Using artificial intelligence to overcome over-indebtedness and fight poverty

Abstract

This research examines how artificial intelligence may contribute to better understanding and to overcome over-indebtedness in contexts of high poverty risk. This research uses Automated Machine Learning (AutoML) in a field database of 1654 over-indebted households to identify distinguishable clusters and to predict its risk factors. First, unsupervised machine learning using Self-Organizing Maps generated three over-indebtedness clusters: low-income (31.27%), low credit control (37.40%), and crisis-affected households (31.33%). Second, supervised machine learning with exhaustive grid search hyperparameters (32,730 predictive models) suggests that Nu-Support Vector Machine had the best accuracy in predicting families’ over-indebtedness risk factors (89.5%). By proposing an AutoML approach on over-indebtedness, our research adds both theoretically and methodologically to current models of scarcity with important practical implications for business research and society. Our findings also contribute to novel ways to identify and characterize poverty risk in earlier stages, allowing customized interventions for different profiles of over-indebtedness.

On the Relation Between Over-Indebtedness and Well-Being: An Analysis of the Mechanisms Influencing Health, Sleep, Life Satisfaction, and Emotional Well-Being

“…Third, our procedure classified all cases of over-indebted participants under the same conceptual umbrella, which is likely to be an oversimplification. In other words, not all over-indebted households should be considered equal ( Ferreira et al, 2020 ). The diversity of risk factors of over-indebtedness strongly suggests that there are different over-indebted profiles associated to distinguishable causes (e.g., work loss, disease, low financial literacy, poor decision-making, and financial imprudence).…”

La tecnología al servicio de la vigilancia y de la defensa de la vida

“…Al final, se entrega el documento de reporte de incidentes a los involucrados, gracias a una impresora térmica acoplada a una Tablet. La actividad policial es auxiliada por el acceso, vía aplicación, de datos oriundos de sistemas de información de otros órganos administrativos, como el Departamento de Tránsito y de Seguridad Pública (Boto Ferreira et al, 2020).…”

Poverty in the Indonesia-Malaysia border province (case study in West Kalimantan Province)

“…They are concentrating their efforts on advancing and utilizing information technology and encouraging their country to lead the service industry. As a result, the residents of both countries have a better standard of living than those of other countries (Watanabe et al, 2018;Ferreira et al, 2020). In the digitalization era, the government of West Kalimantan Province may adopt such actions as well.…”