<p>Service quality has become a central focus in the management of airports due to its significance in realizing the fulfillment of travelers and in turn its impact on the desire of travelers to revisit an airport in the future. Information recorded by information systems supporting operations carried out at airports can provide valuable insights that can assist employees of airports to make more informed decisions at the right time. This work presents an innovative application of predictive process monitoring to enhance luggage handling operations at a large international airport, bridging the gap between AI research and real-world deployment. Concretely, the contribution of this paper is fourfold. First, we show that predictive process monitoring can be successfully deployed in this setting through the execution of several iterations of a development cycle specifically formulated to support the development of predictive process monitoring applications. Second, using advanced sequence-to-sequence models based on long short-term memory (LSTM) networks, we demonstrate how predictive models can accurately forecast the remaining trajectory and runtime of luggage handling processes. Third, several variations of the LSTM based modelling approach are considered, including models which incorporate features encoded using a newly-designed inter-case feature encoding technique. Finally, we provide an in-depth analysis on how a predictive process monitoring system can support the luggage handling operations at an airport. By bridging AI research and real-world application, this work highlights the transformative potential of predictive process monitoring in addressing complex operational challenges, offering a valuable reference for both researchers and practitioners in the AI community.</p>