Enhancing Baggage Handling Duration Predictions for KLM : A Data-driven and Machine Learning Approach Using Camera and Sensor Data

Accurate baggage loading/unloading estimation is crucial for KLM's efficiency at Schiphol Airport. However, their current estimation tool lacks data validation and needs improvement, leading to inaccuracies and inefficiencies turnaround process. In this project, we aim to address the challenges faced in KLM's baggage handling process, which impact operational efficiency and customer satisfaction. The research questions were designed to investigate how data-driven and Machine Learning methods using camera and sensor data can enhance the accuracy of baggage duration predictions at Schiphol Airport. For this, a comprehensive analysis of the current system, empirical data, and modeling techniques were covered.