It is available the submissions for a special issue of the Economic History Yearbook on the application of machine learning and big data in economic history. Our focus is on papers that use large historical datasets – structured or unstructured – starting at around 10,000 observations. While not big data in the conventional sense, the construction of such datasets has become feasible in recent years, presenting new opportunities for the study of economic history. Yet, this data revolution also creates new analytical and methodological challenges making it essential to disseminate these new techniques.

They are particularly welcome papers employing machine learning techniques to explore historical data, with a special emphasis on studies using Large Language Models (LLMs). However, other machine learning methods are also welcome. Contributions should critically assess their potential and limitations in economic history. However, the primary focus remains on empirical applications, rather than methodological or purely theoretical discussions.

Topics of interest include, but are not limited to:

• Machine learning approaches to historical text and numerical data
• The role of LLMs in the analysis of historical data
• Challenges and solutions in applying artificial intelligence (AI) to economic history
• Case studies demonstrating the empirical value of machine learning in economic history

Roadmap:

• First drafts due: December 2025
• Authors’ workshop: February/March 2026 at the University of Hohenheim (we can cover accommodation and travel expenses)
• Final drafts due: June 2026

Economic History Yearbook encourages submissions from researchers in economic history, economics, computer sciences, digital humanities, and related fields.

For inquiries and submissions, please contact: Felix Selgert (fselgert@uni-bonn.de)