Prediction of SACCOS Failure in Tanzania using Machine Learning Models

Authors

  • Cosmas Magashi Department of Information Technology System Development and Management (ITSDM), Nelson Mandela African Institution of Science and Technology (NM-AIST), Tanzania
  • Johnson Agbinya School of Information, Technology, and Engineering, Melbourne Institute of Technology (MIT), Australia
  • Anael Sam Department of Information Technology System Development and Management (ITSDM), Nelson Mandela African Institution of Science and Technology (NM-AIST), Tanzania
  • Jimmy Mbelwa Department of Computer Science and Engineering, University of Dar es Salaam, Tanzania
Volume: 14 | Issue: 1 | Pages: 12887-12891 | February 2024 | https://doi.org/10.48084/etasr.6696

Abstract

Savings and Credit Co-Operative Societies (SACCOS) are seen as viable opportunities to promote financial inclusion and overall socioeconomic development. Despite the positive outlook for socioeconomic progress, recent observations have highlighted instances of SACCOS failures. For example, the number of SACCOS decreased from 4,177 in 2018 to 3,714 in 2019, and the value of shares held by SACCOS members in Tanzania dropped from Tshs 57.06 billion to 53.63 billion in 2018. In particular, there is limited focus on predicting SACCOS failures in Tanzania using predictive models. In this study, data were collected using a questionnaire from 880 members of SACCOS, using a stratified random sampling technique. The collected data was analyzed using machine learning models, including Random Forest (RF), Logistic Regression (LR), K Nearest Neighbors (KNN), and Support Vector Machine (SVM). The results showed that RF was the most effective model to classify and predict failures, followed by LR and KNN, while the results of SVM were not satisfactory. The findings show that RF is the most suitable model to predict SACCOS failures in Tanzania, challenging the common use of regression models in microfinance institutions. Consequently, the RF model could be considered when formulating policies related to SACCOS performance evaluation.

Keywords:

SACCOS, microfinance, machine learning, prediction, classification

Downloads

Download data is not yet available.

References

M. J. Zikalala, "The role of savings and credit cooperatives in promoting access to credit in Swaziland," MSc Thesis, University of Pretoria, South Africa, 2016.

"The role of SACCOS’ microcredits in the empowerment of female-headed households in the Njombe Region, Tanzania," African Journal of Applied Research, vol. 8, no. 1, pp. 200-212, Aug. 2022.

R. A. Effiom, "Impact of cooperative societies in national development and the Nigerian economy," Global Journal of Social Sciences, vol. 13, no. 1, pp. 19–29, 2014. DOI: https://doi.org/10.4314/gjss.v13i1.2

M. D. Kwai and J. K. Urassa, "The contribution of savings and credit cooperative societies to income poverty reduction: A case study of Mbozi District, Tanzania," Journal of African Studies and Development, vol. 7, no. 4, pp. 99–111, Apr. 2015.

A. Addae-Korankye, "Causes and control of loan default/delinquency in microfinance institutions in Ghana," American International Journal of Contemporary Research, vol. 4, no. 12, pp. 36–45, 2014.

M. Semaw Henock, "Financial sustainability and outreach performance of saving and credit cooperatives: The case of Eastern Ethiopia," Asia Pacific Management Review, vol. 24, no. 1, pp. 1–9, Mar. 2019. DOI: https://doi.org/10.1016/j.apmrv.2018.08.001

N. Marwa and M. Aziakpono, "Technical and Scale Efficiency of Tanzanian Saving and Credit Cooperatives," The Journal of Developing Areas, vol. 50, no. 1, pp. 29–46, 2016. DOI: https://doi.org/10.1353/jda.2016.0000

M. T. Pasara, A. Makochekanwa, and S. H. Dunga, "The Role of Savings and Credit Cooperatives (SACCOs) on Financial Inclusion in Zimbabwe," Eurasian Journal of Business and Management, vol. 9, no. 1, pp. 47–60, 2021. DOI: https://doi.org/10.15604/ejbm.2021.09.01.004

Mjatta, G.T, Akarro, and R.R.J, "Traits Associated with the Success or Failure of Emerging SACCOS in Tanzania : A Case of Four Regions in Tanzania Mainland," Global Journal of Commerce & Management Perspective, vol. 5, no. 4, pp. 29–38, 2016.

P. Anania and A. Gikuri, "SACCOS and Members’ Expectations: Factors Affecting SACCOS Capacity to Meet Members’ Expectations," presented at the Co-operative Research Workshop - Moshi Co-operative University, Tanzania, Mar. 2015.

J. Anderson, D. Hopkins, and M. Valenzuela, "The role of financial services in youth education and employment.," Consultative Group to Assist the Poor, Washington, DC, USA, Working Paper, Jun. 2019.

C. Magashi, A. Sam, J. Agbinya, and J. Mbelwa, "Indicative Factors for SACCOs Failure in Tanzania," Engineering, Technology & Applied Science Research, vol. 13, no. 4, pp. 11177–11181, Aug. 2023. DOI: https://doi.org/10.48084/etasr.5989

A. Gikuri and M. B. Sanka, "Status of SACCO’s growth before and during JK Billion Fund In Tanzania Mainland," International Journal of Community and Cooperative Studies, vol. 6, no. 2, pp. 8–18, Jun. 2018.

T. M. Mallya, "The Role of SACCOS on Improving Livelihood of Clients in Moshi Rural District.," MSc Thesis, The Open University of Tanzania, 2020.

A. Bryman, Social Research Methods 4th ed. Oxford University Press, 2001.

C. R. Kothari, Research Methodology: Methods and Techniques. New Delhi, India: New Age International, 2004.

A. Rahman and M. N. A. Khan, "A Classification Based Model to Assess Customer Behavior in Banking Sector," Engineering, Technology & Applied Science Research, vol. 8, no. 3, pp. 2949–2953, Jun. 2018. DOI: https://doi.org/10.48084/etasr.1917

S. Joseph, N. Mduma, and D. Nyambo, "A Deep Learning Model for Predicting Stock Prices in Tanzania," Engineering, Technology & Applied Science Research, vol. 13, no. 2, pp. 10517–10522, Apr. 2023. DOI: https://doi.org/10.48084/etasr.5710

T. S. Mian, "Evaluation of Stock Closing Prices using Transformer Learning," Engineering, Technology & Applied Science Research, vol. 13, no. 5, pp. 11635–11642, Oct. 2023. DOI: https://doi.org/10.48084/etasr.6017

Downloads

How to Cite

[1]
C. Magashi, J. Agbinya, A. Sam, and J. Mbelwa, “Prediction of SACCOS Failure in Tanzania using Machine Learning Models”, Eng. Technol. Appl. Sci. Res., vol. 14, no. 1, pp. 12887–12891, Feb. 2024.

Metrics

Abstract Views: 159
PDF Downloads: 282

Metrics Information

Most read articles by the same author(s)