Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Computer Science and Information Technologies
Mainford Mutandavari
Harare Institute of Technology
Computer Science & IT Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Optimizing interconnection call routing: a machine learning approach for cost and quality efficiency Ivy Anesu Mudari; Mainford Mutandavari; Kenneth Chiworera
Computer Science and Information Technologies Vol 7, No 1: March 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v7i1.p56-65

Abstract

This study presents the design and development of an automated least cost routing (LCR) model for telecommunications interconnection calls using machine learning. Leveraging a random forest regressor, the model predicts the most cost-effective call routing path based on pricing and network latency. Trained on real-world call detail records (CDRs) from TelOne Zimbabwe, the model achieved a high R² score of 0.851, with a mean absolute error (MAE) of $0.0482 per minute. Evaluation results demonstrate an average cost reduction of 46.75% compared to traditional routing methods, with prediction times under 0.1 seconds and latency remaining within acceptable thresholds. This work provides a practical, scalable, and efficient solution for telecom operators seeking to reduce interconnection costs and maintain service quality through intelligent routing automation. The model architecture and performance to make it viable for integration into real-time telecom infrastructure.
Predictive model for high-risk healthcare clients and claims frequency Lenias Zhou; Mainford Mutandavari; Lucia Matondora
Computer Science and Information Technologies Vol 6, No 3: November 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v6i3.p346-354

Abstract

Global healthcare spending surged to approximately USD 9.8 trillion in the aftermath of the COVID-19 pandemic, intensifying the need for effective risk management strategies in healthcare insurance. This study proposes a predictive model designed to identify high-risk clients for timely targeted interventions and to forecast claims frequency for optimized resource allocation. A real-world claims dataset from a healthcare insurance provider was utilized. Bayesian optimization was employed to enhance data labelling. A deep learning (DL) model with sigmoid activation was used to classify high-risk clients, while a regression model forecasted claims frequency. The model was trained and validated, and gave an accuracy of 97%, a precision of 95.2%, a recall of 98.1% and an F1-score of 96.6%. The results confirmed the model’s accuracy in identifying high-risk clients and its ability to provide reliable forecasting of future claims frequency. Importantly, the model also provided the reason behind its classification decision, enhancing transparency and trust. This research provides valuable data-driven insights to both the healthcare insurers and clients, giving them the power to stay ahead in managing key risks, which ultimately reduces the cost of healthcare insurance. This work contributed a scalable and interpretable solution for risk prediction in healthcare insurance.
Cloud-based predictive analytics for pension fund performance optimization Beauty Garaba; Mainford Mutandavari; Jerita Chibhabha
Computer Science and Information Technologies Vol 7, No 1: March 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v7i1.p46-55

Abstract

This study introduces a novel, cloud-based predictive analytics framework tailored for pension fund performance management in Zimbabwe. Addressing limitations in traditional actuarial models, the proposed system leverages real-time data pipelines and explainable artificial intelligence (XAI) techniques to enhance forecasting accuracy and transparency. Using regression, classification, and deep learning models, it forecasts member contributions, identifies risks of contribution drops, and predicts member churn. The system’s cloud deployment ensures scalability and interactive integration with tools like Power BI for decision support. This solution significantly advances sustainable pension fund management for emerging economies.
AI health assistant combining transformers and XGBoost for multilingual care Shamiso Simango; Mainford Mutandavari
Computer Science and Information Technologies Vol 7, No 3: November 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v7i3.p353-368

Abstract

Limited healthcare access, shortages of healthcare professionals, and linguistic diversity continue to impede timely symptom assessment and healthcare delivery in low-resource settings such as Zimbabwe. Existing virtual health assistant (VHAs) are frequently cloud-dependent, English-centric, and lack interpretable decision-making, limiting their effectiveness in bandwidth-constrained and privacy-sensitive environments. This study proposes CIMAS HealthMate, a hybrid multilingual VHA that integrates transformer-based natural language processing (NLP) with an explainable extreme gradient boosting (XGBoost) decision model to provide accurate and transparent symptom triage. The framework employs the no language left behind (NLLB) model for offline English–Shona translation, bidirectional encoder representations from transformers (BERT)-based models for intent classification and medical entity recognition, and XGBoost for structured triage recommendation. The system was evaluated using a multilingual symptom corpus and an anonymized electronic health record-style dataset comprising approximately 23,000 patient records. Experimental results achieved translation accuracies of 76.5% for Shona-to-English and 82.2% for English-to-Shona, symptom extraction accuracy of 86.6%, and end-to-end triage accuracy of 93.3% with an F1-score of 93.3%. These findings demonstrate that the proposed hybrid architecture effectively combines multilingual language understanding, interpretable machine learning, and offline deployment to deliver reliable and privacy-preserving triage support. The proposed approach provides a scalable and practical solution for improving equitable digital healthcare services in multilingual, resource-constrained environments.
Co-Authors Beauty Garaba Ivy Anesu Mudari Jerita Chibhabha Kenneth Chiworera Lenias Zhou Lucia Matondora Shamiso Simango