This study investigates the performance of subsidiaries situated in climate-risk zones through the application of machine learning algorithms. It aims to demonstrate that subsidiary performance during crises depends on both the intervention of the parent company and the subsidiary's capability to manage crises independently. Subsidiaries were evaluated based on their strategic significance to the parent company, determined by organizational factors such as the level of control exerted by the parent and the nature of subsidiary activities. A set of explanatory variables has been defined with the aim of representing the relationship between subsidiaries and parents, and various machine learning techniques have been employed to model the dependence of financial performance on these variables. The results demonstrate how the decision tree algorithm leads to good prediction efficiency, while also allowing for the study of the relationship between the different variables considered and the financial performance achieved by subsidiaries with different profiles.

Climate risks and corporate performances: a machine learning model to assess organizational strategicity / De Iuliis, M., Troisi, R.. - (2024). (CSBF 2024 - 2nd conference on sustainable banking and finance Naples 21 June 2024).

Climate risks and corporate performances: a machine learning model to assess organizational strategicity

De Iuliis, Massimiliano;
2024

Abstract

This study investigates the performance of subsidiaries situated in climate-risk zones through the application of machine learning algorithms. It aims to demonstrate that subsidiary performance during crises depends on both the intervention of the parent company and the subsidiary's capability to manage crises independently. Subsidiaries were evaluated based on their strategic significance to the parent company, determined by organizational factors such as the level of control exerted by the parent and the nature of subsidiary activities. A set of explanatory variables has been defined with the aim of representing the relationship between subsidiaries and parents, and various machine learning techniques have been employed to model the dependence of financial performance on these variables. The results demonstrate how the decision tree algorithm leads to good prediction efficiency, while also allowing for the study of the relationship between the different variables considered and the financial performance achieved by subsidiaries with different profiles.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/3018084
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo