Browsing by Author "Makoni Tendai"

Now showing 1 - 3 of 3

Development of a Health Insurance Premium Prediction Model using Machine Learning
(Great Zimbabwe University, 2025) Makoni Tendai; Rukwava Caroline; Mawere Talent; Chinofunga Peter Tinashe
In Zimbabwe’s evolving healthcare landscape, accurately determining health insurance premiums is critical to improving affordability, reducing risk imbalances, and increasing coverage, particularly amid economic constraints and rising health costs. Traditional actuarial models often struggle to represent the complex, non-linear relationships among socioeconomic, health, and lifestyle variables prevalent in the Zimbabwean population. This paper aims to develop a machine learning model that more precisely and rationally predicts health insurance premiums. Five supervised regression algorithms, Linear Regression (LR), LASSO Regression (LASSO), K-Nearest Neighbours (KNN), Random Forest (RF), and Gradient Boosting (GB), are evaluated for their effectiveness using a representative health insurance dataset that includes demographic and health-related attributes relevant to Zimbabwe. Models were assessed based on their Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) values. The results show that ensemble learning methods, particularly Gradient Boosting, significantly outperform traditional linear models, achieving the highest predictive accuracy. Key predictors of premium costs were identified as chronic illnesses, smoking status, and the number of dependents, variables that are particularly pertinent in local risk assessment. This paper advances health insurance analytics in Zimbabwe by providing evidence that machine learning can support more transparent, data-driven, and context-sensitive premium determination. The findings help insurers, policymakers, and healthcare stakeholders aiming to expand coverage and improve trust in private and public insurance schemes.
From Classroom to Online: Security, Privacy, and Broader Challenges in Higher Education in the Global South
(Great Zimbabwe University, 2025) Mawere Talent; Phiri Chimwemwe; Makoni Tendai
The COVID- 19 pandemic forced higher education institutions worldwide to transition abruptly from traditional classroom teaching to online learning, a shift that exposed significant vulnerabilities in digital readiness, particularly in the Global South, where ICT infrastructure and technological adoption remain underdeveloped. This study investigates the security, privacy, and broader implementation challenges faced by students and lecturers during this transition, using the Technology Readiness and Acceptance Model (TRAM) as the guiding framework. Employing a quantitative case study approach, data were gathered from 1,248 respondents and analyzed using Structural Equation Modelling (SEM) in Amos. The findings reveal that all thirteen hypothesized relationships were statistically significant, demonstrating that perceived usefulness, ease of use, and institutional readiness strongly influence e- learning adoption. Conversely, security and privacy concerns were found to heighten discomfort, diminish optimism, and impede readiness for online learning. The study highlights the urgent need for robust digital infrastructure, comprehensive cybersecurity measures, and targeted digital literacy training to enhance trust and promote sustainable e- learning integration in resource- constrained contexts.
Projection of HIV Incidence Trends in Zimbabwe Using Incremental Mixture Importance Sampling
(Great Zimbabwe University, 2025) Chinofunga Peter Tinashe; Chipepa Fastel; Makoni Tendai; Gwatidzo Sinikiwe; Mawere Talent; Chirima Justin
HIV prevalence has remained high in Zimbabwe due to continued use of Antiretroviral therapy (ART). Incidence is now a better measure of the programmatic efforts in response to the epidemic. Mathematical modeling remains the main tool for assessing incidence trends. Secondary data transmembrane (TM) one, that is [TM1] analysis, was conducted using incremental mixture sampling (IMIS). Absolute neutrophil count (ANC) [TM2] prevalence data were used for modeling incidence in the general population. The force of infection in 6 of the 10 provinces in Zimbabwe is projected to fall below 1%. ART has significantly helped in reducing the force of infection in the country. With continued use of ART coupled with other programmatic interventions, HIV incidence can be reduced to very low levels in many parts of the country. HIV incidence in Zimbabwe varies by geographical location. Matabeleland South province has the highest cumulative incidence in the country, while Harare province has the lowest. There is a difference in the force of infection between rural and urban areas. The force of infection remains high in the Matabeleland South, Midlands, Bulawayo, and Mashonaland East provinces. An increase in the use of ART reduces HIV incidence. Scaling up HIV counselling and testing activities in provinces or districts with high force of infection will help reduce the force of infection in these areas a the number of people on ART will increase, consequently reducing the infectiousness of infected people. Intervention programmes should address cultural differences.