Alternative Risk Scoring Data for Small-Scale Farmers

dc.contributor.authorOtieno, Benjamin
dc.contributor.authorWabwoba, Franklin
dc.contributor.authorMusumba, George
dc.date.accessioned2025-05-10T20:33:51Z
dc.date.issued2023-01
dc.descriptionAlternative Risk Scoring Data for Small-Scale Farmers
dc.description.abstractSmall-scale farmers suffer unfairness during credit risk scoring. This arises from the fact that scoring done using computer machine-learning algorithms has an inherent bias, otherwise called algorithm bias. The data that the small-scale farmers present is another source of bias. This paper explores these data types to bring out the specific challenges with the data and how the same can be remedied. The research findings show that of the possible 23 data types lenders ask from farmers, 14 are regarded as important. Out of these 14, 7 are commonly unavailable while the remaining 7 are not, introducing missing data records. The findings also show that other than the personal/behavioral data that the loan-seeker provides, where the lender asks for historical or environmental data, there is room for the loan-seeker to provide misleading information. This paper proposes 14 data types that can improve the quality of credit risk scoring. The study further proposes using the Internet of things and blockchain to source the environmental and historical data to improve the availability of the missing and outlier challenge in data.
dc.identifier.issn2231-2803
dc.identifier.urihttps://doi.org/10.14445/22312803/IJCTT-V71I1P101
dc.identifier.urihttps://karuspace.karu.ac.ke/handle/123456789/3255
dc.language.isoen
dc.subjectCredit risk scoring
dc.subjectFairness
dc.subjectMissing data
dc.subjectOutliers
dc.subjectAlgorithm bias
dc.titleAlternative Risk Scoring Data for Small-Scale Farmers
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
ABSTRACT.pdf
Size:
54.53 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: