Rural Micro Credit Assessment using Machine Learning in a Peruvian microfinance institution

Condori-Alejo, Henry Ivan; Aceituno-Rojo, Miguel Romilio; Alzamora, Guina Sotomayor

doi:10.1016/j.procs.2021.04.117

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unlike traditional statistical methods, the ML techniques have relevant importance due to their limited dependence on assumptions and their importance in processes automation (Li et al, 2020). The application of machine learning in our study is also supported by the fact that this is widely used in the literature of credit risk evaluation in microfinance (Bakshi, 2021; Beketnova, 2020; Bhatore et al, 2020; Condori‐Alejo et al, 2021; Ruiz et al, 2017). Given the qualities that machine learning possesses, we contrast the result from the traditional logistic regression with that from the machine learning approach.…”

Section: Introductionsupporting

confidence: 61%

“…ML is at the intersection of many other disciplines like statistics and computer science. While traditional statistical models focus on metrics such as R 2 , p-values and statistical significance, the ML techniques focus on out-of-sample forecasting and the biasvariance trade-off (Gogas & Papadimitriou, 2021).Unlike traditional statistical methods, the ML techniques have relevant importance due to their limited dependence on assumptions and their importance in processes automation (Li et al, 2020).The application of machine learning in our study is also supported by the fact that this is widely used in the literature of credit risk evaluation in microfinance (Bakshi, 2021;Beketnova, 2020;Bhatore et al, 2020;Condori-Alejo et al, 2021;Ruiz et al, 2017). Given the qualities that machine learning possesses, we contrast the result from the traditional logistic regression with that from the machine learning approach.…”

Section: Logical Development Of the Researchmentioning

confidence: 62%

See 1 more Smart Citation

Kinship, gender and social links impact on micro group lending defaults

et al. 2023

View full text Add to dashboard Cite

Joint liability aspires to improve micro-loan performance through the support of, and pressure from, the group borrowers. This paper examines how the group composition, in terms of the mixture of kinship (Family) ties and social (Friends and Neighbours) ties among the borrowers, affects the default rates. Using binary logistics regression and three machine learning models, responses from 507 group micro-loan borrowers from four major Moroccan cities were analysed. The results show that the stronger the family and kinship ties are within a loan group, the higher is the default rate. On the contrary, the stronger the social ties are among the group, the lower is the default rate.Other key findings include that the diversion of fund usage from investment to consumption is not found to significantly cause default. Also, loan default can be a consequence of borrowers' strategic choice rather than financial distress.As compared to the female members, male borrowers are found to be causing higher default rates. Interestingly, the gender-related default rates are lower when more of the male borrowers are only socially related. Finally, group size is found to be positively associated with default. Our findings can help microfinance institutions refine their lending policies and guidance on groups' composition and size to reduce default rates.

show abstract

Section: Introductionsupporting

confidence: 61%

Section: Logical Development Of the Researchmentioning

confidence: 62%

Kinship, gender and social links impact on micro group lending defaults

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Credit score assignment As in classical banking, the score is used to determine whether or not to approve a loan. The loan approval decision problem has been modeled as a binary classification problem, which is then solved using machine learning methods, such as discriminant analysis [40], logistic regression [41,42] and neural networks [43][44][45]. However, such system often cannot work when there is missing data because the credit score assignment require all the features to be present, and missing data have to be imputed.…”

Section: A Additional Related Workmentioning

confidence: 99%

A Learning and Control Perspective for Microfinance

Kurniawan¹,

Deng²,

Chakraborty³

et al. 2022

Preprint

View full text Add to dashboard Cite

Microfinance in developing areas such as Africa has been proven to improve the local economy significantly. However, many applicants in developing areas cannot provide adequate information required by the financial institution to make a lending decision. As a result, it is challenging for microfinance institutions to assign credit properly based on conventional policies. In this paper, we formulate the decision-making of microfinance into a rigorous optimization-based framework involving learning and control. We propose an algorithm to explore and learn the optimal policy to approve or reject applicants. We provide the conditions under which the algorithms are guaranteed to converge to an optimal one. The proposed algorithm can naturally deal with missing information and systematically tradeoff multiple objectives such as profit maximization, financial inclusion, social benefits, and economic development. Through extensive simulation of both real and synthetic microfinance datasets, we showed our proposed algorithm is superior to existing benchmarks. To the best of our knowledge, this paper is the first to make a connection between microfinance and control and use control-theoretic tools to optimize the policy with a provable guarantee.Preprint. Under review.

show abstract

“…O campo de microfinanças mostrou-se um forte instrumento de redução de desigualdade social (Baghdasaryan et al, 2021;Bennouna & Tkiouat, 2019;Medina-Olivares et al, 2021). O microcrédito é um instrumento relevante ao desenvolvimento de comunidades rurais (Condori-Alejo et al, 2021), e entender os fatores que influenciam a inadimplência nesta linha de crédito é fundamental para a perenidade da sua oferta.…”

Section: Logitunclassified

“…O Brasil, por meio do Instituto de Pesquisa Econômica Aplicada (Ipea), adaptou as metas da Agenda 2030 à realidade doméstica (Ipea, 2018), explicitando o acesso a linhas de crédito como um dos meios de se atingir as metas de aumento da produtividade e da renda dos pequenos produtores. Esta importância dada ao crédito é tema recorrente na literatura (Bennouna & Tkiouat, 2019;Condori-Alejo et al, 2021;Kumar et al, 2013;Linh et al, 2019;Twumasi et al, 2020Twumasi et al, , 2021, a qual atribui o acesso ao crédito como instrumento de ganho econômico-social de pequenos produtores e famílias rurais.…”

Section: Introductionunclassified

De Basileia para o campo: estimando a estrutura de dependência de >i<default>/i< em portfólios de crédito rural por meio de cópulas

Rensi¹

View full text Add to dashboard Cite

show abstract

Rural Micro Credit Assessment using Machine Learning in a Peruvian microfinance institution

Cited by 9 publications

References 9 publications

Kinship, gender and social links impact on micro group lending defaults

Kinship, gender and social links impact on micro group lending defaults

A Learning and Control Perspective for Microfinance

De Basileia para o campo: estimando a estrutura de dependência de >i<default>/i< em portfólios de crédito rural por meio de cópulas

Contact Info

Product

Resources

About