Abstract:
In the Sri Lankan logistics sector, the identification and selection of optimal suppliers play a crucial role in enhancing supply chain efficiency and competitiveness. Traditional supplier selection methods often lack the adaptability and accuracy needed to address the dynamic challenges of modern logistics operations. This research proposes a machine learning-based approach to predict the best suppliers, aiming to optimize supply chain performance. By leveraging machine learning algorithms such as decision trees, support vector machines, and neural networks, this study seeks to develop a predictive model capable of analyzing diverse supplier data and identifying patterns that lead to superior performance. The primary objectives of this research include exploring various machine learning methodologies for supplier prediction, identifying key variables influencing supplier performance, and developing a robust predictive model tailored to the Sri Lankan logistics context. Through a comprehensive analysis of historical supplier data and performance metrics, this research aims to provide logistics stakeholders with actionable insights for more informed supplier selection decisions. The findings of this study are expected to contribute to the enhancement of supply chain efficiency, cost reduction, and improved service levels in the Sri Lankan logistics sector. Furthermore, this research underscores the importance of adopting innovative machine learning techniques to address the evolving challenges of supplier selection and supply chain management in the contemporary business environment.
