Browsing by Author "Magashi, Cosmas"

Now showing 1 - 2 of 2

Indicative Factors for SACCOs Failure in Tanzania
(Engineering, Technology & Applied Science Research, 2023-08-09) Magashi, Cosmas; Sam, Anael; Agbinya, John; Mbelwa, Jimmy
SACCOs are viewed as a feasible opportunity toward financial inclusion in an economy where most of the citizens are poor, as they are very essential for the socio-economic development of members, the community, and the world at large. However, SACCOs sometimes do not realize the expected socio-economic potential, especially when they fail. This study aimed to comprehensively assess financial and non-financial factors, at institutional and personal levels, that contribute to the failure of SACCOS in Tanzania. The data were collected using a questionnaire on 5,000 members of SACCOs, obtained using stratified random sampling. Data collected were analyzed using descriptive statistics and binary logistic regression. The findings showed that both financial and non-financial factors, at personal and institutional levels, had a statistically significant and positive relationship with the failure of SACCOs. Therefore, the performance of SACCOs and other Microfinance Financial Institutions (MFIs) should be addressed from a comprehensive view of both financial and non-financial factors, at personal or institutional levels. In other words, the failure of MFIs should be addressed from a holistic point of view.
Prediction of SACCOS Failure in Tanzania using Machine Learning Models
(Engineering, Technology and Applied Science Research, 2024-02-08) Magashi, Cosmas; Agbinya, Johnson; Sam, Anael; Mbelwa, Jimmy
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.