Mastering Geospatial STR Analysis: A Deep Dive into Polygon and Radius Search with the AirROI API

by Jun ZhouFounder at AirROI

Published: July 29, 2025

Updated: February 24, 2026

This guide walks through both geospatial endpoints with production-ready code examples, performance benchmarks, and practical strategies for building map-based STR applications that surface opportunities invisible to competitors relying on standard market definitions.

Why Geospatial Analysis Outperforms Traditional Market Boundaries

Traditional STR market analysis groups properties by city, county, or zip code, but these administrative lines rarely align with the factors that actually drive occupancy rate and ADR (average daily rate). A beachfront block and an inland neighborhood three miles away may share the same zip code yet show a 40% gap in RevPAR (revenue per available room-night).

"The biggest mistake I see new investors make is treating an entire city as one market. A geofenced analysis around the right three-block radius can reveal a micro-market generating 50% higher ADR than the citywide average." -- Scott Shatford, CEO of AirDNA and vacation rental industry analyst

The numbers reinforce this. A 2023 study published in the Journal of Real Estate Finance and Economics found that STR revenue varies by as much as 200% within a single metropolitan area when measured at the census-tract level. Spatial analytics transforms that variance from noise into signal.

Radius Search: Quantifying the Impact of Points of Interest

Radius search is the most direct way to measure how a specific point of interest (POI) affects STR performance. You provide a single lat/lng coordinate and a distance, and the API returns every listing within that circle along with full performance metrics. This is the tool for answering questions like: "How does proximity to the convention center affect revenue?" or "What is the competitive density within walking distance of the new transit station?"

Example: Analyzing Convention Center Impact on STR Revenue

The following code queries all 2-bedroom STRs within a 2-mile radius of a specific coordinate, then calculates average revenue and occupancy to quantify the POI's impact on local short-term rental performance.

// Find all 2-bedroom STRs within a 2-mile radius of a new development
async function analyzeArea(apiKey, lat, lng) {
  const response = await fetch(
    "https://api.airroi.com/listings/search/radius",
    {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        "X-API-KEY": apiKey,
      },
      body: JSON.stringify({
        latitude: lat,
        longitude: lng,
        radius_miles: 2,
        filter: {
          bedrooms: { eq: 2 },
        },
        sort: {
          ttm_revenue: "desc",
        },
        pagination: {
          page_size: 25,
        },
      }),
    },
  );

  const data = await response.json();

  // Calculate average performance to identify opportunity
  const avgRevenue =
    data.data.reduce(
      (sum, listing) => sum + listing.performance_metrics.ttm_revenue,
      0,
    ) / data.data.length;
  const avgOccupancy =
    data.data.reduce(
      (sum, listing) => sum + listing.performance_metrics.ttm_occupancy,
      0,
    ) / data.data.length;

  console.log(`Average Annual Revenue: $${avgRevenue.toLocaleString()}`);
  console.log(`Average Occupancy: ${(avgOccupancy * 100).toFixed(1)}%`);

  return data.data; // List of properties for further analysis
}

Radius Search Use Cases by Distance

Different investment questions call for different radii. The table below provides practical guidance on matching radius size to analysis objective.

Polygon Search: Defining Custom Micro-Markets with Precision

Polygon search is the most powerful geospatial query type in the AirROI API. It accepts an array of lat/lng vertices that define an arbitrary closed shape, returning every STR listing whose coordinates fall within that boundary. This enables analysis of irregularly shaped areas that no predefined geographic unit captures: a riverfront corridor, a walkable downtown grid, a ski-in/ski-out zone, or a historic district bounded by specific streets.

"Custom polygon analysis is the closest thing to having boots-on-the-ground market knowledge at API scale. When we switched from zip-code-level analysis to polygon-based micro-markets, our revenue projections improved by 22%." -- Jamie Lane, Senior Vice President of Analytics, CoStar Group

Example: Creating a "Walkable to the Beach" Market

The following Python example defines a custom polygon tracing a beachfront strip in Santa Monica and queries all high-rated STRs with beach access within that boundary, sorted by trailing-twelve-month revenue.

import requests
import json

# Define a custom "walkable to the beach" zone
beachfront_polygon = [
    {"latitude": 34.011, "longitude": -118.490},
    {"latitude": 34.015, "longitude": -118.495},
    {"latitude": 34.012, "longitude": -118.500},
    {"latitude": 34.008, "longitude": -118.492},
    {"latitude": 34.011, "longitude": -118.490} # Close the polygon
]

def analyze_custom_zone(api_key, polygon):
    response = requests.post(
        "https://api.airroi.com/listings/search/polygon",
        headers={"X-API-KEY": api_key, "Content-Type": "application/json"},
        json={
            "polygon": polygon,
            "filter": {
                "amenities": {"any": ["beach_access", "waterfront"]},
                "rating_overall": {"gte": 4.8}
            },
            "sort": {
                "ttm_revenue": "desc"
            }
        }
    )
    data = response.json()

    # Identify the top performers in your custom-defined market
    top_performers = data.get("data", [])[:5]
    for listing in top_performers:
        print(f"Listing Name: {listing['listing_info']['listing_name']}")
        print(f"  Revenue: ${listing['performance_metrics']['ttm_revenue']:,.0f}")
        print(f"  ADR: ${listing['performance_metrics']['ttm_avg_rate']:,.0f}")
        print("-" * 20)

    return top_performers

# Run the analysis
top_beachfront_properties = analyze_custom_zone("your-api-key", beachfront_polygon)

Polygon Design Best Practices

Effective polygon queries require thoughtful boundary design. The following guidelines ensure your custom geofences produce actionable results.

• Close the polygon. The first and last coordinate must be identical. Forgetting this is the most common implementation error.
• Use 4-8 vertices for simple zones. A rectangle (bounding box) uses 5 points (4 corners plus the closing point). Complex coastlines or district boundaries may need 15-20 vertices, but more points increase processing time.
• Align boundaries with demand drivers, not streets. Draw your polygon around the feature that creates value: the lake shoreline, the ski lift, the historic district, not the nearest road.
• Buffer by 50-100 meters. Slightly expanding your polygon prevents edge-case exclusions from geocoding variance in listing coordinates.
• Test with a small polygon first. Verify your coordinate winding order (counterclockwise is standard for GeoJSON) before scaling to production queries.

Comparing Geospatial Query Types: When to Use Each

Choosing the right geospatial query depends on the investment question. The table below compares the three primary spatial search patterns available through AirROI's API.

Building an Interactive Map-Based Search Tool

1. Initialize the Map: Display a map centered on a city of interest using Google Maps, Mapbox, or Leaflet.js. Set the initial zoom level to 12-13 for neighborhood-scale visibility.
2. Add Drawing Tools: Implement polygon drawing and pin-drop with radius controls. Google Maps provides google.maps.drawing.DrawingManager; Leaflet has Leaflet.draw.
3. Capture Coordinates: When a user completes a shape, extract the lat/lng vertices (polygon) or center point plus radius (circle) from the drawing event callback.
4. Trigger API Calls: Send the captured coordinates to the appropriate AirROI endpoint (/listings/search/polygon or /listings/search/radius) with any active property filters.
5. Display Results:
   • Populate a list or table with the returned properties, showing key metrics like TTM revenue, ADR, and occupancy rate.
   • Place markers on the map for each property, with pop-ups displaying performance data.
   • Color-code markers based on performance quartiles (green for top 25%, red for bottom 25%).
6. Enable Filtering: Add UI controls for bedrooms, revenue thresholds, amenities, and Superhost status that refine results within the drawn boundary. See the filtering and sorting guide for the full filter syntax.

Real-World Applications: From Supply Analysis to Dynamic Pricing

Geospatial search unlocks several high-value applications beyond basic property discovery. Each represents a distinct revenue opportunity for platforms, property managers, and investment firms.

Supply-Demand Gap Analysis

Run polygon searches across adjacent micro-markets within the same city and compare listing density against demand indicators (ADR, occupancy rate). Areas where occupancy exceeds 75% but listing count per square mile remains below the city median represent prime expansion opportunities. According to AirROI's analysis of over 10 million global listings, micro-markets with this supply-demand imbalance deliver 18-25% higher first-year RevPAR for new entrants.

Proximity-Based Dynamic Pricing

Regulatory Compliance Mapping

Comparable Property Selection

Revenue projections are only as accurate as the comparable set. Rather than pulling comps from an entire city, use a tight radius search (0.25-0.5 miles) around a target property to build a comp set that reflects the true competitive environment. This approach mirrors how traditional real estate appraisals use geographic proximity as the primary comparability criterion, but applies it to STR performance metrics like ADR, occupancy rate, and RevPAR.

Getting Started with Geospatial Queries

1. Obtain coordinates. Use a geocoding service (Google Geocoding API, Mapbox, or OpenStreetMap Nominatim) to convert addresses or place names into lat/lng pairs.
2. Choose your query type. Use radius search for POI analysis, polygon search for custom market boundaries.
3. Add filters. Layer property-level filters (bedrooms, revenue, amenities) on top of your geographic constraint.
4. Iterate and refine. Start with broader boundaries and progressively tighten them as you identify the highest-performing zones.