diff --git a/CLAUDE.md b/CLAUDE.md
index cec08b2..9162bcd 100644
--- a/CLAUDE.md
+++ b/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)
diff --git a/nadlan_mcp/config.py b/nadlan_mcp/config.py
index 0e08e3a..17ec72a 100644
--- a/nadlan_mcp/config.py
+++ b/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)