Optimization of the System of Allocation of Overdue Loans in a Sub-Saharan Africa Microfinance Institution

Andreia Araújo, Filipe Portela, Filipe Alvelos and Saulo Ruiz
Additional contact information
Andreia Araújo: Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal
Filipe Portela: Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal
Filipe Alvelos: Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal
Saulo Ruiz: Pelican Rhythms, 4100-456 Porto, Portugal

Future Internet, 2022, vol. 14, issue 6, 1-19

Abstract: In microfinance, with more loans, there is a high risk of increasing overdue loans by overloading the resources available to take actions on the repayment. So, three experiments were conducted to search for a distribution of the loans through the officers available to maximize the probability of recovery. Firstly, the relation between the loan and some characteristics of the officers was analyzed. The results were not that strong with F1 scores between 0 and 0.74, with a lot of variation in the scores of the good predictions. Secondly, the loan is classified as paid/unpaid based on what prediction could result of the analysis of the characteristics of the loan. The Support Vector Machine had potential to be a solution with a F1 score average of 0.625; however, when predicting the unpaid loans, it showed to be random with a score of 0.55. Finally, the experiment focused on segmentation of the overdue loans in different groups, from where it would be possible to know their prioritization. The visualization of three clusters in the data was clear through Principal Component Analysis. To reinforce this good visualization, the final silhouette score was 0.194, which reflects that is a model that can be trusted. This way, an implementation of clustering loans into three groups, and a respective prioritization scale would be the best strategy to organize and assign the loans to maximize recovery.

Keywords: assignment problem; data mining; microfinance (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/6/163/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/6/163/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:6:p:163-:d:825368

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().