Department of Mathematics and Computer Science

Permanent URI for this communityhttp://192.168.0.58:4000/handle/123456789/46

Browse

Now showing 1 - 19 of 19

An investigation on e-resource utilisation among university students in a developing country:
(AOSIS, 2018) Mawere Talent; Sai Kundai O.S.
Electronic libraries are the recent development in the ever-changing technological world today. Students nowadays have the ability to carry the library wherever they are, their Internet-enabled devices being the only requirement. Most universities worldwide have subscribed to various online databases and other e-resources as a way of availing resources to their students. To their credit, most institutions of higher learning in developing countries have not been left out in this stampede.his study has provided some basic insights on utilisation of e-resources in universities of developing countries. Despite the younger generation being described as digital natives, on the contrary, it is quite evident that their uptake of technological innovations especially in education is quite poor. This research will assist both researchers and management of institutions of higher learning to provide and design amicable solutions to the problem of poor utilisation of e-resources as it highlights the major causes of poor utilisation in the developing country context.
Introduction: Computational Intelligence and Mathematical Modelling for Industry and Commerce
(Great Zimbabwe University, 2025) Nyawo Zvidenga Vongai
g/0000-0003-2603-2273 Abstract - Between July 29 and July 31, 2025, GreatZimbabwe University’s School of Natural Sciences hosted its second International Conference on Computational Intelligence and Mathematics Modelling for Industry and Commerce, themed ‘Unlocking the Potential of the Fourth Industrial Revolution in Knowledge Work.’ The conference venue was the Victoria Falls Safari Lodge in Victoria Falls, Zimbabwe. The Minister of Higher and Tertiary Education, Honourable Dr Fredrick Shava, was the guest of Honour. The theme of the conference reflected the imperative to recalibrate the intellectual framework to respond to technological disruptions in the educational space. Great Zimbabwe University, as a Zimbabwean institution, is alert to the urgency of contextualizing the disruption within the national development agenda. The government of Zimbabwe, through flagship policies such as Heritage Based Education 5.0 and National Development Strategy 1, repositioned universities as engines of industrial transformation and national development. What this means is that institutions of higher learning go beyond teaching and learning, embrace innovation and industrialization. It is in this breath that the 2025 conference was relevant and apt. The fields of Computational Intelligence and Mathematical Modelling are emergent foundational academic disciplines to the implementation of Education 5.0.
Towards a comprehensive framework for enablers and inhibitors of bad news reporting on software projects in state universities in Zimbabwe
(Great Zimbabwe University, 2025) Maseko Melody; Tsokota Theo
Software project status reporting is critical in software project management, yet team members often find it easier to report positive news than negative progress. This research investigates the ‘mum effect’, which refers to the reluctance to report bad news on software projects by project team members. Silence on project bad news has remained a major contributor to project failure in higher learning institutions. This study, therefore, aimed to come up with a framework for the inhibitors and enablers of bad news reporting by project team members on specific academic and administrative software projects within state universities in Zimbabwe. Naturally, it is easier to report positive news than negative progress encountered during the software project life cycle. Following a qualitative, multiple-holistic case study approach, this research employed focus group discussions and key informant interviews with project managers, team members, and system users from three state universities in Zimbabwe. The findings indicate that the main enablers of bad news reporting include open communication, a positive organisational culture, and feedback and motivation to achieve. On the other hand, the results suggest that the main inhibitors of bad news reporting include a lack of communication, fear of punishment, an unfair distribution of work, and a lack of skills. The findings of this study can help institutions understand the dynamics at play in status reporting for software projects. Results from this study contribute to the body of knowledge theoretically and, practically, to status reporting on software project development in institutions of higher learning. This reduces the chances of software project failure and escalation.
Framework for the Upskilling for the 4th Industrial Revolution: Challenges, Curriculum and the Way Forward
(Great Zimbabwe University, 2025) Mafukidze Harry D.; Sadock Brian; Chitiza Kennedy; Nechibvute Action
The Fourth Industrial Revolution (4IR or Industry 4.0) presents a significant shift in the operation of industries and economies. It is a manufacturing paradigm that integrates cyber-physical systems, artificial intelligence (AI), robotics, and the Internet of Things (IoT) to create more intelligent, connected industrial systems. Unlike previous industrial revolutions, 4IR offers unprecedented advances, enabling machines to learn, adapt, and make decisions in manufacturing environments. However, operating, maintaining, and integrating these emerging technologies requires dedicated skill sets to thrive in this new landscape. The purpose of this work is to develop a pedagogical framework to promote key skills needed for the fourth industrial revolution and the implementation of its curriculum in tertiary education institutions in Zimbabwe. Quantitative and qualitative data were collected via stakeholder engagements, online surveys, and interviews with educators and captains of industry. This study developed a comprehensive framework for 4IR education within tertiary institutions from four skill sets: general, soft skills, hard skills, and critical skills. The framework will play a key role in the effective upskilling of communities in the 4IR, especially those in low-resource Sub Saharan regions
Machine Learning Adoption Among Technopreneurs in Gweru, Zimbabwe
(Great Zimbabwe University, 2025) Chapwanya Natsai; Munthali Akim
This paper explored the present condition, operating challenges and facilitators of Artificial Intelligence (AI) and Machine Learning (ML) among Technopreneurs at Gweru, a secondary city in Zimbabwe. The research incorporated the use of qualitative exploratory design and Technology-Organization-Environment (TOE) framework in which semi-structured interviews were held with 23, purposely sampled, Technopreneurs in different fields. The results showed that there is a young-adoption environment, with merely 26 percent of Technopreneurs already taking action with AI/ML, and 35 percent are still in the investigative stages. The sectoral analysis showed that there was more implementation in fintech (37.5) and strong exploration in agritech (30%). The greatest impediments identified were infrastructural constraints which were common and presented as an untrustworthy power, an expensive and slow internet, and expensive cloud service. The other impediments were critical knowledge gaps that require informal learning and lack of familiarity with AI/ML ventures by investors. On the other hand, collaborative peer learning networks, resource sharing and incremental adoption models became some of the important enablers. Specifically, the paper has emphasized the exponential nature of an "AI divide" necessitated by computational needs and suggested locally based suggestions, such as the creation of AI hubs, the development of local cloud infrastructure, formalizing training and mentorship, and training investors on how to faster accelerate AI-based Technopreneurship. This study bridged a significant gap in the knowledge on AI/ML adoption outside of main sources of innovation in emerging economies.
A Conceptual Framework for Integrating AI, IoT, and Blockchain to Accelerate Zimbabwe's Sustainable Development: An ICT4D Perspective
(Great Zimbabwe University, 2025) Manjeese Caleb
Information and Communication Technology for Development (ICT4D) is the use of technology with a developmental agenda, especially in the underserved regions and has been instrumental in sustainable development. Combined with Artificial Intelligence (AI), the Internet of Things (IoT), and Blockchain (BC), there has been a new dimension to sustainable development as new prospects are presented by the three technologies in synergy. AI has the capability to provide technicians with new ways of solving challenges efficiently. Industries like health, education and agriculture can be revolutionized as tailor made solutions boost decision making and productivity. IoT can guarantee smooth data exchange, real time monitoring and automation thereby increasing productivity and saving costs. BC is a technology that guarantees transparency, accountability and trust during transacting digitally thus making it ideal for use in governance, finance and supply chain management. A qualitative approach was used to gather opinions from a sample of ICT4D practitioners and stakeholders to gauge the perceived impact of AI, IoT, and Blockchain on sustainable development and to explore possible opportunities available with the combined technologies. In-depth interviews were conducted with experts in the field to gather detailed insights on the success factors for AI, IoT and BC, what considerations in designing a framework, and framework suitability to the integration of the three technologies. The results indicated that AI, IoT, and Blockchain have the potential to positively impact sustainable development in various aspects, including increased efficiency, improved decision-making, and enhanced innovation. For the integration framework to bring positive results, it needs to consider ICT4D and sustainable development components such as local context, capacity building, and green technology.
Numerical Computation of Ruin Probability Using Hybrid Extreme Learning Machine And Whale Optimization Algorithm
(Great Zimbabwe University, 2025) Majeke Felix; Nyamambishi Tinashe; Chikodza Eriyoti; Paul Sambo
Accurate estimation of ruin probabilities remains a fundamental challenge in actuarial risk theory, particularly when claim-size distributions do not admit closed form solutions. In such cases, numerical and approximation techniques are essential for evaluating infinite-time ruin probabilities in classical surplus processes. In this study, we propose a hybrid learning framework that integrates an Improved Extreme Learning Machine (IELM) with the Whale Optimization Algorithm (WOA). While ELM-based models offer fast training, their performance is sensitive to random initialization of hidden-layer parameters and network configuration. Incorporating WOA provides a structured global search to optimize hidden-layer selection and parameter initialization, thereby enhancing stability and predictive accuracy. The ruin probability satisfies a renewal-type integro– differential equation, which is approximated using a trigonometric neural network representation. Convolution terms in the renewal structure are computed via numerical quadrature, allowing the framework to handle general claim size distributions without restrictive assumptions. Optimization minimizes the mean squared approximation error, guiding WOA to identify network configurations that yield accurate and stable estimates. We validate the approach through numerical experiments under exponential, Weibull, and Pareto claim-size distributions. Across all scenarios, the hybrid ELM–WOA model consistently outperforms the standard ELM with random initialization, achieving lower mean absolute error (MAE) and root mean square error (RMSE) while maintaining computational efficiency. These results demonstrate that coupling neural-network approximation with metaheuristic optimization offers a robust and practical alternative for computing ruin probabilities in complex actuarial risk models, particularly where analytical solutions are unavailable.
Driving Education 5.0 through Green Boardrooms: Evaluating the Adoption and Impact of Advanced Technologies in Zimbabwean Higher Education Institutions
(Great Zimbabwe University, 2025) Marima Ivy Jean
This study explored the integration of advanced technologies in education and their potential in creating sustainable and eco-friendly practices. Evidence from research revealed a determined shift towards “green governance” among sampled institutions, with main drivers being moving towards convergence of “environmental sustainability”, “Education 5.0” policy, and a necessity for institutional efficiency in the digital world. Extant literature revealed that green boardrooms support progressive solutions to minimize environmental impact while intensifying collaboration, productivity, and decision-making. In our study, the main technologies explored included cloud computing, blockchain, AI & Big Data, and Internet of Things. Unlike prior studies, which mainly focused on the adoption of advanced digital technology in the learning environment, our study explored the level of adoption of advanced digital technologies in Higher Education Institutions to promote green boardrooms. We applied an exploratory approach with a pragmatic paradigm and utilized a mixed-method design. The major challenge identified in our study was the deployment gap that prevailed, where there was high paper reduction, but more power intensive hardware remained. Qualitative insights identified the high cost of technology and infrastructure, a human capital skills gap, and poor connectivity to neutralize the efficiency gains of digital tools. Ultimately, the study confirmed that green governance in Zimbabwean Higher Education Institutions is currently more paperless than sustainable.
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.
The Role of Emerging Technologies in Enhancing Service Delivery among Academic Libraries in Masvingo District
(Great Zimbabwe University, 2025) Chibidi Inos
Rapid advancements in emerging technologies are reshaping how academic libraries operate, improving access, efficiency, and user experience. This study examined the types of emerging technologies adopted in academic libraries in Masvingo District, Zimbabwe, and assessed their impact on service delivery. Using a qualitative phenomenological approach, the study gathered insights from librarians, ICT personnel, library staff, and patrons. Findings revealed that Artificial Intelligence (AI), Cloud Computing, theInternet of Things (IoT), Big Data Analytics, and Radio Frequency Identification (RFID) are the most commonly utilized technologies. Their adoption has led to notable improvements in operational efficiency, faster information retrieval, enhanced user support, and more streamlined resource management. However, limited digital skills, inadequate infrastructure, and resource constraints continue to hinder full-scale implementation. The study recommends targeted staff training, increased investment in digital infrastructure, and broader adoption of emerging technologies to strengthen service delivery in academic libraries.
Artificial Intelligence in the Zimbabwe Banking Sector: A Systematic Literature Review
(Great Zimbabwe University, 2025) Shambira Leonard; Edna Shambira
The study methodology employed a systematic literature review (SLR) based on Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA). The guidelines were used to find the current state of Artificial Intelligence (AI) adoption in the Zimbabwe banking sector. The research employed a structured PRISMA review protocol to search journal articles from Google Scholar, Research gate and Semantic Scholar. Data were also searched from regulatory and Institutional publications, industry reports, and grey literature published between 2015 and 2025. A total of 381 articles were identified, 328 articles were excluded and 53 were included. The review identified AI applications, reasons for AI adoption, benefits which come with AI adoption, challenges in integrating AI applications and governance issues in the Zimbabwean banking sector. Results indicate that AI adoption in the Zimbabwe banking sector is in its early adoption phase used mainly in customer service automation, reporting systems, and basic operational efficiency tools, while advanced applications such as predictive compliance modelling and AI driven credit analytics remain limited. Barriers to AI adoption are skills shortages, data governance concerns, integration challenges, and regulatory uncertainty. The study contributes to the literature by consolidating fragmented data from various sources, and it also identifies research gaps and recommends a future research trajectory and policy recommendations for AI adoption in the Zimbabwe banking sector.
Cybersecurity in the Age of Digital Transformation: Safeguarding Knowledge Work in the 4th Industrial Revolution
(Great Zimbabwe University, 2025) Muwani Tendai Shelton; Njodzi Ranganai; Mutipforo Gracious; Denhere Prosper Tafadzwa; Ruvinga Lawrence; Katsande Chipo
The 4th Industrial Revolution has also been triggered by the high intensity of artificial intelligence (AI), Internet of Things (IoT), and big data, which is bringing a revolution in knowledge work, but also posing unprecedented cybersecurity threats. Even with technological advancement, organizations are finding it difficult to ensure that sensitive intellectual property is not compromised by advanced cyber attacks, which is also a cause of concern to data integrity, privacy and operational resilience. This study project was intended to answer the following questions: How do new technologies in the 4th Industrial Revolution transform the problem of cybersecurity in knowledge-based industries? How can organizations ensure that they reduce cyber risks to embrace digital transformation? How is policy frameworks and the preparedness of the workforce contributing to enhancing cyber defenses? This paper was a crucial point of intersection between cybersecurity and the 4th Industrial Revolution, which provided a glimpse into how knowledge work can be secured in the age of hyperconnectivity. The research establishes certain gaps in IoT and cloud governance and suggests a hybrid system comprising of NIST CSF and Zero Trust principles in knowledge-intensive systems. This paper will use a mixed-methodology in order to assess cybersecurity strategies. It combines case studies, analyses of breach patterns using quantitative data, interviews with experts, and a literature review and interprets the findings in terms of the NIST Cybersecurity Framework, Zero Trust Architecture, and human-centric security models. The results showed that AI and automation bring defensive and attack types; those companies that are adaptive and layered in their security measures also exhibit greater resilience. Regulatory loopholes and lack of skills also negatively impact successful management of cyber risks, and coordinative structures (public-private partnerships) improve the sharing of threat intelligence. Due to the redefinition of knowledge work provided by the 4th Industrial Revolution, active cybersecurity strategies should also transform. This study emphasizes the importance of agile policies, upskilling of work forces, and integrating technology into security to tap all the potential of the revolution in a secure way.
From Policy to Practice: Evaluation of Telecom Cybersecurity Regulation and Capacity in Southern Africa.
(Great Zimbabwe University, 2025) Njodzi Ranganai; Magoso Mercy Nyasha; Chidoko Clainos; Sambo Paul; Mushamainza Zvishamiso; Zivanai Lemias
The authors inquired on the effectiveness of cybersecurity controls and regulations within the telecommunications industry in Southern Africa and expounded the strengths and weaknesses of the effective governance frameworks. Complex cyber threats are much targeted to digital technology infrastructure and resilience is important to provide economic stability, consumer protection as well as national security. The investigation used a mixed method design that includes the surveys of telecom operators, policy documents study, and interviews with regulators and industry actors, the research also determines some crucial tendencies. The findings of the research show the inconsistency of policy implementation in a country, disordered compliance with regulations by telecom operator and lack of enforcement frameworks on a state level. Moreover, the absence of cross border cooperation, resource insufficiency, and the dissimilarity of the institution capabilities prevent the mutuality of cybersecurity activities. The absence of user consciousness that persists also reduces the strength of resilience as the users are still under the threat of phishing, mobile money attacks and SIM-swap fraud. The positive advances in this study also include the emergence of national Computer emergency response teams (CERT), the adoption and congruency of policies with global standards and the increasing political intent to prevent the cyber threat. To sum up, it is important to note that despite the significant improvement, the telecom industry in the region is at the lowest level of cybersecurity. The paper takes into account standardization of cybersecurity at regional level, increased regulatory controls, capacity-building and sensitization efforts through skills and awareness gimmicks, and regional integration to produce a healthier, more sensitive and secure telecom environment in Southern Africa.
AI Readiness Metrics in Public Sector Organizations: Zimbabwe Organizations Case Study Africa
(Great Zimbabwe University, 2025) Njodzi Ranganai; Magoso Mercy Nyasha; Zivanai Lemias; Sambo Paul; Muwani Tendai Shelton
This paper explores Zimbabwe’s public sector AI readiness and preparedness. There is an urgent need to find out the drivers of preparedness since AI is becoming more mainstream in the hands of governments in an attempt to increase governance and service delivery. The methods that the authors use are a combination of mixed approaches that include quantitative surveys of different organizations operating in the public sector and qualitative interviews with some of the stakeholders in the area of focus. The key elements of AI preparation such as skills of the work force, organizational culture, data and technological infrastructure are defined and measured by authors in quantifiable terms. The results indicate that the degree of preparedness in the firms has considerable differences that can be attributed to a combination of diverse factors including the opportunity to train and resource allocation. The research paper provides the urgent need of the customized plans of optimizing the AI application in the state sector in Zimbabwe. In addition to equipping policymakers and government administrators with operational knowledge enabled to achieve innovation and enhance governance, this study may be applied to create successful implementation strategies of AI, since the study may offer an effective metrics framework. Finally, to make sure that the AI technology could be successfully adopted by the public sector organizations to promote the services delivery and communication with citizens, AI Metrics on public sectors as recommended by the authors.
Justice v Corruption: The Judiciary`s Role in the Battle for Economic Prosperity in Zimbabwe
(Great Zimbabwe University, 2025) Masiya Emerge; Machaya Musavengana
Corruption remains a global cancerous disease that undermines economic development while eroding public trust in institutions. In Zimbabwe, corruption has been a persistent issue, with the country scoring 21 out of 100 on the 2024 Corruption Perceptions Index. The economic ramifications are severe, with corruption contributing to inefficiencies in governance, misallocation of resources, and diminished investor confidence. In response to this, Zimbabwe has established several legal instruments and institutions to combat corruption. The paper examines the role of the judiciary, as an independent legal institution in Zimbabwe that is ‘central to the rule of law’, in curbing corruption. The Constitution of Zimbabwe promotes transparency and accountability, with Chapter 13 establishing key anti corruption bodies. Judicial oversight remains the key bottleneck for all anti-corruption enforcement efforts. Using a doctrinal research method, the study analyses existing case law and literature to assess the effectiveness of judicial enforcement in combating corruption. Lee’s General Theory of Law and Development serves as the theoretical framework, providing insights into the regulatory impact of the judiciary and identifying systemic loopholes that hinder anti-corruption efforts. This paper contributes to existing literature by providing a comprehensive analysis of the judiciary’s pivotal role in combating corruption and fostering economic development in Zimbabwe through the lens of Lee`s Theory of Law and Economic Development. The findings of this paper highlight the judiciary’s role as a legal institution in shaping regulatory frameworks and enforcing anti-corruption measures. The paper suggests an integrated approach to combat corruption that is constant of the existing multifaceted frailties to enhance transparency, rebuild public trust, and support sustainable development.
Urbanisation and Inequality in Zimbabwe: A Disaggregated Analysis
(Great Zimbabwe University, 2025) Muneri Ranganai; Mwanyepedza Robert
The world urban population has surpassed the 55 % mark, from 30% in 1950, 50% in 2007, and is projected to exceed 70% by 2050. Urbanisation is generally associated with human development and improved human welfare; however, contemporary literature also links it to increased inequality. This is partly explained by the urban wage premium resulting from rural-urban disparities in access to quality education and labour market unequal dynamics. This study investigates impact of urbanisation on income inequality in Zimbabwe, using 1992-2022 provincial-level disaggregated data. Employing the Fully Modified Ordinary Least Squares (FMOLS) and the Dynamic Ordinary Least Squares (DOLS) models, the study reveals that urbanisation increases income inequalities in Zimbabwe. These findings urban suggest that urbanisation in Zimbabwe is associated with urban decay, unequal access to education, employment opportunities, and other socio-economic amenities. It also reveals insufficient urban infrastructure, whose supply fails to keep pace with urban population growth. The study prescribes well-planned urban expansion, inclusive development policies, a strong rural development strategy and service delivery improvements in rural and peri-urban and informal settlement areas. Addressing inequalities in access to quality education and socio-economic opportunities, coupled with data-driven policy decisions and increased community participation remains critical to ameliorate inequalities associated with the urban expansion.
An Application of the Naïve Bayes Algorithm as a Tool for Predicting Cases of Poaching in Wildlife Management
(Great Zimbabwe University, 2025) Vengesai Sikozho; Winji Lucia; Mawere Talent
Poaching presents a serious threat to both wildlife management and tourism sustainability, making proactive, data driven interventions necessary. This study explores the application of predictive data mining in crime management within Zimbabwe’s wildlife sector, focusing on the use of the Naïve Bayes algorithm to predict poaching occurrences in protected areas. Secondary data from ranger patrol logs, incident reports, weather observations, and spatial datasets were collected from selected wildlife management areas between 2015–2023. The data was cleaned, integrated, and underwent feature engineering before it was modelled with the Naïve Bayes classifier to identify patterns of poaching risk. After evaluation, the model achieved an accuracy of 87%, precision of 0.84, recall of 0.82 and a ROC (AUC) curve of 0.89 showing strong predictive capabilities. Key predictors included weather conditions, patrol intensity and recent poaching history. The model’s false positives (predicting poaching where none occurs) may result in extra patrols, while false negatives (failing to predict actual poaching) put wildlife at greater risk, showing the importance of balancing prediction sensitivity and resource allocation. These findings show that predictive data mining can promote crime prevention, enhance resource allocation, and reinforce wildlife protection in Zimbabwe. The study recommends including predictive analytics into conservation planning to protect the country’s wildlife resources.
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.
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.