Publicación: Relación entre la emisión de bonos verdes y la “prima verde” en mercado primario. Evidencias con modelos de aprendizaje automático.
Fecha
2025-02
Autores
Editor/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (UNED). E.T.S. de Ingeniería Informática
Resumen
Este trabajo presenta un análisis del mercado de bonos verdes y su relación con los criterios ambientales, sociales y de gobernanza (ESG) de las empresas emisoras. El objetivo principal es investigar la existencia de una «prima verde» en estos bonos, es decir, si los inversores están dispuestos a aceptar un rendimiento menor a cambio de invertir en empresas que certifican como verde su deuda. Se han utilizado para ello datos de entidades no públicas que han emitido deuda verde a medio y largo plazo en el período 2020 y 2024, en todo el mundo. En una primera aproximación del estudio, se compara el ratio de deuda verde emitida por las organizaciones con sus puntuaciones ESG para buscar una relación directa entre estos dos parámetros. Dado que la muestra de bonos verdes con puntuaciones completas ESG es escasa, se han utilizado algoritmos de aprendizaje automático para completarla. Posteriormente se ha hecho un estudio pormenorizado sobre la existencia de la prima verde, basado en una técnica de comparación de datos reales con datos generados a través de un modelo de aprendizaje automático. Para llevar a cabo estos análisis, se han construido y probado varios modelos de aprendizaje automático para seleccionar el más adecuado en cada ocasión. La muestra de estudio incluye una selección diversa de bonos verdes emitidos por empresas con diferentes niveles de compromiso con la sostenibilidad. Las calificaciones para la reconstrucción de los parámetros ESG, así como las valoraciones de la deuda, se obtienen de fuentes de datos reconocidas. Este estudio contribuye a la literatura existente sobre bonos verdes y ESG al proporcionar evidencia empírica sobre la existencia y magnitud de la prima verde. Asimismo, puede ofrecer información relevante para los inversores que buscan integrar criterios de sostenibilidad en sus decisiones de inversión y para las empresas que buscan financiar proyectos verdes a través de la emisión de bonos.
This document presents an analysis of the green bond market and its relationship with the environmental, social, and governance (ESG) criteria of issuing companies. The main objective is to investigate the existence of a "green premium" in these bonds, that is, whether investors are willing to accept a lower yield in exchange for investing in companies that certify their debt as green. For this purpose, data from private organizations with medium- and long-term green debt issuance between 2020 and 2024 worldwide have been used. In a first approach of the study, the ratio of green debt issued by organizations is compared with their ESG scores to look for a direct relationship between these two parameters. Since the sample of green bonds with complete ESG scores is scarce, machine learning algorithms have been used to complete it. Subsequently, a detailed study has been carried out on the existence of the green premium, based on a technique of comparing real data with data generated through a machine learning model. To carry out these analyses, several machine learning models have been built and tested to select the most suitable one on each occasion. The study sample includes a diverse selection of green bonds issued by companies with different levels of commitment to sustainability. The ratings for the reconstruction of ESG parameters, as well as debt valuations, are obtained from recognized data sources. This study contributes to the existing literature on green bonds and ESG by providing empirical evidence on the existence and magnitude of the green premium. It can also offer relevant information for investors seeking to integrate sustainability criteria into their investment decisions and for companies seeking to finance green projects through bond issuance.
This document presents an analysis of the green bond market and its relationship with the environmental, social, and governance (ESG) criteria of issuing companies. The main objective is to investigate the existence of a "green premium" in these bonds, that is, whether investors are willing to accept a lower yield in exchange for investing in companies that certify their debt as green. For this purpose, data from private organizations with medium- and long-term green debt issuance between 2020 and 2024 worldwide have been used. In a first approach of the study, the ratio of green debt issued by organizations is compared with their ESG scores to look for a direct relationship between these two parameters. Since the sample of green bonds with complete ESG scores is scarce, machine learning algorithms have been used to complete it. Subsequently, a detailed study has been carried out on the existence of the green premium, based on a technique of comparing real data with data generated through a machine learning model. To carry out these analyses, several machine learning models have been built and tested to select the most suitable one on each occasion. The study sample includes a diverse selection of green bonds issued by companies with different levels of commitment to sustainability. The ratings for the reconstruction of ESG parameters, as well as debt valuations, are obtained from recognized data sources. This study contributes to the existing literature on green bonds and ESG by providing empirical evidence on the existence and magnitude of the green premium. It can also offer relevant information for investors seeking to integrate sustainability criteria into their investment decisions and for companies seeking to finance green projects through bond issuance.
Descripción
Categorías UNESCO
Palabras clave
bonos verdes, ESG, prima verde, aprendizaje automático, sostenibilidad, medio ambiente, responsabilidad social corporativa, green bonds, ESG, greemiun, machine learning, sustainability, corporate social responsibility, CSR
Citación
Cuevas i Fajardo, Àlvar. Trabajo Fin de Máster: Relación entre la emisión de bonos verdes y la “prima verde” en mercado primario. Evidencias con modelos de aprendizaje automático.. Universidad Nacional de Educación a Distancia (UNED) 2025
Centro
E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial