Senior Housing Demographics & Care Demand Analyzer with Google ADK
Senior housing operators face a trillion-dollar expansion requirement driven by aging demographic demand. Build an agentic geospatial platform using Google Agent Development Kit (ADK) and Gemini on Vertex AI to evaluate senior housing expansion locations with 90% demand forecasting accuracy.
What you are building
The core problem, expected build, and operating context for this challenge.
Implement a Google ADK multi-agent pipeline with Gemini 1.5 Pro to query demographic trends and healthcare facility proximity for senior housing site selection.
How work is evaluated
Evaluates Google ADK site suitability scores and senior bed deficit calculations for targeted metropolitan markets.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Recommended Care Type Accuracy
Ensures appropriate care facility type is recommended based on income and age profile.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
suitability_score_mae
Mean Absolute Error of suitability score compared to market ground truth • target: 3 • range: 0-100
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build a Google ADK agent utilizing Gemini 1.5 Pro for multimodal census map and demographic parsing.
Integrate geospatial search tools for assessing proximity to tertiary hospital networks.
Compute projected senior bed penetration rates and 5-year care demand spikes.
Generate site suitability scores for institutional senior housing development.
Reference links and supporting material
Dataset of 50 US Metropolitan Statistical Areas (MSAs) containing senior demographics (75+ population), existing licensed bed inventory, median senior incomes, and healthcare proximity markers.
Challenge setup
Evaluates Google ADK site suitability scores and senior bed deficit calculations for targeted metropolitan markets.
Challenge input
JSON containing msa_name, pop_over_75, existing_licensed_beds, median_household_income_75plus, and hospital_distance_miles
Google ADK
Mandatory Google framework for building Gemini-powered agents.
Evaluated output
JSON with bed_deficit, projected_occupancy_rate, suitability_score (0-100), and recommended_care_type
- Ensures appropriate care facility type is recommended based on income and age profile.
- Mean Absolute Error of suitability score compared to market ground truth • target: 3 • range: 0-100
- Benchmark: Geospatial Demand Allocation Benchmark
- Suitability Score Mae target: 3
- 1 public reference case
- 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
- Google · Required
- Google ADK · Optional
- Google Gemini · Optional
Evaluation contract
- Recommended Care Type Accuracy · Weight 1
- suitability_score_mae · Weight 1
Metrics
- suitability_score_mae · Target 3
Benchmarks
- Geospatial Demand Allocation Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing msa_name, pop_over_75, existing_licensed_beds, median_household_income_75plus, and hospital_distance_miles
Output: JSON with bed_deficit, projected_occupancy_rate, suitability_score (0-100), and recommended_care_type
Execution harness: Python
Evaluation tools
- Google ADK · Agent Development Framework
Recipe freeze marker
No recipe freeze time is recorded.