Abstract: „In this contribution, the authors examine the spatiotemporal distribution of residential burglaries in a Belgian police zone based on monthly residential burglaries before and during the COVID-19 crisis and assess the performance of a predictive crime model during this period. In general, compared to 2019, there were fewer home burglaries in 2020 during the COVID-19 crisis. Except for a few changes, the spatial distribution of residential burglaries in 2020 is largely similar to that of residential burglaries in 2019. The authors observe that the predictive crime model performs significantly worse at the start of the pandemic and when severe measures are taken, but that the model’s performance then rises again after a few months as the algorithm becomes more proficient in adjusting itself to big societal changes.“