Optimizing Logistics with AI : A Conceptual Comparison Framework of Manual and Automated Route Planning at Bouwvervoer

As Artificial Intelligence (AI) becomes increasingly dominant in logistics, companies face the challenge of evaluating its potential against traditional planning methods. This thesis develops a conceptual comparison framework to assess the performance of Bouwvervoer’s current semi-digital manual route planning system versus a pilot AI-driven alternative. Eight Key Performance Indicators (KPIs) were selected to capture operational efficiency, employee satisfaction, and customer service quality. Their relative importance was determined through the Multiplicative Analytic Hierarchy Process (MAHP) based on expert input from company stakeholders. The framework incorporates three analytical tools: Descriptive Statistics to assess performance variability, Weighted Composite Score (WCS) to provide an overall performance metric, and Weighted Difference Analysis (WDA) to reveal KPI-specific gaps between systems. Due to limited operational availability, these methods were implemented in an interactive Power BI dashboard using mock-up data. Evaluation feedback from the company supervisor confirmed the dashboard’s usability and strategic value while suggesting improvements for future development. The framework offers a scalable and transferable approach for logistics firms considering AI adoption, providing structured decision support in performance evaluation.