on this page

Measuring and Modeling the U.S. Regulatory Ecosystem

dataset

Large-scale empirical analysis of regulatory complexity using 165,000+ SEC filings to map the evolution of the U.S. regulatory landscape

period: 2017-present
tech:
Computational LawComplex Systems
GitHub
══════════════════════════════════════════════════════════════════

A groundbreaking research project analyzing the U.S. regulatory ecosystem through computational analysis of over 165,000 corporate annual reports (Form 10-Ks) filed with the SEC between 1993-2016.

Research Overview

This project conceptualizes the regulatory environment as an “ecosystem” where companies are “organisms” that must adapt to regulatory changes. By analyzing over 4.5 million references to U.S. Federal Acts and Agencies, the research provides empirical evidence for regulatory complexity trends.

Publication

  • Authors: Michael James Bommarito, Daniel Martin Katz
  • Published: Journal of Statistical Physics (August 2017)
  • Paper: Available on arXiv and SSRN

Methodology

Data Collection

  • Source: SEC EDGAR database via LexPredict
  • Scope: 34,000+ companies, 165,000+ Form 10-K filings
  • Timeline: 23 years (1993-2016)
  • Extracted: 4.5+ million regulatory references

Analysis Framework

  • “Regulatory bitstring” encoding for each company-year
  • Network analysis of regulatory similarities
  • Dimensionality and diversity measurements
  • Temporal evolution tracking

Key Findings

  1. Increasing Regulatory “Temperature”

    • Rise in regulatory energy per filing
    • Growing complexity over time

  2. Growing Ecosystem Diversity

    • Expanding dimensionality of regulatory space
    • Increasing distance between companies’ regulatory profiles

  3. Sector-Specific Patterns

    • Identification of regulatory “microclimates”
    • Industry-specific adaptation patterns

Technical Implementation

The project employs:

  • Natural Language Processing for reference extraction
  • Network visualization of regulatory relationships
  • Statistical modeling of ecosystem dynamics
  • Jupyter notebooks for reproducible analysis

Impact

This research:

  • Provides first large-scale empirical evidence for regulatory complexity claims
  • Establishes framework for measuring regulatory burden
  • Enables data-driven policy discussions
  • Demonstrates computational approaches to legal analysis

Broader Significance

“While individuals across the political, economic, and academic world frequently refer to trends in this regulatory ecosystem, far less attention has been paid to supporting such claims with large-scale, longitudinal data.” This project fills that gap with rigorous empirical analysis.

on this page