Psychometric Credit Scoring in Latin America: Replicated Samples Across Five Countries

Saul Fine

Review of Behavioral Economics2025https://doi.org/10.1561/105.00000206article
AJG 2ABDC B
Weight
0.50

What the paper says

Psychometric credit scoring models tap relevant behavioral data associated with borrowers’ personal character traits. Despite the increased application of psychometric models in recent years, this topic remains largely understudied. In addition, given their behavioral nature, the efficacy of psychometric models may differ across culturally diverse geographic regions, making it difficult to generalize findings from individual local studies alone. The purpose of this study, therefore, was to provide empirical evidence for psychometric scoring in Latin America, based on a total of 26,638 borrowers from five different countries. The results found the psychometric model to be consistently and similarly correlated with loan defaults across all samples. AUCs ranged from 0.629 to 0.767, KSs from 0.201 to 0.416, and default rates decreased monotonically along the score bands. Overall, the results support the usage of psychometric credit solutions in Latin America, particularly with respect to improving financial inclusion among underbanked consumers.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1561/105.00000206

Or copy a formatted citation

@article{saul2025,
  title        = {{Psychometric Credit Scoring in Latin America: Replicated Samples Across Five Countries}},
  author       = {Saul Fine},
  journal      = {Review of Behavioral Economics},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1561/105.00000206},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Psychometric Credit Scoring in Latin America: Replicated Samples Across Five Countries

Flags are reviewed by the Arbiter methodology team within 5 business days.


Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.