Tax Code Analysis Tool 1.0

Applying Machine Learning to Map the Tax Code

Carter C. Price, Leonardo Bueno, Kara Jia, Minju Jo, Sabahat Zafar, George Zuo

ToolPublished Mar 19, 2026

Given the complexity of the federal tax code, it is challenging to determine how changes in one section might affect other areas. The authors created the Tax Code Analysis Tool (CAT) to analyze the U.S. tax code as a graph structure to more naturally explore connections. CAT links the text of Title 26 of the U.S. Code to the entities and concepts it covers. Title 26 specifies the income taxes for individuals and businesses and has more than 1,900 sections. This complexity makes it a natural target for modern text analysis methods, including large language models.

CAT describes the relationships between different parts of the federal tax law (e.g., a chapter, section, subsection), the entities those parts relate to, and the relevant concepts included in the part as a network. Further, by layering in additional data sources, the tool can provide useful information to researchers and policymakers.

CAT currently has four main capabilities, with additions planned: (1) Identify the sections that reference or are referenced in a section; (2) identify the sections that relate to some concept, entity, or topic; (3) assess the complexity of the tax code from the perspective of different types of entities; and (4) connect the text of Title 26 to data from the IRS to determine the fiscal implications of specific provisions and the connections to those provisions.

Topics

Document Details

Citation

Chicago Manual of Style

Price, Carter C., Leonardo Bueno, Kara Jia, Minju Jo, Sabahat Zafar, and George Zuo, Tax Code Analysis Tool 1.0: Applying Machine Learning to Map the Tax Code. Santa Monica, CA: RAND Corporation, 2026. https://www.rand.org/pubs/tools/TLA4392-1.html.
BibTeX RIS

Research conducted by

This work was supported by the Diller-von Furstenberg Family Foundation and Pershing Square Philanthropies and conducted by the RAND von Furstenberg Family Budget Model Initiative within RAND Education, Employment, and Infrastructure.

This publication is part of the RAND tool series. RAND tools include models, databases, calculators, computer code, GIS mapping tools, practitioner guidelines, web applications, and various other toolkits and applied research products. All RAND tools undergo rigorous peer review to ensure both high data standards and appropriate methodology in keeping with RAND's commitment to quality and objectivity.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.

Version Note

This publication supersedes a previous version published in 2025 (WR-A4129-1).