3. Producción
Browse
4 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Determinants of Market Power in the Peruvian Regulated Microfinance Sector(Springer, 2020-12-01)The objective of this study is to analyze the evolution and determinants of market power in Peru’s regulated microfinance sector during the period of January 2003 to June 2016. We estimate both a conventional Lerner index (LICON) and an efficiency-adjusted Lerner index (LIADJ) using information from a wide panel of microfinance institutions (MFIs), thus finding that the LIADJ is significantly greater than the LICON. This result confirms that not considering MFIs’ inefficiency leads to an underestimation of their market power. Both indices decreased until 2014, which indicates that regulated MFIs’ market power decreased significantly for more than a decade. Beginning in 2015, market power significantly grew; the largest entities as well as those with the highest efficiency have greater market power. This last result evidences the fulfillment of the efficient structure (ES) hypothesis. In addition, a less elastic demand for microcredit, a lower default risk, as well as the processes of mergers, takeovers, and changes in the business structure of some MFIs, increase market power. Finally, the MFIs that operate in localized areas exhibit greater market power. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Market power, social welfare, and efficiency in the Peruvian microfinance(Springer Science and Business Media Deutschland GmbH, 2024-04-01)This study quantifies the social welfare loss caused by market power in Peru’s regulated microfinance industry and analyzes its effect on microfinance institutions’ (MFIs) efficiency from 2003 to 2019. We estimate the efficiency-adjusted Lerner index as a measure of market power and obtain efficiency scores via cost and profit stochastic frontiers estimation using data from a wide panel of MFIs. Additionally, to analyze the effect of market power on the MFI’s efficiency, we estimate a fixed effects model with instrumental variables to correct the endogeneity problem. The results show that the welfare loss due to market power in Peru’s regulated microfinance industry has increased from 0.12% of GDP in 2003 to 0.27% in 2019. It is also found that market power positively affects Peruvian MFIs’ efficiency. Therefore, reducing market power leads to a welfare gain by lowering the social welfare loss (Harberger’s triangle) and a welfare loss due to decreased efficiency in MFIs. However, we find that reducing market power leads to a positive net effect on social welfare due to greater welfare gain than loss. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, The Nonlinearity of the Relationship Between Competition and the Dual Performance of Regulated Microfinance Institutions in Peru(Springer Nature, 2023-07-01)The objective of this study is to determine whether a nonlinear relationship exists between competition and outreach, as well as, between competition and financial sustainability of Peruvian regulated microfinance institutions (MFIs) from 2003 to 2019. We consider three different competition measures reflecting market power, the geographical presence of MFIs, and market concentration. Our findings are as follows: Market concentration does not affect financial sustainability and outreach, whereas market power has a nonlinear U-shaped relationship with financial sustainability and depth of outreach and a negative linear relationship with outreach breadth. Furthermore, the geographic presence of MFIs has a nonlinear U-shaped relationship with financial sustainability and depth of outreach, while it has a nonlinear inverted U-shaped relationship with outreach breadth. These findings reveal differentiated effects of competition on the performance of MFIs that depend on the level of their market power and their geographic presence in the market. Given the high market power and low geographic presence, on average, of Peruvian MFIs, we find that competition negatively affects their financial sustainability and positively affects their outreach. This study brings to the debate on the effects of competition on MFI performance a new interpretation of these effects based on empirical evidence that reconciles previous empirical results. - 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.