Lessons from a human-in-the-loop machine learning approach for identifying vacant, abandoned, and deteriorated properties in Savannah, Georgia
This work addresses the challenge of property identification for urban planning, but it is incremental as it applies an existing HITLML approach to a specific domain.
The researchers tackled the problem of identifying vacant, abandoned, and deteriorated properties in Savannah, Georgia by developing a human-in-the-loop machine learning model called VADecide, which achieved higher prediction accuracy than a model without human input.
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 VADecide 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 vs. human-generated results. Our findings contribute to knowledge about the advantages and challenges of HITLML in urban planning. [Accepted for Publication at a Peer Review Journal]