Skip to main content
Back to challenges
Challenge

Senior Housing Demographic & Site Selection Agent with Google ADK

Expanding senior housing operators must evaluate local healthcare access and senior population growth vectors. Build a Google ADK agent leveraging Gemini 1.5 Pro to process geospatial census data and construction cost indexes into ranked site recommendations.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop a geospatial site selection agent using Google Agent Development Kit (ADK) and Gemini 1.5 Pro multimodal and long-context APIs.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of senior housing bed-demand scoring models across suburban Metropolitan Statistical Areas (MSAs).

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

priority_tier_assignment

Markets with score >= 80 must be marked Tier 1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

scoring_precision

Correlation with benchmark demographic suitability rankings • target: 0.94 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Build a Google ADK agent integrated with Vertex AI and Gemini 1.5 Pro.

  • Ingest demographic time-series data (age 75+ growth rates) and hospital proximity vectors.

  • Execute structured site scoring models combining bed-demand metrics and construction costs.

  • Output ranked geographical target markets with complete analytical provenance.

Resources and assets

Reference links and supporting material

Dataset notes

US Census demographic projections for 65+ age groups across 30 MSAs with hospital location coordinates and existing bed inventory.

Challenge setup

Evaluates accuracy of senior housing bed-demand scoring models across suburban Metropolitan Statistical Areas (MSAs).

Challenge input

JSON containing msa_code, pop_over_75_growth, hospital_distance_miles, bed_supply_gap

Google ADK

Framework assignment for Google Cloud AI agent deployment.

Evaluated output

JSON with market_score, priority_tier, recommended_bed_count

Evaluation checks
  • Markets with score >= 80 must be marked Tier 1
  • Correlation with benchmark demographic suitability rankings • target: 0.94 • range: 0-1
Configured evaluation evidence
  • Benchmark: ADK-Location-Bench
  • Scoring Precision target: 0.94
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Google ADK · Required
  • Google · Optional
  • Google Gemini · Optional

Evaluation contract

  • priority_tier_assignment · Weight 1
  • scoring_precision · Weight 1

Metrics

  • scoring_precision · Target 0.94

Benchmarks

  • ADK-Location-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing msa_code, pop_over_75_growth, hospital_distance_miles, bed_supply_gap

    Output: JSON with market_score, priority_tier, recommended_bed_count

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Senior Housing Demographic & Site Selection Agent with Google ADK