3. Producción
Browse
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, FinTech Adoption and Bank Credit Risk: Evidence of a Nonlinear Relationship from Latin America(Pontificia Universidad Católica del Perú. Departamento de Economía, 2026-08)We examine how FinTech adoption affects credit risk in a panel of commercial banks from Chile, Colombia, Mexico and Peru over 2010–2024, covering more than 90 percent of bank lending in each country. Because structured technology-expenditure data do not exist for these banking systems, we construct cumulative dictionary-based digitalization indices from a raw corpus of 785 annual-report PDFs across six technological dimensions. Panel estimates with Driscoll–Kraay inference document an inverted-U relationship between cumulative digitalization and nonperforming loans: early adoption raises NPLs as lending expands towards borrowers without credit histories, while beyond a threshold efficiency gains in screening dominate and credit risk declines. The pattern is specific to the IT-infrastructure dimension of adoption; it survives various robustness exercises. A Cournot framework with two borrower segments organises the opposing inclusion and efficiency channels that motivate the quadratic specification. The turning point falls with bank size, and slopes differ across countries, so the pooled estimates are averages over heterogeneous national markets. With 82% of observations below the threshold, these banking systems remain largely in the phase where digital adoption is associated with rising credit risk. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Risk Analysis in Microfinance Using Machine Learning and Potential Integration with Artificial Intelligence Agent(Universidad del Pacifico, 2026-01-01)This study proposes a comprehensive approach for the early detection of default risk in microfinance portfolios, combining machine learning techniques with historical analysis of clients' payment behavior. A database of more than 50,000 microcredits granted in Peru by a microfinance institution in Huancayo (2019–2021) was used, constructing a risk indicator based on the proportion of days in arrears relative to the agreed payment frequency, with a critical threshold of 25% of the installment period. This criterion differentiates clients with a higher propensity to default without penalizing minor delays, improving analytical accuracy. The study focuses on microenterprises and informal entrepreneurs, traditionally excluded from formal banking. It provides predictive tools adapted to segments with limited credit history, fostering financial inclusion and strengthening risk management in microfinance institutions. Four predictive models were evaluated, representing the main families of supervised learning: Gradient Boosting Machine (GBM) for Boosting, Bayesian Additive Regression Trees (BART) for Bayesian ensembles, Random Forest (RF) for Bagging, and Support Vector Machines (SVM) as optimal margin classifiers. This selection allows contrasting methodologies and identifying the most suitable approach for the microfinance context. The use of supervised learning is justified because the problem has historical labels of default and non-default, enabling predictions directly applicable to credit decision-making. Performance was assessed using metrics such as Cohen's Kappa, Geometric Mean, and F1-score. Results show that GBM delivers the most consistent performance, BART achieves the best F1-score, and SVM excels in geometric precision. These findings validate the effectiveness of supervised learning in segmenting credit risk, optimizing operational management, and laying the foundation for incorporating artificial intelligence agents to monitor payments in real time and reduce losses from default.