Causal analysis of macroeconomic shocks on financial markets through machine learning methods

Stefano Campita () and Francesco Benedetto ()
Additional contact information
Stefano Campita: Department of Economics, Roma Tre University, Rome, Italy
Francesco Benedetto: Department of Economics, Università degli Studi Roma Tre

Journal of Economics and Business Letters, 2026, vol. 6, issue 2, 30-42

Abstract: Macroeconomic announcements often trigger sharp market reactions; however, their causal impact is difficult to measure. This study quantifies the causal effects of the consumer price index (CPI), non-farm payrolls (NFP), and Federal Open Market Committee (FOMC) decisions on the S&P 500, Gold, and the VIX using daily data from 2022 to 2024. Three estimators are applied: Ordinary Least Squares, Propensity Score Matching, and Double Machine Learning. The results show limited price adjustments but strong and statistically meaningful volatility responses. FOMC shocks generate the most persistent effects, whereas CPI and NFP impacts are short-lived. Overall, the findings indicate that volatility, rather than prices, is the primary transmission channel of macroeconomic news, highlighting the value of causal machine learning in identifying structural market responses.

Keywords: double machine learning; macroeconomic announcements; propensity score matching; S&P 500 (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journal.privietlab.org/download.php?id=13508 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:prv:jeblpv:1449

Ordering information: This journal article can be ordered from
https://journal.priv ... BL/article/view/1449

DOI: 10.55942/jebl.v6i2.1449

Access Statistics for this article

More articles in Journal of Economics and Business Letters from Privietlab Research Center
Bibliographic data for series maintained by Mochammad Fahlevi ().