Alternative Risk Scoring Data for Small-Scale Farmers

© 2023 by IJCTT Journal
Volume-71 Issue-1
Year of Publication : 2023
Authors : Benjamin Otieno, Franklin Wabwoba, George Musumba
DOI :  10.14445/22312803/IJCTT-V71I1P101

How to Cite?

Benjamin Otieno, Franklin Wabwoba, George Musumba, "Alternative Risk Scoring Data for Small-Scale Farmers," International Journal of Computer Trends and Technology, vol. 71, no. 1, pp. 1-7, 2023. Crossref,

Small-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.

Credit risk scoring, Fairness, Missing data, Outliers, Algorithm bias.


[1] Awni Hannun, The Label Bias Problem, 2020.
[2] Heinrich Jiang, and Ofir Nachum, “Identifying and Correcting Label Bias in Machine Learning,” International Conference on Artificial Intelligence and Statistics, vol. 108, pp. 702-712, 2020.
[3] Fernando Martínez-Plumed et al., “Fairness and Missing Values,” arXiv preprint arXiv:1905.12728, 2019. Crossref,
[4] Muhammad Aurangzeb Ahmad et al., “Fairness in Machine Learning for Healthcare,” In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3529-3530, 2020. Crossref,
[5] D. J. Hand, and W. E. Henley, “Statistical Classification Methods in Consumer Credit Scoring: A Review,” Journal of the Royal Statistical Society: Series A (Statistics in Society) vol. 160, no. 3, pp. 523-541, 1997
[6] Kolade Kamilu Bolarinwa, and E. O. Fakoya, “Impact of Farm Credit on Farmers Socio-Economic Status in Ogun State Nigeria,” Journal of Social Sciences, vol. 26, no. 1, pp. 67-71, 2011. Crossref,
[7] Saima Ayaz et al., “Role of Agricultural Credit on Production Efficiency of Farming Sector in Pakistan - A Data Envelopment Analysis,” Pakistan Journal of Life and Social Sciences, vol. 9, no. 1, pp. 38-44, 2011.
[8] Marie-Laure Charpignon, Enguerrand Horel, and Flora Tixier, “Prediction of Consumer Credit Risk,” 2014.
[9] Bowen Baker, “Consumer Credit Risk Modeling,” MIT Departments of Physics and EECS, 2015.
[10] Fabio Wendling Muniz de Andrade, and Abraham Laredi Sicsú, “A Credit Risk Model For Consumer Loans Portfolios,” Latin American Business Review, vol. 8, no. 3, pp. 75-91, 2008. Crossref,
[11] Fernando Martínez-Plumed et al., “Fairness and Missing Values,” Valencian Research Institute for Artificial Intelligence (VRAIN), 2019.
[12] Cole R. Gustafson, Ronald J. Beyer, and David M. Saxowsky, “Credit Evaluation: Investigating the Decision Process of Agricultural Loan Officers,” in Regional Research Committee NC-161, Manhattan, 1992.
[13] Benjamin H. Otieno, Franklin Wabwoba, and George Musumba, “Towards Small-Scale Farmers Fair Credit Scoring Technique," in IST-Africa Conference, pp. 1-11, 2020.
[14] Marc H. Gorelick, “Bias Arising from Missing Data in Predictive Models,” Journal of Clinical Epidemiology, vol. 59, no. 10, pp. 1115- 1123, 2006. Crossref,
[15] Savitha Sam Abraham, "Fair Outlier Detection," arXiv preprint arXiv:2005.09900, 2020. Crossref,
[16] Philip Ngare, Martin Kweyu, and Chris Huka, Modelling Risk of Financing Agribusiness in Kenya, Kenya Bankers Association, 2015.
[17] S. Balamurugan et al., "Internet of Agriculture: Applying IoT to Improve Food and Farming Technology," International Research Journal of Engineering and Technology, vol. 03, no. 10, pp. 713-719, 2016.
[18] K. A. Patil, and N. R. Kale, “A Model for Smart Agriculture Using IoT,” in IEEE 26th International Symposium on Industrial Electronics (ISIE), 2017.
[19] Congduc Pham, Abdur Rahim, and Philippe Cousin, “Low-Cost, Long-Range Open Iot for Smarter Rural African Villages,” in IEEE International Smart Cities Conference, pp. 1-6, 2016. Crossref,
[20] Nelson Bore et al., “ADW: Blockchain-enabled Small-scale Farm Digitization,” arXiv preprint arXiv:2003.06862, 2020. Crossref,
[21] Abderahman Rejeb, “Blockchain Potential in Tilapia Supply Chain in Ghana,” Acta Technica Jaurinensis, vol. 11, no. 2, pp. 104-118, 2018.
[22] Jeremiah Blocki, and Hong-Sheng Zhou, “Designing Proof of Human-Work Puzzles for Cryptocurrency and Beyond,” Theory of Cryptography Conference, Berlin, Heidelberg, 2016. Crossref,
[23] U. Römer, and O. Mußhoff, “Can Agricultural Credit Scoring for Microfinance Institutions be Implemented and Improved by Weather Data?,” Discussion Contribution, Georg-August University of Göttingen, Department of Agricultural Economics and Rural Development (DARE), Göttingen, 2017.
[24] Arindam Bandyopadhyay, Credit Risk Models for Managing Bank’s Agricultural Loan Portfolio, National Institute of Bank Management, Pune, India, 2007.
[25] Women’s World Banking, "Credit Scoring in Microfinance," 2003.
[26] Andrea Berger, and Marisa Barrera, Credit Scoring for Microenterprise Lenders, The Aspen Institute, 2007.
[27] USAID, A Handbook for Developing Credit Scoring System in Microfinance Context, USAID, 2006.