Wire flash
Shanghai Silver 20-Day ML Timing Model Outperforms Buy-and-Hold; Mid-Frequency Signals Fit Current Volatility
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
A financial news article from China Finance Network (CFi.CN) reports that a machine learning timing model for Shanghai silver futures (沪银) has demonstrated effectiveness. Data shows the 20-day XGBoost timing model achieved a directional accuracy of 62.50% and an AUC of approximately 0.618. The long-short strategy's ending net value reached 7.73, significantly higher than the buy-and-hold net value of 4.68. The 5-day model had 60.19% accuracy but underperformed simple holding and dual moving average strategies during the long bull market cycle. Recent institutional research indicates the 20-day timing strategy still generates significant excess returns after deducting transaction costs, suggesting medium-frequency signals are better suited to current silver volatility characteristics. The research notes the model does not pursue high-frequency capture but uses a fusion of macro, price-volume, and event factors to effectively filter short-term noise, providing stable entry and exit signals during periods of strong trend continuity. High-confidence stratification improves per-trade win rates but produces too few signals (only 12 trades in 20 days), limiting practicality. The default threshold 20-day strategy has a profit-loss ratio of 2.33, and combined with position management can control drawdowns. The core value for traders is providing an implementable medium-frequency timing framework, not replacing trend-following strategies.
Source report
Date: September 23, 2026 16:16:46 | Source: CFi.CN
Data indicates that the 20-day XGBoost timing model for Shanghai Silver achieved a directional accuracy of 62.50%, with an AUC of approximately 0.618. The net value of the long-short strategy reached 7.73, significantly outperforming the buy-and-hold net value of 4.68 over the same period.
The 5-day model recorded an accuracy of 60.19%. However, due to the sample period being within a long-term bull market, the fully invested long-short strategy underperformed both simple buy-and-hold and dual moving average strategies.
Key Findings from Recent Institutional Research
- The 20-day timing model still generates significant excess returns after accounting for transaction costs, indicating that medium-frequency signals are better suited to the current volatility characteristics of Shanghai Silver.
- The model does not aim for high-frequency capture. Instead, it integrates macroeconomic, price-volume, and event-driven factors to effectively filter short-term noise, providing reliable entry and exit signals during periods of strong trend continuity.
Practical Considerations for Traders
- High-confidence stratification improves per-trade win rates, but generates too few signals (only 12 trades over 20 days), limiting practical applicability.
- Under the default threshold, the 20-day strategy achieves a profit-to-loss ratio of 2.33, and when combined with position management, can effectively control drawdowns.
- For traders, the core value lies in offering a practical medium-frequency timing framework, rather than replacing trend-following strategies.
Source
中财网-行业新闻Eastern
Part of this Story
Shanghai Silver ML Timing Model Outperforms Buy-and-Hold with 62.5% Accuracy