GIS/ValTech 2027

Most of us have interacted with Large Language Models (LLMs) like ChatGPT or Gemini through standard browser chat windows. However, this simple approach often leads to concerns about data privacy, security, and ongoing subscription costs. Furthermore, many of us have experienced model "hallucinations" or generic outputs that do not align with our specific appraisal processes, making AI results difficult to integrate safely into jurisdictional workflows.

This presentation addresses both of these critical issues. First, we will introduce a secure, open-source alternative: running powerful models locally on standard hardware using Hugging Face. This approach keeps your sensitive data entirely on-site and free from recurring API fees. Second, we will demystify how to use LangGraph to build structured, stateful workflows. Think of this as creating a custom map for your AI to follow. You will learn how to tightly control every step the model takes, dictate its actions after a decision is made, and choose exactly what tools (like local databases or calculators) it can access to aid its reasoning.

This session features an accessible introduction to these two open-source frameworks, followed by a step-by-step demonstration of a LangGraph agent facilitating daily efficiency in mass appraisal. Attendees will walk away with a practical understanding of local LLM's to help their offices start charting their own path and uncovering the hidden "rich stuff" in their data.


Keywords: Artificial Intelligence & Machine Learning, Mass Appraisal & Valuation Modeling, Advanced

Maricopa County built a spatial tool in ArcGIS Experience Builder for comparing parcel characteristics and attribute data on an interactive map. Including properties, neighborhoods, subdivisions, parcel class, improvement areas, and more. With a huge parcel count, it enables parcel-level review and catches data inconsistencies through custom queries and filters. We'll cover how it works, how it was built, and its growing role and reputation as an office-wide data quality tool.

Orleans Parish applied that same "see it differently" idea to appeals. We'll walk an appeal end to end from submission, staff review, valuation, decision, documentation, and taxpayer communication. Then showing how digital workflows, AI-assisted valuation, and virtual assistance make the process faster, more transparent, and more consistent, without losing professional judgment.

30-minutes: Concept to Clarity: Inside Maricopa County’s Supplementary Valuation Tool
Keywords: GIS & Spatial Analysis, Mass Appraisal & Valuation Modeling, Intermediate
Sarah Sharp, GIS Specialist, Maricopa County Assessor's Office - AZ

60-minutes: The Future of Assessment Appeals Is Now: AI, Automation & Analytics
Keywords: Assessment Appeals, Artificial Intelligence & Machine Learning, Beginner
Brent Ardeneaux, RES, AAS, Residential Sales Modeler/Sales Validation Supervisor, Orleans Parish Assessor’s Office, LA
David Barnett, MAI, SRA, CEO, GAR Associates LLC - NY
Russell Almaraz, RES, AAS, Residential Modeler, Orleans Parish Assessor’s Office, LA

This presentation examines the core assessment issues of uniformity, valuation, and taxpayer impact through an interactive mapping case study spanning ten years and 1.8 million parcels in Cook County, the second-largest assessment jurisdiction in the United States. The scale of the data presents significant analytical challenges, including outliers, classification complexities, and changing valuation patterns.

The study revisits the foundational work of Homer Hoyt, whose 1933 landmark analysis, starting in 1830, linked Chicago land values to race, rents, income, and urban growth. It also builds upon the research of Gabriel Ahlfeldt and Daniel McMillen, who documented how transportation, economic change, and neighborhood density influenced land values between 1913–2010.

By comparing Cook County land valuations from 2016–2025 with studies spanning 1830–2010, the presentation identifies major divergences in land-value patterns across centuries. It explores the practical implications of assessment policies and taxation shifts in Cook County, Illinois, the second-highest property tax jurisdiction in the nation with the highest tax delinquencies and increasing land-based appeals. Cook County’s 30 miles of Lake Michigan shoreline includes some of the most valuable urban and suburban land in the Midwest. Land value now represents an increasingly significant component of property assessment, creating new challenges for assessors, taxpayers, and assessment professionals.

The study leverages customized proprietary software, QGIS, and other GIS tools to analyze assessment characteristics, land values, and spatial patterns. We demonstrate why assessors, assessment and legal professionals should develop their own land valuation analysis, visualization tools, using open-source and in-house technologies.

Andrea Raila, Senior Tax Analyst, Raila & Associates - IL

Keywords: GIS & Spatial Analysis, Assessment Equity, Mass Appraisal & Valuation Modeling, Beginner