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.
What you are building
Develop a geospatial site selection agent using Google Agent Development Kit (ADK) and Gemini 1.5 Pro multimodal and long-context APIs.
How work is evaluated
Evaluates accuracy of senior housing bed-demand scoring models across suburban Metropolitan Statistical Areas (MSAs).
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
priority_tier_assignment
Markets with score >= 80 must be marked Tier 1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
scoring_precision
Correlation with benchmark demographic suitability rankings • target: 0.94 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
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
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
- Markets with score >= 80 must be marked Tier 1
- Correlation with benchmark demographic suitability rankings • target: 0.94 • range: 0-1
- Benchmark: ADK-Location-Bench
- Scoring Precision target: 0.94
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
- 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
- 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.