Lessons from a Human-in-the-Loop Machine Learning Approach for Identifying Vacant, Abandoned, and Deteriorated Properties in Savannah, Georgia
Xiaofan Liang, Brian Brainerd, Tara Hicks, Clio Andris · Journal of Planning Education and Research · 2024
Addressing strategies for managing vacant, abandoned, and deteriorated (VAD) properties is important for maintaining healthy communities. Yet, the process of identifying these properties can be difficult. Here, we create a human-in-the-loop machine learning (HITLML) model called VAD ecide and apply it to a parcel-level case study in Savannah, Georgia. The results show a higher prediction accuracy than was achieved when using a machine learning model without human input in the training. The HITLML approach also reveals differences between machine versus human-generated results. Our findings contribute to knowledge about the advantages and challenges of HITLML in urban planning.