Upper bounds on default probability for small cooperative loan books with no observed defaults

Savings and credit cooperatives (SACCOs) often hold small loan books with no formal defaults on record, for example because loans are fully collateralised or guaranteed by other members. A zero default count is not a default probability of zero. This technical note collects four standard ways to compute an upper bound on the default probability in that situation (the independent bound of Pluto and Tasche, a Bayesian bound with a uniform prior, a one-factor correlated bound and a beta-binomial bound), applies them to book sizes typical of an Ethiopian SACCO, and shows how much the answer depends on the correlation assumption. For 50 loans and no defaults, the 90% upper bound is 4.50% if defaults are independent and 5.2% to 9.2% under one-factor correlation of 0.03 to 0.16. Code and synthetic data: https://github.com/Nahombehailu22/sacco-credit-bounds (MIT licence; no member data).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-01
DOI
https://doi.org/10.5281/zenodo.23864350
Primary Topic
Credit Risk and Financial Regulations
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Upper bounds on default probability for small cooperative loan books with no observed defaults

Nahom Behailu Geremew
Zenodo (CERN European Organization for Nuclear Research)
Credit Risk and Financial Regulations
article

Upper bounds on default probability for small cooperative loan books with no observed defaults

Nahom Behailu Geremew
article en

Abstract

Savings and credit cooperatives (SACCOs) often hold small loan books with no formal defaults on record, for example because loans are fully collateralised or guaranteed by other members. A zero default count is not a default probability of zero. This technical note collects four standard ways to compute an upper bound on the default probability in that situation (the independent bound of Pluto and Tasche, a Bayesian bound with a uniform prior, a one-factor correlated bound and a beta-binomial bound), applies them to book sizes typical of an Ethiopian SACCO, and shows how much the answer depends on the correlation assumption. For 50 loans and no defaults, the 90% upper bound is 4.50% if defaults are independent and 5.2% to 9.2% under one-factor correlation of 0.03 to 0.16. Code and synthetic data: https://github.com/Nahombehailu22/sacco-credit-bounds (MIT licence; no member data).

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 9%
Credit Risk and Financial Regulations
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon