Change default IQR multiplier to 1.0 for more aggressive outlier filtering

- Change ANALYSIS_IQR_MULTIPLIER default from 1.5 to 1.0 in config.py
- Add iqr_multiplier parameter to all filtering & statistics functions
- Allow runtime override via MCP tools (get_valuation_comparables, get_deal_statistics)
- Update CLAUDE.md docs with new default & override examples

Rationale: k=1.0 catches more suspicious deals (e.g. 43% below median) while
still preserving legitimate edge cases via hard bounds. Users can override
per-call for more conservative filtering (k=1.5) if needed.

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

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

CLAUDE.md

@@ -252,7 +252,7 @@ The MCP now includes configurable outlier detection and robust statistical measu
 ```bash
 # Outlier Detection Strategy
 ANALYSIS_OUTLIER_METHOD=iqr          # Options: iqr, percent, none (default: iqr)
-ANALYSIS_IQR_MULTIPLIER=1.5          # 1.5=moderate, 3.0=conservative (default: 1.5)
+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)
 
 # Hard Bounds (catches obvious data errors)
@@ -273,10 +273,14 @@ ANALYSIS_INCLUDE_UNFILTERED_STATS=true  # Report both filtered/unfiltered (defau
 from nadlan_mcp.govmap.statistics import calculate_deal_statistics
 from nadlan_mcp.config import GovmapConfig
 
-# With outlier filtering (default behavior)
+# With outlier filtering (default behavior, k=1.0)
 config = GovmapConfig()  # Uses env vars or defaults
 stats = calculate_deal_statistics(deals, config)
 
+# Override IQR multiplier for more/less aggressive filtering
+stats = calculate_deal_statistics(deals, config, iqr_multiplier=1.5)  # More conservative
+stats = calculate_deal_statistics(deals, config, iqr_multiplier=0.5)  # More aggressive
+
 # Access filtered statistics (main results after outlier removal)
 filtered_mean = stats.filtered_price_per_sqm_statistics["mean"]
 filtered_median = stats.filtered_price_per_sqm_statistics["median"]
@@ -292,10 +296,10 @@ original_mean = stats.price_per_sqm_statistics["mean"]
 ```
 
 **Design Principles:**
-- **Enabled by default**: Moderate filtering (k=1.5) to catch common errors
+- **Enabled by default**: Aggressive filtering (k=1.0) to catch common errors & suspicious deals
 - **Transparent**: Both filtered and unfiltered statistics returned
 - **Conservative with real data**: Hard bounds + IQR preserve legitimate high-end properties
-- **Configurable**: Adjust sensitivity via environment variables
+- **Configurable**: Adjust sensitivity via environment variables or function parameters
 - **MCP provides data, LLM provides intelligence**: Outlier detection improves data quality; LLM interprets results
 
 ### Retry Logic

nadlan_mcp/config.py

@@ -61,7 +61,7 @@ class GovmapConfig:
         default_factory=lambda: os.getenv("ANALYSIS_OUTLIER_METHOD", "iqr")
     )
     analysis_iqr_multiplier: float = field(
-        default_factory=lambda: float(os.getenv("ANALYSIS_IQR_MULTIPLIER", "1.5"))
+        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"))

nadlan_mcp/fastmcp_server.py

@@ -772,11 +772,12 @@ def get_valuation_comparables(
     max_floor: Optional[int] = None,
     radius_meters: int = 100,
     max_comparables: int = 50,
+    iqr_multiplier: Optional[float] = None,
 ) -> str:
     """Get comparable properties for valuation analysis.
 
     This tool provides detailed comparable deals filtered by your criteria.
-    Automatically applies IQR outlier filtering (k=1.5) to remove statistical outliers
+    Automatically applies IQR outlier filtering (k=1.0 default) to remove statistical outliers
     and improve data quality. The response includes metadata about filtering so you can
     inform users about removed outliers.
 
@@ -794,6 +795,7 @@ def get_valuation_comparables(
         max_floor: Maximum floor number
         radius_meters: Search radius in meters (default: 100, larger than find_recent_deals to get more comparables)
         max_comparables: Maximum number of deals to return (default: 50, optimized for MCP token limits)
+        iqr_multiplier: Override IQR multiplier for outlier detection (default: 1.0). Lower = more aggressive filtering
 
     Returns:
         JSON string containing:
@@ -803,7 +805,7 @@ def get_valuation_comparables(
           - total_deals_before_filtering: Count before filtering
           - outliers_removed: Number of deals filtered out
           - filtering_method: Method used (e.g., "iqr")
-          - iqr_multiplier: IQR multiplier used (e.g., 1.5)
+          - iqr_multiplier: IQR multiplier used (e.g., 1.0)
     """
     log_mcp_call(
         "get_valuation_comparables",
@@ -820,6 +822,7 @@ def get_valuation_comparables(
         max_floor=max_floor,
         radius_meters=radius_meters,
         max_comparables=max_comparables,
+        iqr_multiplier=iqr_multiplier,
     )
     try:
         # Get all deals for the address with higher limits for valuation
@@ -876,10 +879,13 @@ def get_valuation_comparables(
         ):
             deals_before_outlier_filter = len(filtered_deals)
             filtered_deals, outlier_report = filter_deals_for_analysis(
-                filtered_deals, config, metric="price_per_sqm"
+                filtered_deals, config, metric="price_per_sqm", iqr_multiplier=iqr_multiplier
+            )
+            effective_k = (
+                iqr_multiplier if iqr_multiplier is not None else config.analysis_iqr_multiplier
             )
             logger.info(
-                f"After outlier filtering ({config.analysis_outlier_method}, k={config.analysis_iqr_multiplier}): "
+                f"After outlier filtering ({config.analysis_outlier_method}, k={effective_k}): "
                 f"{len(filtered_deals)} deals (removed {deals_before_outlier_filter - len(filtered_deals)} outliers)"
             )
         else:
@@ -946,6 +952,7 @@ def get_deal_statistics(
     property_type: Optional[str] = None,
     min_rooms: Optional[float] = None,
     max_rooms: Optional[float] = None,
+    iqr_multiplier: Optional[float] = None,
 ) -> str:
     """Calculate statistical aggregations on deal data for an address.
 
@@ -958,6 +965,7 @@ def get_deal_statistics(
         property_type: Filter by property type (e.g., "דירה", "בית")
         min_rooms: Minimum number of rooms
         max_rooms: Maximum number of rooms
+        iqr_multiplier: Override IQR multiplier for outlier detection (default: 1.0). Lower = more aggressive filtering
 
     Returns:
         JSON string containing statistical metrics (mean, median, percentiles, etc.)
@@ -969,6 +977,7 @@ def get_deal_statistics(
         property_type=property_type,
         min_rooms=min_rooms,
         max_rooms=max_rooms,
+        iqr_multiplier=iqr_multiplier,
     )
     try:
         # Get all deals for the address
@@ -998,7 +1007,7 @@ def get_deal_statistics(
             )
 
         # Calculate statistics
-        stats = client.calculate_deal_statistics(deals)
+        stats = client.calculate_deal_statistics(deals, iqr_multiplier=iqr_multiplier)
 
         # Normalize response structure to match other tools
         return json.dumps(

nadlan_mcp/govmap/client.py

@@ -873,7 +873,9 @@ class GovmapClient:
         )
 
     # Statistics methods (delegate to statistics module)
-    def calculate_deal_statistics(self, deals: List[Deal]) -> DealStatistics:
+    def calculate_deal_statistics(
+        self, deals: List[Deal], iqr_multiplier: Optional[float] = None
+    ) -> DealStatistics:
         """
         Calculate statistical aggregations on deal data.
 
@@ -881,11 +883,12 @@ class GovmapClient:
 
         Args:
             deals: List of Deal model instances
+            iqr_multiplier: Override IQR multiplier for outlier detection (optional)
 
         Returns:
             DealStatistics model with comprehensive metrics
         """
-        return statistics.calculate_deal_statistics(deals)
+        return statistics.calculate_deal_statistics(deals, iqr_multiplier=iqr_multiplier)
 
     def _calculate_std_dev(self, values: List[float]) -> float:
         """

nadlan_mcp/govmap/outlier_detection.py

@@ -173,7 +173,10 @@ def apply_hard_bounds_deal_amount(
 
 
 def filter_deals_for_analysis(
-    deals: List[Deal], config: Optional[GovmapConfig] = None, metric: str = "price_per_sqm"
+    deals: List[Deal],
+    config: Optional[GovmapConfig] = None,
+    metric: str = "price_per_sqm",
+    iqr_multiplier: Optional[float] = None,
 ) -> Tuple[List[Deal], Dict[str, Any]]:
     """
     Filter deals to remove outliers based on configuration.
@@ -192,6 +195,7 @@ def filter_deals_for_analysis(
         config: Configuration object (optional, uses global if not provided)
         metric: Which metric to apply statistical outlier detection to
                 Options: "price_per_sqm", "deal_amount"
+        iqr_multiplier: Override IQR multiplier (optional, uses config value if not provided)
 
     Returns:
         Tuple of:
@@ -239,6 +243,11 @@ def filter_deals_for_analysis(
             filters_to_remove[i] = True
 
     # Step 3: Apply statistical outlier detection to specified metric
+    # Use override value if provided, otherwise use config
+    effective_iqr_multiplier = (
+        iqr_multiplier if iqr_multiplier is not None else config.analysis_iqr_multiplier
+    )
+
     if config.analysis_outlier_method == "iqr":
         # Extract values for the specified metric
         if metric == "price_per_sqm":
@@ -260,7 +269,7 @@ def filter_deals_for_analysis(
             value_indices = []
 
         if values:
-            statistical_outliers = detect_outliers_iqr(values, config.analysis_iqr_multiplier)
+            statistical_outliers = detect_outliers_iqr(values, effective_iqr_multiplier)
             for i, is_outlier in enumerate(statistical_outliers):
                 if is_outlier:
                     filters_to_remove[value_indices[i]] = True
@@ -302,7 +311,7 @@ def filter_deals_for_analysis(
         "outlier_indices": outlier_indices,
         "method_used": config.analysis_outlier_method,
         "parameters": {
-            "iqr_multiplier": config.analysis_iqr_multiplier
+            "iqr_multiplier": effective_iqr_multiplier
             if config.analysis_outlier_method == "iqr"
             else None,
             "metric": metric,

nadlan_mcp/govmap/statistics.py

@@ -152,7 +152,7 @@ def _calculate_basic_stats(deals: List[Deal]) -> Dict:
 
 
 def calculate_deal_statistics(
-    deals: List[Deal], config: Optional[GovmapConfig] = None
+    deals: List[Deal], config: Optional[GovmapConfig] = None, iqr_multiplier: Optional[float] = None
 ) -> DealStatistics:
     """
     Calculate statistical aggregations on deal data with optional outlier filtering.
@@ -164,6 +164,7 @@ def calculate_deal_statistics(
     Args:
         deals: List of Deal model instances
         config: Configuration object (optional, uses global config if not provided)
+        iqr_multiplier: Override IQR multiplier (optional, uses config value if not provided)
 
     Returns:
         DealStatistics model with comprehensive metrics, including:
@@ -203,7 +204,7 @@ def calculate_deal_statistics(
     ):
         # Filter deals for analysis (primarily targeting price_per_sqm outliers)
         filtered_deals, report_dict = filter_deals_for_analysis(
-            deals, config, metric="price_per_sqm"
+            deals, config, metric="price_per_sqm", iqr_multiplier=iqr_multiplier
         )
 
         # Create OutlierReport model