Use of machine learning techniques in bank credit risk analysis

Fenerich, Amanda Trojan; Steiner, María Teresinha Arns; Neto, Pedro José Steiner; Tochetto, Edevar; Tsutsumi, Diego P.; Assef, Fernanda Medeiros; Santos, Bruno Samways dos

doi:10.23967/j.rimni.2020.08.003

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding selecting features that can improve the predictor models' performance, some techniques can facilitate the visualization and understanding of the estimated parameters and avoid over tting problems. Some of the approaches recommended in the literature are Feature Ranking, which serves to establish a ranking of the features based on information gain independent of the classi er algorithm, and Wrapper Subset Eval, to select a subset of features that results in better evaluation performance, depending on the classi er algorithm (Fenerich et al, 2020). Notably, some features may be irrelevant and generate poor classi cation results and higher complexity, so selecting and removing them is necessary.…”

Section: Credit Risk Analysis Models With Arti Cial Intelligencementioning

confidence: 99%

Financial Inclusion of Vulnerable Sectors with a Gender Perspective: Risk Analysis Model with Artificial Intelligence Based on Complex Thinking

Vidal

Alonso-Galicia

González-Mendoza

et al. 2023

Preprint

View full text Add to dashboard Cite

The objective is to present a proposal for a gender-sensitive risk analysis model using artificial intelligence (AI) within the framework of complex thinking, specifically for impoverished and vulnerable women. This international non-parametric study analyzed business and entrepreneurial activity in a sample of 2,787 women. The methodological design included data analysis, the postulation of a proposed model, and a validation method for the credit risk analysis model. There is a correlation between the level of schooling of impoverished and vulnerable women with the possibility of self-employment and selling a product or service. In the framework of complex thinking, the perception of innovative thinking is related to the level of education and innovative decision-making in professional projects. Women with a higher level of schooling tend to think about their professional projects systematically. Promoting complex thinking involves innovative educational practices to encourage critical, systemic, scientific, and innovative thinking in entrepreneurship and sustainable development. Integrating reasoning for complexity benefits women and contributes to economic and social growth in vulnerable regions. In contrast to other models, our credit risk analysis model uses AI and variables for gender, vulnerability, and complex thinking to detect patterns in women's behaviors and attitudes in the venture start-up process.

show abstract

Section: Credit Risk Analysis Models With Arti Cial Intelligencementioning

confidence: 99%

Financial Inclusion of Vulnerable Sectors with a Gender Perspective: Risk Analysis Model with Artificial Intelligence Based on Complex Thinking

Vidal

Alonso-Galicia

González-Mendoza

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Suitable when the goal is high performance and multiple algorithms can be used. [8] Machine Learning Efficient…”

Section: Very Efficientmentioning

confidence: 99%

“…CRA can use technology-based methods, models, and algorithms to make predictions and select borrowers [8]. In this type of assessment, banks create computer models to represent the process of selecting customers for loan granting so that the approach is clearer and produces better results [9].…”

Section: Introductionmentioning

confidence: 99%

Modelos para la evaluación de riego crediticio en el ámbito de la tecnología financiera: una revisión

Tadeo Espinoza,

Coral Ygnacio

2023

TecnoL.

View full text Add to dashboard Cite

Esta revisión analiza una selección de artículos científicos sobre la implantación de sistemas de evaluación del riesgo de crédito para identificar las soluciones existentes, las más acertadas y las limitaciones y problemas en su desarrollo. Se adoptó la declaración PRISMA del siguiente modo: se formularon las preguntas de investigación, se definieron los criterios de inclusión, se seleccionaron las palabras clave y se diseñó la cadena de búsqueda. Por último, se calcularon varios estadísticos descriptivos de los artículos seleccionados. En los estudios seleccionados se identificaron 31 soluciones, entre métodos, modelos y algoritmos. Algunos de los modelos más utilizados se basan en técnicas de Inteligencia Artificial (IA), especialmente Redes Neuronales y Bosques Aleatorios. Se concluyó que las Redes Neuronales son las soluciones más eficientes, con precisiones medias superiores al 90 %, pero su desarrollo puede tener limitaciones. Estas soluciones deben implementarse teniendo en cuenta el contexto en el que se van a emplear.

show abstract

“…Muitos trabalhos têm sido feitos com técnicas de mineração de dados e, no lado financeiro, muitos são voltados aos investimentos, como nos exemplos de aplicação levantados na revisão de Henrique, Sobreiro e Kimura (2019), ou na concessão de crédito, como sumarizado por (Fenerich et al, 2020). Entretanto, não se verificou trabalhos de classificação no contexto da inclusão financeira, principalmente com foco na realidade latino-americana.…”

Section: Introductionunclassified

Utilização De Técnicas De Classificação Em Conjunto De Dados Sobre Inclusão Financeira: Um Estudo Baseado Em Países Latinoamericanos

Souza

Tomazi

Santos

2022

Revista Brasileira de Engenharia de Produção

View full text Add to dashboard Cite

A inclusão financeira é importante para reduzir a pobreza e proporcionar um crescimento econômico inclusivo, principalmente comparando grupos com grande desigualdade social. Este artigo utilizou a pesquisa Global Financial Inclusion (Global Findex) da World Bank Group para comparar técnicas de aprendizado de máquina na classificação de homens e mulheres quanto ao uso de serviços financeiros. Para isso, utilizou-se os classificadores Árvore de decisão, -vizinhos mais próximos, Naïve Bayes e Floresta randômica, e avaliadas as métricas de acurácia, precisão, sensibilidade, f1-score e área sob a curva Receiver Operating Characteristic (ROC). Verificou-se que todas as técnicas (exceto por Naïve Bayes) obtiveram uma acurácia próxima a 70%, sensibilidade próxima a 88% e precisão acima dos 72% na maioria dos parâmetros investigados. Quanto à área sob a curva ROC, a Floresta randômica atingiu 0,77, superando as outras técnicas nesta avaliação.

show abstract

Use of machine learning techniques in bank credit risk analysis

Cited by 6 publications

References 0 publications

Financial Inclusion of Vulnerable Sectors with a Gender Perspective: Risk Analysis Model with Artificial Intelligence Based on Complex Thinking

Financial Inclusion of Vulnerable Sectors with a Gender Perspective: Risk Analysis Model with Artificial Intelligence Based on Complex Thinking

Modelos para la evaluación de riego crediticio en el ámbito de la tecnología financiera: una revisión

Utilização De Técnicas De Classificação Em Conjunto De Dados Sobre Inclusão Financeira: Um Estudo Baseado Em Países Latinoamericanos

Contact Info

Product

Resources

About