eprintid: 50295 rev_number: 10 eprint_status: archive userid: 1482 importid: 105 dir: disk0/00/05/02/95 datestamp: 2025-02-14 13:39:10 lastmod: 2025-03-14 12:40:59 status_changed: 2025-03-14 12:40:59 type: article metadata_visibility: show creators_name: Koch, Philipp creators_name: Stojkoski, Viktor creators_name: Hidalgo, Cesar Augusto creators_id: philipp.koch@ecoaustria.ac.at creators_id: cesar.hidalgo@tse-fr.eu creators_idrefppn: 274021951 creators_idrefppn: 283419385 creators_idrefppn: 187385661 creators_halaffid: 506116 creators_halaffid: 506116 creators_halaffid: 506116; 1002422 title: Augmenting the availability of historical GDP per capita estimates through machine learning ispublished: pub subjects: subjects_ECO abstract: Can we use data on the biographies of historical figures to estimate the GDP per capita of countries and regions? Here, we introduce a machine learning method to estimate the GDP per capita of dozens of countries and hundreds of regions in Europe and North America for the past seven centuries starting from data on the places of birth, death, and occupations of hundreds of thousands of historical figures. We build an elastic net regression model to perform feature selection and generate out-of-sample estimates that explain 90% of the variance in known historical income levels. We use this model to generate GDP per capita estimates for countries, regions, and time periods for which these data are not available and externally validate our estimates by comparing them with four proxies of economic output: urbanization rates in the past 500 y, body height in the 18th century, well-being in 1850, and church building activity in the 14th and 15th century. Additionally, we show our estimates reproduce the well-known reversal of fortune between southwestern and northwestern Europe between 1300 and 1800 and find this is largely driven by countries and regions engaged in Atlantic trade. These findings validate the use of fine-grained biographical data as a method to augment historical GDP per capita estimates. We publish our estimates with CI together with all collected source data in a comprehensive dataset. date: 2024-09-16 date_type: published publisher: National Academy of sciences id_number: 10.1073/pnas.2402060121 official_url: http://tse-fr.eu/pub/130192 faculty: tse divisions: tse language: en has_fulltext: FALSE doi: 10.1073/pnas.2402060121 view_date_year: 2024 full_text_status: none publication: Proceedings of the National Academy of Sciences of the United States of America volume: Vol. 121 number: N° 39 place_of_pub: Washington refereed: TRUE issn: 0027-8424 oai_identifier: oai:tse-fr.eu:130192 harvester_local_overwrite: number harvester_local_overwrite: volume harvester_local_overwrite: creators_name harvester_local_overwrite: issn harvester_local_overwrite: pending harvester_local_overwrite: note harvester_local_overwrite: creators_idrefppn harvester_local_overwrite: creators_halaffid harvester_local_overwrite: publication harvester_local_overwrite: publisher harvester_local_overwrite: place_of_pub harvester_local_overwrite: creators_id harvester_local_overwrite: date harvester_local_overwrite: publish_to_hal harvester_local_overwrite: hal_id harvester_local_overwrite: hal_version harvester_local_overwrite: hal_url harvester_local_overwrite: hal_passwd oai_lastmod: 2025-03-10T10:51:16Z oai_set: tse site: ut1 publish_to_hal: TRUE hal_id: hal-04948360 hal_passwd: &@dlw3 hal_version: 1 hal_url: https://hal.science/hal-04948360 citation: Koch, Philipp , Stojkoski, Viktor and Hidalgo, Cesar Augusto (2024) Augmenting the availability of historical GDP per capita estimates through machine learning. Proceedings of the National Academy of Sciences of the United States of America, Vol. 121 (N° 39).