Machine learning applications in risk management - Trends and research agenda - Research article

Aug 4, 2026

Risk management has become a foundational aspect in numerous industries, driving the adoption of machine learning for impact assessment, prevention, and decision-making. However, important gaps remain in identifying emergent trends and cross-cutting applications. This study uses bibliometric analysis of scientific output in Scopus and Web of Science, following the PRISMA-2020 framework. Results show a 98.99% rise in publications from 2018 to 2023, with China, South Korea, and the United States leading. The work highlights new directions in areas such as urban tree risk and SARS-CoV-2 related risk management.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages43

Reading Time1 h 48 min

AccessFree to download

Abstract

Study approach and data sources

Key findings and emerging trends

Keywords and research scope

Open Peer Review

Version history and approval status

Keywords

Core terms used

RESEARCH ARTICLE Machine learning applications in risk management: Trends and research agenda [version 2; peer review: 3 approved, 1 approved with reservations] Alejandro Valencia-Arias 1, Jesus Alberto Jimenez Garcia 2, Erica Agudelo-Ceballos3, Aarón José Alberto Oré León4, Ezequiel Martínez Rojas 5, Julio Leyrer Henríquez6, Diana Marleny Ramírez-Ramírez7 1 Escuela de Ingeniería Industrial, Universidad Senor de Sipan, Chiclayo, 14001, Peru 2 Dirección de Planificación y Desarrollo Institucional, Universidad Senor de Sipan, Chiclayo, 14001, Peru 3 Departamento de Ciencias Administrativas, Instituto Tecnologico Metropolitano, Medellín, 50010, Colombia 4Instituto de Investigación de Estudios de la Mujer, Universidad Ricardo Palma, Santiago de Surco, 15039, Peru 5Vicerrectoría de Investigación e Innovación, Universidad Arturo Prat, Iquique, Tarapacá Region, Chile 6Universidad Ricardo Palma, Lima, Peru 7Ciencias económicas y administrativas, Instituto Tecnologico Metropolitano, Medellín, 50010, Colombia v2 First published: 25 Feb 2025, 14:233 [https://doi.org/10.12688/f1000research.161993.1](https://doi.org/10.12688/f1000research.161993.1) [Latest published:](Latest published: 07 Apr 2025)[ 07 Apr 2025](Latest published: 07 Apr 2025), 14:233 [https://doi.org/10.12688/f1000research.161993.2](https://doi.org/10.12688/f1000research.161993.2) Abstract Abstract Risk management has become a foundational aspect in numerous industries, propelling the implementation of machine learning technologies for impact assessment, prevention, and decision-making processes. Nevertheless, lacunae in the extant literature persist, particularly with regard to the identification of emergent trends and transversal applications. This study addresses this limitation through abibliometric analysis of scientific production in Scopus and Web of Science, adhering to the PRISMA-2020 declaration. The findings reveal a substantial growth in publications on machine learning applied to risk management, with an increase of 98.99% between 2018 and 2023. China, South Korea, and the United States are identified as the primary research-producing countries. The analysis also identifies emerging trends, such as the application of machine learning in the evaluation of urban trees and the management of risks associated with the pandemic of severe acute respiratory syndrome (SARS-CoV- 2) . Key terms include random forest, support vector machines (SVM), and credit risk assessment, while terms such as prediction, postpartum depression, big data, and security emerge as new areas Open Peer Review | Approval Status | | | | | | --- | --- | --- | --- | --- | | 1 | | 2 | 3 | 4 | | version 2
(revision) |
view |
view view view | | | | 07 Apr 2025 | | | | | | version 1
25 Feb 2025 |
view |
view | | | 1. Ajay Vikram Singh , German Federal Institute for Risk Assessment (BfR), Berlin, Germany 2. Rakibul Hasan Chowdhury , University of Portsmouth, Portsmouth, UK 3. muskan Khan , Karnatak University Dharwad, Dharwad, India 4. Tian Tian , Illinois Institute of Technology College of Computing, Chicago, USA Any reports and responses or comments on the of study. Furthermore, there is a transition from traditional approaches such as stacking to advanced deep learning and featureselection techniques, reflecting the evolution of the discipline. Keywords Decision Making, Random Forest, Big Data, Deep Learning, Security article can be found at the end of the article. Corresponding author: Alejandro Valencia-Arias ([valenciajho@uss.edu.pe](valenciajho@uss.edu.pe)) Author roles: Valencia-Arias A: Conceptualization, Writing – Original Draft Preparation, Writing – Review & Editing; Jimenez Garcia JA: Conceptualization, Writing – Original Draft Preparation, Writing – Review & Editing; Agudelo-Ceballos E: Conceptualization, Writing – Original Draft Preparation, Writing – Review & Editing; Oré León AJA: Conce

FAQs

What research gap does the study address in machine learning for risk management?

It targets gaps in the literature regarding identification of emergent trends and transversal, cross-cutting applications in risk management.

How was the evidence collected and analyzed?

The study conducts a bibliometric analysis of scientific production from Scopus and Web of Science, aligned with the PRISMA-2020 declaration.

What major trends and indicators are highlighted in the results?

Publication output increased substantially between 2018 and 2023, and emerging themes include applications such as urban tree evaluation and risk management related to SARS-CoV-2.

Aug 4, 2026

Upload by River Wang