This paper investigates the use of machine learning (ML) models to predict housing prices. A well-performing housing price model was trained, which can seamlessly be integrated into public sector processes to increase market transparency and is based on modern ML and feature engineering methods. For these models, particular consideration was given to the spatial component. The research uses the Design Science Research approach, with a case study carried out in the city of Duisburg, Germany. The ML models developed showed better performance than traditional models. The models were embedded in official processes using Shapley values to increase interpretability. The study concludes that ML models can contribute to increased market transparency in the real estate sector.