Upload README.md with huggingface_hub

README.md

@@ -34,27 +34,27 @@ metrics:
   - cagr
   - win_rate
 model-index:
-  - name: romeo-v5-daily
+  - name: romeo-v6-15m
     results:
       - task:
           type: binary-classification
-          name: Daily Price Direction Prediction
+          name: 15-Minute Price Direction Prediction
         dataset:
           type: yahoo-finance-gc-f
           name: Gold Futures (GC=F)
         metrics:
           - type: accuracy
-            value: 49.47
+            value: 49.28
             name: Win Rate
           - type: sharpe
-            value: 0.3119
-            name: Sharpe Ratio
+            value: 0.0
+            name: Sharpe Ratio (N/A for simple metrics)
           - type: max_drawdown
-            value: -47.66
-            name: Max Drawdown (%)
+            value: 0.0
+            name: Max Drawdown (N/A for simple metrics)
           - type: cagr
-            value: 0.0444
-            name: CAGR
+            value: 0.0
+            name: CAGR (N/A for simple metrics)
 ---
 
 # Romeo V6 — High-Risk Ensemble Trading Model for XAUUSD
@@ -91,15 +91,12 @@ Romeo V6 is a high-risk ensemble machine learning model designed for predicting
 ### Metrics
 - **Evaluation Data**: Unseen 15m intraday data (out-of-sample).
 - **Metrics**:
-  - Initial Capital: 500
-  - Final Capital: 884.82
-  - CAGR: 0.0158
-  - Annual Volatility: 0.5980
-  - Sharpe Ratio: 0.3258
-  - Max Drawdown: -48.24%
-  - Total Trades: 3610
-  - Win Rate: 49.47%
-  - Avg PnL per Trade: 0.1066
+  - Initial Capital: 100
+  - Final Capital: 162.31
+  - Total Return: 62.31%
+  - Total Trades: 207
+  - Win Rate: 49.28%
+  - Avg PnL per Trade: 0.3010
 
 ### Training Data
 - **Source**: Yahoo Finance (GC=F) historical data.
@@ -107,7 +104,9 @@ Romeo V6 is a high-risk ensemble machine learning model designed for predicting
 - **Split**: Trained on historical data; evaluated on unseen fresh dataset.
 
 ### Quantitative Analyses
-- **Robustness Scan**: Coarse grid sweep (slippage: 0-1 pips, commission: 0-0.0005, threshold: 0.5-0.6). Best scenarios: low friction, threshold ~0.5. Worst: high commission/threshold.
+- **Robustness Scan**: Tested under normal conditions (commission 0.02%, slippage 0.5 pips) and difficult market conditions (commission 0.05%, slippage 1.0 pips).
+  - Normal: Win Rate 50.51%, Return 62.80%, Trades 198.
+  - Difficult: Win Rate 31.82%, Return -16.38%, Trades 198.
 - **M2M Equity**: Per-bar mark-to-market equity calculation for accurate risk metrics.
 
 ### Ethical Considerations