FRAMING OF THE RESEARCH. This research discusses the application of sustainable management (SM) concepts, which integrate economic, social, and environmental aspects, to decision-making processes using artificial intelligence (AI) methodologies. The proposed framework utilizes decision trees to learn sustainable practices in strategic areas, such as healthcare and corporate balance sheet management. PURPOSE OF THE PAPER. The research aims to use AI methodologies, specifically decision trees, to induce sustainable practices in decision-making processes. The research also seeks to capture “common sense knowledge” from data, which has been a challenge for AI since its foundation as a discipline. METHODOLOGY. The proposed methodology uses decision trees, a well-known AI methodology, to automatically generate a set of rules (i.e., practices) that satisfy the pillars of sustainability. The rules are learned from data coming from different sources in strategic areas such as healthcare management and corporate balance sheet management. The approach aims to capture “common sense knowledge” from data, which has been a challenge for AI since its foundation as a discipline. RESULTS. The proposed methodology allows decision-makers to explore the underlying processes with greater awareness and trust, overcoming the opacity and uncertainty of typical black box strategies offered by some AI solutions. Overall, the paper proposes an explainable AI methodology that captures common sense knowledge without losing methodological rigor, to support sustainable decision-making. RESEARCH LIMITATIONS. A limitation of this paper is represented by the intervals of data that should be introduced in order to get a better classification and, as a consequence, a better decision-making process. MANAGERIAL IMPLICATIONS. By learning a set of sustainable practices from data in strategic areas such as healthcare management and corporate balance sheet management, decision makers can make better decisions that satisfy the pillars of sustainability. The framework also addresses the challenge of capturing common sense knowledge from data, which has been a challenge for AI since its foundation. By providing interpretable rules or practices, decision makers can have a better understanding of the underlying processes and greater trust in the decision-making process. ORIGINALITY OF THE PAPER. he proposed methodology is an “explainable AI” that makes it possible to capture common sense knowledge without losing methodological rigor. The paper also emphasizes the importance of sustainable practices and how they can benefit current and future generations while limiting the depletion of natural resources. Strategic areas such as healthcare management and corporate balance sheet management are identified as areas where sustainable practices are more than desirable.

Some methodological remarks for a sustainable management – An explainable artificial intelligence paradigm approach / D'Avanzo, Ernesto. - STAMPA. - (2023), pp. 585-599. (Intervento presentato al convegno Sinergie - Sima Management Conference 2023 tenutosi a Bari nel 29th-30th June 2023).

Some methodological remarks for a sustainable management – An explainable artificial intelligence paradigm approach

D'Avanzo, Ernesto
Primo
2023-01-01

Abstract

FRAMING OF THE RESEARCH. This research discusses the application of sustainable management (SM) concepts, which integrate economic, social, and environmental aspects, to decision-making processes using artificial intelligence (AI) methodologies. The proposed framework utilizes decision trees to learn sustainable practices in strategic areas, such as healthcare and corporate balance sheet management. PURPOSE OF THE PAPER. The research aims to use AI methodologies, specifically decision trees, to induce sustainable practices in decision-making processes. The research also seeks to capture “common sense knowledge” from data, which has been a challenge for AI since its foundation as a discipline. METHODOLOGY. The proposed methodology uses decision trees, a well-known AI methodology, to automatically generate a set of rules (i.e., practices) that satisfy the pillars of sustainability. The rules are learned from data coming from different sources in strategic areas such as healthcare management and corporate balance sheet management. The approach aims to capture “common sense knowledge” from data, which has been a challenge for AI since its foundation as a discipline. RESULTS. The proposed methodology allows decision-makers to explore the underlying processes with greater awareness and trust, overcoming the opacity and uncertainty of typical black box strategies offered by some AI solutions. Overall, the paper proposes an explainable AI methodology that captures common sense knowledge without losing methodological rigor, to support sustainable decision-making. RESEARCH LIMITATIONS. A limitation of this paper is represented by the intervals of data that should be introduced in order to get a better classification and, as a consequence, a better decision-making process. MANAGERIAL IMPLICATIONS. By learning a set of sustainable practices from data in strategic areas such as healthcare management and corporate balance sheet management, decision makers can make better decisions that satisfy the pillars of sustainability. The framework also addresses the challenge of capturing common sense knowledge from data, which has been a challenge for AI since its foundation. By providing interpretable rules or practices, decision makers can have a better understanding of the underlying processes and greater trust in the decision-making process. ORIGINALITY OF THE PAPER. he proposed methodology is an “explainable AI” that makes it possible to capture common sense knowledge without losing methodological rigor. The paper also emphasizes the importance of sustainable practices and how they can benefit current and future generations while limiting the depletion of natural resources. Strategic areas such as healthcare management and corporate balance sheet management are identified as areas where sustainable practices are more than desirable.
2023
Rediscovering local roots and interactions in management: Conference Proceedings Long Papers
Verona
CUEM
978-88-947136-1-9
D'Avanzo, Ernesto
Some methodological remarks for a sustainable management – An explainable artificial intelligence paradigm approach / D'Avanzo, Ernesto. - STAMPA. - (2023), pp. 585-599. (Intervento presentato al convegno Sinergie - Sima Management Conference 2023 tenutosi a Bari nel 29th-30th June 2023).
File in questo prodotto:
File Dimensione Formato  
Conference_Proceeding_Single_Paper_D_Avanzo.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.4 MB
Formato Adobe PDF
5.4 MB Adobe PDF   Visualizza/Apri

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/11572/390730
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact