Machine learning has been widely and rapidly adopted to create new measurements that are difficult to proxy or gauge from traditional financial reports or articles. In the context of text-based analysis, machine learning can assist finance and accounting researchers in extracting information from the language used in financial documents, such as earnings calls. Many top journals have started to publish these measurements, with the main contribution of their papers being the introduction of new metrics, that were previously difficult to measure, using text-based machine learning models.
This post will continuously update and summarize publicly available measurements of various financial or economic indices, such as firm-level climate change risk, firm-level geographical risk, corporate culture, political risk, and more.
Tarek A. Hassan, Stephan Hollander, Laurence van Lent, Ahmed Tahoun, 2019, “Firm-Level Political Risk: Measurement and Effects,” Quarterly Journal of Economics, 134 (4), pp.2135-2202. https://doi.org/10.1093/qje/qjz021.
Caldara, Dario, and Matteo Iacoviello (2022), “Measuring Geopolitical Risk,” American Economic Review, April, 112(4), pp.1194–1225.
Li, K., F. Mai, R. Shen, and X. Yan, 2021. “Measuring Corporate Culture Using Machine Learning,” Review of Financial Studies 34 (A Special Issue on Big Data in Finance), 3265-3315.
- Firm-Level Labor-Shortage Exposure (Working paper)
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4410126
Sautner, Z., L. van Lent, G. Vilkov, and R. Zhang, 2023. Firm-level climate change exposure. The Journal of Finance 78(3), 1449-1498, DOI: 10.1111/jofi.13219.
Qing Li, Hongyu Shan, Yuehua Tang, Vincent Yao, Corporate Climate Risk: Measurements and Responses, The Review of Financial Studies, Volume 37, Issue 6, June 2024, Pages 1778–1830, https://doi.org/10.1093/rfs/hhad094