jan 2021–Dec 2024 represents knowledge included in mannequin coaching; the interval Jan 2025–Jan 2026 constitutes strictly out-of-sample analysis.

Interpretation: The out-of-sample interval demonstrates continued profitability with metrics that degrade gracefully from the coaching interval:

• Win charge decreases from 88.71% to 83.67%—a managed 5% discount indicating the mannequin generalizes somewhat than memorizes
• Revenue issue stays above 1.50, confirming constructive expectancy on unseen knowledge
• The upper OOS Sharpe ratio (13.9 vs 9.90) offers sturdy proof towards overfitting

This efficiency hole is anticipated and wholesome. The managed degradation confirms real sample generalization.

6.2 Likelihood Threshold Evaluation

The mannequin outputs steady likelihood scores. Evaluation reveals the connection between likelihood ranges and commerce outcomes:

Why 88% Minimal Threshold? The 88% threshold was decided by way of systematic analysis because the optimum entry level balancing commerce frequency towards high quality. Beneath this threshold, false-positive charges enhance considerably.

6.3 Exit Composition Evaluation

The overwhelming majority of successful trades exit by way of the ratchet system, capturing earnings dynamically somewhat than ready for full TP.

6.4 Temporal Consistency

All years worthwhile with constant efficiency patterns throughout coaching and out-of-sample intervals.

7. Commerce Administration

The system implements a complete commerce administration layer that extends past easy entry execution.

7.1 Likelihood-Based mostly Choice Making

Not like methods that generate discrete “purchase” or “promote” alerts, the structure calculates likelihood scores instantaneously on every new bar:

• Entry Choice: Likelihood should exceed 88% threshold earlier than place opening
• Course Choice: Greater likelihood between BUY and SELL fashions determines path
• Exit Timing: Likelihood adjustments inform place closure selections
• Maintain/Shut Logic: Steady likelihood monitoring throughout open positions

7.2 Entry Validation and Filtering

• Twin-Mannequin Affirmation: Each BUY and SELL mannequin possibilities are assessed to substantiate directional bias and filter ambiguous circumstances
• Regime Filtering: Further filters detect unfavorable market regimes (excessive volatility occasions, low liquidity intervals)
• Conditional Execution: Commerce execution proceeds solely after likelihood thresholds are happy and regime filters affirm favorable circumstances

7.3 Ratchet Revenue Safety

Downside Addressed: Value might transfer 80% towards the take-profit degree, then reverse—with out energetic administration, this unrealized revenue could be misplaced.

Ratchet Resolution: As worth strikes favorably, the system progressively locks in revenue by tightening exit circumstances, making certain that vital favorable strikes are captured even when the total take-profit is just not reached.

7.4 Ratchet Loss Minimization

Downside Addressed: Even high-confidence predictions often fail; ready for the fastened stop-loss ends in most loss on each shedding commerce.

Ratchet Resolution: When worth strikes adversely, the system actively manages the exit to reduce loss somewhat than passively ready for stop-loss execution, lowering common loss per unsuccessful commerce.

8. Trustworthy Limitations

8.1 What This System Is NOT

• Not infallible: Roughly 15–18% of alerts lead to suboptimal entries relying on market circumstances
• Not common: Skilled solely for XAUUSD with its particular market microstructure and session dynamics
• Not static: Periodic retraining (3–6 months) is required as markets evolve
• Not assured: Out-of-sample validation demonstrates methodology soundness however doesn’t assure future efficiency

8.2 Recognized Danger Elements

8.3 Execution Assumptions

All reported outcomes are based mostly on historic simulations. No further slippage mannequin has been utilized, and real-world execution might result in materially totally different efficiency. These statistics ought to be interpreted as estimates beneath splendid execution circumstances.

9. Conclusion

This text introduced a technique for fixing two basic failures that characterize retail algorithmic buying and selling—overfitting to historic noise and reactive sign technology—by way of rigorous machine studying practices.

The core improvements demonstrated within the Golden Gauss structure embrace:

• Predictive labeling that allows real anticipation of worth strikes
• Twin-model directional specialization that respects market asymmetry
• Likelihood-driven execution that quantifies confidence earlier than commerce entry
• Clever commerce administration that minimizes losses when predictions show suboptimal

On strictly out-of-sample 2025 knowledge—collected in spite of everything mannequin selections have been finalized—the system demonstrates roughly 83.67% directional accuracy on the 88% likelihood threshold. The managed efficiency differential from coaching metrics signifies real sample studying somewhat than memorization.

Key Takeaways for Practitioners

1. By no means shuffle time-series knowledge throughout validation—this creates lookahead bias and knowledge leakage
2. Out-of-sample efficiency is the one significant metric for evaluating dwell buying and selling potential
3. Likelihood thresholds allow accuracy/frequency tradeoffs—larger thresholds yield fewer however higher-quality alerts
4. Twin binary fashions respect the asymmetry between bullish and bearish market dynamics
5. Commerce administration amplifies edge—ratchet mechanisms maximize wins and reduce losses
6. All methods have limitations—sincere acknowledgment permits acceptable deployment and danger administration

The retail algorithmic buying and selling trade suffers from systematic misalignment between vendor incentives and consumer outcomes. The methodology introduced right here—strict temporal separation, documented efficiency degradation, bounded confidence claims—presents a template for sincere system analysis that prioritizes sustainable operation over advertising attraction.

Skilled critique of the validation methodology and underlying assumptions is welcomed. Progress in algorithmic buying and selling requires methods designed to outlive scrutiny somewhat than keep away from it.

10. Implementation & Availability

The structure described on this paper—particularly the predictive labeling engine and the ONNX likelihood inference—has been absolutely carried out within the Golden Gauss AI system.

To help additional analysis and validation, the entire system is offered for testing within the MQL5 Market. The bundle contains the “Visualizer” mode, which renders the likelihood cones and “Kill Zones” immediately on the chart, permitting merchants to watch the mannequin’s decision-making course of in real-time.

Danger Disclaimer: Buying and selling foreign exchange and CFDs includes substantial danger of loss and isn’t appropriate for all traders. Previous efficiency, whether or not in backtesting or dwell buying and selling, doesn’t assure future outcomes. The validation outcomes introduced characterize historic evaluation beneath particular market circumstances that won’t persist. Merchants ought to solely use capital they’ll afford to lose and may contemplate their monetary state of affairs earlier than buying and selling.

References

1. Cao, L. J. and Tay, F. E. H. (2001). Monetary forecasting utilizing help vector machines. Neural Computing & Functions, 10(2), 184-192.
2. Chen, T. and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the twenty second ACM SIGKDD Worldwide Convention on Information Discovery and Information Mining, 785-794.
3. López de Prado, M. (2018). Advances in Monetary Machine Studying. Wiley.
4. Bailey, D. H. and López de Prado, M. (2014). The likelihood of backtest overfitting. Journal of Computational Finance, 17(4), 39-69.
5. Pardo, R. (2008). The Analysis and Optimization of Buying and selling Methods (2nd ed.). Wiley.
6. Krauss, C., Do, X. A., and Huck, N. (2017). Deep neural networks, gradient-boosted bushes, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Analysis, 259(2), 689-702.
7. Baur, D. G. and McDermott, T. Ok. (2010). Is gold a secure haven? Worldwide proof. Journal of Banking & Finance, 34(8), 1886-1898.
8. ONNX Runtime Builders (2021). ONNX Runtime: Excessive efficiency inference and coaching accelerator. Out there: https://onnxruntime.ai/