Fix: Lower outlier detection threshold from 10 to 5 deals

**Problem:** Outlier detection was skipped for 9-deal datasets due to
threshold=10, allowing extreme outliers (₪920K vs ₪1.75M median) to
skew valuation results.

**Root Cause:** Real-world filtered queries (e.g., 3 rooms, ~60m²)
often yield 5-9 comparables. Small samples NEED outlier filtering more
than large ones (one outlier = 11-20% of dataset).

**Solution:** Lower ANALYSIS_MIN_DEALS_FOR_OUTLIER_DETECTION: 10 → 5

**Impact:**
- IQR & percentage methods valid with 5+ deals
- Real estate valuation uses 5-10 comparables standard
- Verified: 9-deal test now removes 2 outliers correctly

**Changes:**
- nadlan_mcp/config.py: Default threshold 10 → 5
- CLAUDE.md: Updated config documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

CLAUDE.md

@@ -345,7 +345,7 @@ The MCP now includes configurable outlier detection and robust statistical measu
 # Outlier Detection Strategy
 ANALYSIS_OUTLIER_METHOD=iqr          # Options: iqr, percent, none (default: iqr)
 ANALYSIS_IQR_MULTIPLIER=1.0          # 1.0=aggressive, 1.5=moderate, 3.0=conservative (default: 1.0)
-ANALYSIS_MIN_DEALS_FOR_OUTLIER_DETECTION=10  # Minimum deals needed (default: 10)
+ANALYSIS_MIN_DEALS_FOR_OUTLIER_DETECTION=5  # Minimum deals needed (default: 5)
 
 # Percentage-based Backup Filtering (catches extreme outliers in heterogeneous data)
 ANALYSIS_USE_PERCENTAGE_BACKUP=true  # Enable percentage backup (default: true)

nadlan_mcp/config.py

@@ -64,7 +64,7 @@ class GovmapConfig:
         default_factory=lambda: float(os.getenv("ANALYSIS_IQR_MULTIPLIER", "1.0"))
     )
     analysis_min_deals_for_outlier_detection: int = field(
-        default_factory=lambda: int(os.getenv("ANALYSIS_MIN_DEALS_FOR_OUTLIER_DETECTION", "10"))
+        default_factory=lambda: int(os.getenv("ANALYSIS_MIN_DEALS_FOR_OUTLIER_DETECTION", "5"))
     )
 
     # Percentage-based backup filtering (catches extreme outliers in heterogeneous data)