Modestus Okwu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Modestus Okwu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Lagouge Kwanda Tartibu
Department of Mechanical Engineering, University of Johannesburg, Johannesburg, South Africa
2 shared publications - Joachim Osheyor Gidiagba
University of Johannesburg, South Africa
1 shared publication - Osheyor Joachim Gidiagba
Department of Mechanical and Industrial Engineering, University of Johannesburg, Johannesburg 2092, South Africa
1 shared publication
Latest Publications
- Open Access
Integrating Machine Learning with Multi-Criteria Decision-Making Models for Sustainable Supplier Selection in Dynamic Supply Chains
Background: Supplier evaluation and selection are pivotal processes in supply chain management, profoundly influencing organisational efficiency and sustainability. This study addresses the limitations of traditional multi-criteria decision-making approaches, particularly the Technique for Order Preference by Similarity to an Ideal Solution, which often lacks dimensional reduction capability and assumes uniform weight distribution across criteria. Methods: To overcome these challenges, a hybrid model integrating non-negative matrix factorisation, random forest, and the Technique for Order Preference by Similarity to an Ideal Solution is developed for supplier evaluation in the pharmaceutical sector. The method first applies non-negative matrix factorisation to condense twenty-four evaluation criteria into eight core dimensions, enhancing analytical efficiency and reducing complexity. Random forest is then employed to derive data-driven weights for each criterion, ensuring accurate prioritisation. Finally, the Technique for Order Preference by Similarity to an Ideal Solution ranks suppliers and provides actionable insights for decision-makers. Results: Results from real-world pharmaceutical data validate the model’s effectiveness and demonstrate superior performance over conventional evaluation methods. Conclusions: The findings confirm that integrating machine learning techniques with established decision-making frameworks enhances precision, interpretability, and sustainability in supplier selection while requiring adequate data quality and computational resources for implementation.
Open AccessIntegrating Machine Learning with Multi-Criteria Decision-Making Models for Sustainable Supplier Selection in Dynamic Supply Chains
Background: Supplier evaluation and selection are pivotal processes in supply chain management, profoundly influencing organisational efficiency and sustainability. This study addresses the limitations of traditional multi-criteria decision-making approaches, particularly the Technique for Order Preference by Similarity to an Ideal Solution, which often lacks dimensional reduction capability and assumes uniform weight distribution across criteria. Methods: To overcome these challenges, a hybrid model integrating non-negative matrix factorisation, random forest, and the Technique for Order Preference by Similarity to an Ideal Solution is developed for supplier evaluation in the pharmaceutical sector. The method first applies non-negative matrix factorisation to condense twenty-four evaluation criteria into eight core dimensions, enhancing analytical efficiency and reducing complexity. Random forest is then employed to derive data-driven weights for each criterion, ensuring accurate prioritisation. Finally, the Technique for Order Preference by Similarity to an Ideal Solution ranks suppliers and provides actionable insights for decision-makers. Results: Results from real-world pharmaceutical data validate the model’s effectiveness and demonstrate superior performance over conventional evaluation methods. Conclusions: The findings confirm that integrating machine learning techniques with established decision-making frameworks enhances precision, interpretability, and sustainability in supplier selection while requiring adequate data quality and computational resources for implementation.
- Open Access
Multi-Criteria Decision Support for Sustainable Supplier Evaluation in Mining SMEs: A Fuzzy Logic and TOPSIS Approach
Background: Improving operational efficiency in the mining industry increasingly de-pends on a mature asset management framework and the careful selection of reliable, sustainable suppliers for systems, personnel, equipment, and services. Given the complexity of mining operations and the growing use of digital tools, choosing the right maintenance management system requires a robust decision-making process that considers economic, environmental, and social sustainability factors. Methods: This study develops and compares two multi-criteria decision-making approaches, a ranking method and a fuzzy logic-based model to evaluate four maintenance management systems against fifteen sustainability-related criteria. Expert opinions from executives and operational managers in the South African mining sector were gathered, focusing on factors such as cost, integration, reliability, ease of use, inventory control, and predictive capabilities. Results: The ranking method produced a clear, quantitative order of preference, while the fuzzy model addressed uncertainty and subjectivity in expert judgments. Both methods identified the same top choice: UPKEEP, followed by SAP, FIIX, and LIMBLE. Conclusions: This comparison shows that combining fuzzy logic with sustainability-focused evaluation can improve the flexibility and reliability of supplier selection in asset management. The proposed approach offers practical guidance for aligning maintenance system choices with broader sustainability goals in mining operations.
Open AccessMulti-Criteria Decision Support for Sustainable Supplier Evaluation in Mining SMEs: A Fuzzy Logic and TOPSIS Approach
Background: Improving operational efficiency in the mining industry increasingly de-pends on a mature asset management framework and the careful selection of reliable, sustainable suppliers for systems, personnel, equipment, and services. Given the complexity of mining operations and the growing use of digital tools, choosing the right maintenance management system requires a robust decision-making process that considers economic, environmental, and social sustainability factors. Methods: This study develops and compares two multi-criteria decision-making approaches, a ranking method and a fuzzy logic-based model to evaluate four maintenance management systems against fifteen sustainability-related criteria. Expert opinions from executives and operational managers in the South African mining sector were gathered, focusing on factors such as cost, integration, reliability, ease of use, inventory control, and predictive capabilities. Results: The ranking method produced a clear, quantitative order of preference, while the fuzzy model addressed uncertainty and subjectivity in expert judgments. Both methods identified the same top choice: UPKEEP, followed by SAP, FIIX, and LIMBLE. Conclusions: This comparison shows that combining fuzzy logic with sustainability-focused evaluation can improve the flexibility and reliability of supplier selection in asset management. The proposed approach offers practical guidance for aligning maintenance system choices with broader sustainability goals in mining operations.