Tourism development and U.S energy security risks: a KRLS machine learning approach

ABSTRACTThis study presents evidence on how tourism development affects U.S. energy security risks from 1997 to 2020 using a Kernel-based regularized least squares (KRLS) machine learning approach. Our empirical results demonstrate that tourism development amplifies the U.S. energy security-related risks. Also, while technological innovation and urbanization dampen the pressure on energy security-related risks, economic policy-based uncertainty and industrial production increase energy security risks. These results survive in the disaggregated models except for the environmental-related risks sub-index which decreases as a result of tourism development. Our findings, therefore, provide useful insights for policymakers to minimize energy security-related risks.KEYWORDS: U.S energy security riskstourism developmentpolicy uncertaintytechnology innovationKRLS machine learning Disclosure statementNo potential conflict of interest was reported by the author(s).Correction StatementThis article has been corrected with minor changes. These changes do not impact the academic content of the article.Notes1 Except for IP, all other variables are converted from annual frequency to quarterly frequency using the quadratic match sum – the most preferred method of converting low-frequency data to high-frequency data (Kisswani et al., Citation2020).2 The corresponding author will provide the results of these tests upon a reasonable request.