eprintid: 4474 rev_number: 12 eprint_status: archive userid: 2 dir: disk0/00/00/44/74 datestamp: 2022-11-11 23:30:04 lastmod: 2023-07-12 23:31:05 status_changed: 2022-11-11 23:30:04 type: article metadata_visibility: show creators_name: García Villena, Eduardo creators_name: Pascual Barrera, Alina Eugenia creators_name: Álvarez, Roberto Marcelo creators_name: Dzul López, Luis Alonso creators_name: Tutusaus, Kilian creators_name: Vidal Mazón, Juan Luis creators_name: Miró Vera, Yini Airet creators_name: Brie, Santiago creators_name: López Flores, Miguel A. creators_id: eduardo.garcia@uneatlantico.es creators_id: alina.pascual@unini.edu.mx creators_id: roberto.alvarez@uneatlantico.es creators_id: luis.dzul@uneatlantico.es creators_id: kilian.tutusaus@uneatlantico.es creators_id: juanluis.vidal@uneatlantico.es creators_id: yini.miro@uneatlantico.es creators_id: santiago.brie@uneatlantico.es creators_id: miguelangel.lopez@uneatlantico.es title: Evaluation of the Sustainable Development Goals in the Diagnosis and Prediction of the Sustainability of Projects Aimed at Local Communities in Latin America and the Caribbean ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: unincol_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica divisions: unic_produccion_cientifica full_text_status: public keywords: SMOTE; artificial intelligence; projects; fuzzy logic abstract: The purpose of this article is to help to bridge the gap between sustainability and its application to project management by developing a methodology based on artificial intelligence to diagnose, classify, and forecast the level of sustainability of a sample of 186 projects aimed at local communities in Latin American and Caribbean countries. First, the compliance evaluation with the Sustainable Development Goals (SDGs) within the framework of the 2030 Agenda served to diagnose and determine, through fuzzy sets, a global sustainability index for the sample, resulting in a value of 0.638, in accordance with the overall average for the region. Probabilistic predictions were then made on the sustainability of the projects using a series of supervised learning classifiers (SVM, Random Forest, AdaBoost, KNN, etc.), with the SMOTE resampling technique, which provided a significant improvement toward the results of the different metrics of the base models. In this context, the Support Vector Machine (SVM) + SMOTE was the best classification algorithm, with accuracy of 0.92. Lastly, the extrapolation of this methodology is to be expected toward other realities and local circumstances, contributing to the fulfillment of the SDGs and the development of individual and collective capacities through the management and direction of projects. date: 2022-11 publication: Applied Sciences volume: 12 number: 21 pagerange: 11188 id_number: doi:10.3390/app122111188 refereed: TRUE issn: 2076-3417 official_url: http://doi.org/10.3390/app122111188 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Fundación Universitaria Internacional de Colombia > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Abierto Inglés The purpose of this article is to help to bridge the gap between sustainability and its application to project management by developing a methodology based on artificial intelligence to diagnose, classify, and forecast the level of sustainability of a sample of 186 projects aimed at local communities in Latin American and Caribbean countries. First, the compliance evaluation with the Sustainable Development Goals (SDGs) within the framework of the 2030 Agenda served to diagnose and determine, through fuzzy sets, a global sustainability index for the sample, resulting in a value of 0.638, in accordance with the overall average for the region. Probabilistic predictions were then made on the sustainability of the projects using a series of supervised learning classifiers (SVM, Random Forest, AdaBoost, KNN, etc.), with the SMOTE resampling technique, which provided a significant improvement toward the results of the different metrics of the base models. In this context, the Support Vector Machine (SVM) + SMOTE was the best classification algorithm, with accuracy of 0.92. Lastly, the extrapolation of this methodology is to be expected toward other realities and local circumstances, contributing to the fulfillment of the SDGs and the development of individual and collective capacities through the management and direction of projects. metadata García Villena, Eduardo; Pascual Barrera, Alina Eugenia; Álvarez, Roberto Marcelo; Dzul López, Luis Alonso; Tutusaus, Kilian; Vidal Mazón, Juan Luis; Miró Vera, Yini Airet; Brie, Santiago y López Flores, Miguel A. mail eduardo.garcia@uneatlantico.es, alina.pascual@unini.edu.mx, roberto.alvarez@uneatlantico.es, luis.dzul@uneatlantico.es, kilian.tutusaus@uneatlantico.es, juanluis.vidal@uneatlantico.es, yini.miro@uneatlantico.es, santiago.brie@uneatlantico.es, miguelangel.lopez@uneatlantico.es (2022) Evaluation of the Sustainable Development Goals in the Diagnosis and Prediction of the Sustainability of Projects Aimed at Local Communities in Latin America and the Caribbean. Applied Sciences, 12 (21). p. 11188. ISSN 2076-3417 document_url: http://repositorio.uneatlantico.es/id/eprint/4474/1/applsci-12-11188.pdf