ABSTRACT

The Centre for Digital Humanities and Multilateralism invites you to "The Kitchen Series" a series of Friday seminars providing a collaborative forum to engage with researchers and their projects on the digitisation of data and the use of digitised archival resources. 

In this seminar, Pierre-Cyrille Hautcoeur and Angelo Riva will trace the origins and development of the Data for Financial History project. This project has gathered market data on securities listed on the Paris Stock Exchange between 1795 and 1973, as well as additional information on the issuers of these securities. They will highlight the constraints and opportunities encountered in the process of collecting, producing, and organizing these data.  

Then François Chahuneau and Thierry Puisseguir-Ripet will first go through the source document selection process to achieve best digital capture and data extraction versus quality and cost effort. They will also share their findings and thoughts illustrating the evolution from traditional OCR text extraction to innovative AI assisted data extraction methods for accurate financial data output. 

ABOUT THE SPEAKERS

• François Chahuneau is the former CTO of Numen and now a consultant for data extraction and AI engineering. With 25 years of experience, François Chahuneau is a recognised expert in the field of standards related to document management and data structuring, XML technologies, EDM, publishing, digitisation and OCR. He has worked with Thierry Puissegur-Ripet i on automated data extraction for large collections of documents including Stock Exchange Project in Paris in 2016. 

• Pierre-Cyrille Hautcoeur is professor of economics and economic history at the Ecole des hautes études en sciences sociales / Paris School of Economics. He was the principal investigator in various large research projects, especially Data for financial history (DFIH), which gathered data from the Paris stock exchange for 1800-1953. 

• Thierry Puissegur-Ripet is the former Head of Operations of Numen and now a digitization project architect expert. He has worked with François Chahuneau on automated data extraction for large collections of documents including Stock Exchange Project in Paris in 2016. 

• Angelo Riva is a Professor at INSEEC Grande Ecole and Director of Doctoral Development at the OMNES Research Center. He is also an Affiliate Researcher at the Paris School of Economics and an Academic Fellow at the Institut Louis Bachelier. An economist and historian, his research explores the transitions of financial systems across historical periods. His work also contributes to the digital and organizational development of research through the construction of financial data infrastructures. Angelo has led and participated in numerous interdisciplinary research initiatives such as the “Data for Financial History”, the H2020 project “European Historical Firms. Long-Term Data for Europe” and the ANR project “Systemic Risk in the 1930s”.