XAUUSD Backtesting Case Study: 4-Fold Walk-Forward Rerun

This XAUUSD backtesting case study shows public fold-level results from a SparklingAI gold research rerun completed on May 23, 2026 Malaysia time. The rerun produced a public-safe alpha signal artifact with 26,038 rows for execution-aware analysis.

The goal is to document what the walk-forward test shows without exposing the proprietary alpha logic. The latest result is mixed but useful: some folds were inactive or weak, while the newest fold was active and positive.

Walk-Forward Setup

The public result uses four out-of-sample folds:

• Fold 0: December 2021 to February 2023
• Fold 1: February 2023 to April 2024
• Fold 2: April 2024 to May 2025
• Fold 3: May 2025 to May 2026

Each fold starts with a $5,000 research equity baseline. The stitched walk-forward equity moved from $5,000.00 to $5,439.03 across all out-of-sample windows. The numbers below are aggregated public metrics from the test folds, not the private model recipe.

What The New Rerun Shows

The fold sequence is not uniformly positive, which makes it a better research note:

• Fold 0 produced no trades, which means the system was inactive rather than profitable.
• Fold 1 ended around -1.36% with 26 trades, 61.5% win rate, and 0.83 profit factor.
• Fold 2 ended around +1.53%, but only had one trade, so it is not strong evidence by itself.
• Fold 3 ended around +8.61% with 81 trades, 63.0% win rate, and 1.21 profit factor.
• The combined stitched out-of-sample result was around +8.78% after $205.18 in fees.

This is useful because it shows the full validation story instead of only highlighting the best recent fold.

Why Fold 3 Still Needs Careful Interpretation

Fold 3 is the most recent window and has the highest trade count, so it is valuable for studying current XAUUSD behavior. It also has meaningful drawdown and a profit factor that is positive but not large.

That means Fold 3 should not be presented as a simple victory. It is useful because it shows how the stack behaves in a more active recent period, but the result still needs fees, drawdown, and trade-count context. This is exactly why SparklingAI tracks fold-level metrics instead of only reporting the final return.

Why Not Publish Every Diagnostic

The research folder contains more diagnostic experiments than the public chart shows. Some internal diagnostics test alternate profile heads, execution profiles, and research variants.

Those diagnostics are useful internally, but they are not the selected public walk-forward result. Publishing them in detail could overstate the result and reveal too much about the private alpha and execution stack. For public reporting, the cleaner approach is to show the selected fold-level metrics and explain the validation caveats.

What Is Not Being Published

This case study intentionally avoids publishing:

• Alpha construction
• Signal thresholds
• Feature engineering details
• Training configuration
• Exact execution rules
• Private model-selection logic

The public goal is to explain validation quality, not give away the system.

For the validation method behind this case study, read walk-forward testing for AI trading strategies. For the broader system direction, read what SparklingAI is building.