Objective
The City of St. Louis needed a reliable way to identify, analyze, and visualize vacant and potentially vacant properties across the city. Existing property records were stored in a large Microsoft Access database that was poorly documented, inconsistently formatted, and difficult to analyze.
Researchers were developing predictive models to understand how property vacancy impacts surrounding property values. Both initiatives required transforming fragmented municipal data into a structured, scalable analytics platform capable of supporting urban planning, redevelopment, and public policy decisions.
Outcome
AspirationalX prototyped the initial transformation of complex and unreliable property datasets into a geospatial intelligence platform that enabled city stakeholders to identify vacant properties, prioritize redevelopment efforts, and support predictive property valuation models.
What began as a rapid weekend engagement evolved into a multi-year initiative that provided ongoing value to city planners, researchers, and community development organizations.
Challenge
The source data presented several significant challenges:
Poor Data Quality
Property records were stored in a legacy Microsoft Access database containing inconsistent formats, undocumented fields, and incomplete records.
Large-Scale Geospatial Analysis
The project involved analyzing approximately 250,000 property parcels and more than 25,000 vacant parcels throughout the city.
Predictive Modeling Requirements
Researchers required engineered geospatial features capable of quantifying the relationship between property values and nearby vacancy patterns.
Public Visualization
The city needed an intuitive way to visualize vacancy trends and communicate redevelopment priorities to stakeholders.
Solution
AspirationalX designed a geospatial data engineering and analytics workflow that transformed raw municipal property data into actionable insights.
The solution combined Alteryx, Tableau and feature engineering to support both operational decision-making and predictive analytics initiatives.
Key Interventions / Skills
Data Extraction and Cleansing
Our team extracted data from legacy municipal systems and developed ETL workflows using Alteryx to standardize, clean, and transform inconsistent property records into structured datasets suitable for analysis.
Geospatial Feature Engineering
To support predictive property valuation models, AspirationalX developed a proximity-based feature that calculated the relationship between individual parcels and surrounding vacant properties.
This feature enabled researchers to better quantify how vacancy influences neighborhood property values and improve model accuracy.
Vacancy Mapping and Visualization
Using Tableau and GIS techniques, our team created interactive maps that identified vacant and potentially vacant properties throughout the city.
These visualizations allowed stakeholders to quickly assess neighborhood conditions and prioritize intervention efforts.
Optimized Analytics Workflows
Alteryx workflows were engineered for fast iterative execution, allowing analysts to rapidly test assumptions, refine models, and process large geospatial datasets efficiently.
Results
Improved Redevelopment Prioritization
City stakeholders gained visibility into thousands of vacant and abandoned properties, helping prioritize demolition and redevelopment initiatives.
Enhanced Predictive Modeling
New geospatial features improved the ability to model the impact of vacancy on surrounding property values.
Accelerated Analysis
Optimized ETL and analytics workflows significantly reduced the time required to prepare and analyze complex municipal datasets.
Long-Term Strategic Value
What began as a rapid proof-of-concept evolved into a multi-year initiative that supported ongoing urban planning and property management efforts throughout St. Louis.
Conclusion
AspirationalX transformed fragmented municipal property records into a initial geospatial analytics platform that supported redevelopment planning, predictive modeling, and public-sector decision-making. By combining data engineering, GIS analysis, and visualization, our team helped create actionable intelligence that enabled more effective management of urban infrastructure and community development initiatives.