# Network-Based Transfer Learning Helps Improve Short-Term Crime Prediction Accuracy

arXiv: https://arxiv.org/abs/2406.06645 · HTML: https://mlsanity.com/paper/2406.06645/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 52 references that are in the map.
- First posted on arXiv 10 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https://mlsanity.com/paper/1901.08518/) (2019)
- [Multiscale Dynamic Human Mobility Flow Dataset in the U.S. during the COVID-19 Epidemic](https://mlsanity.com/paper/2008.12238/) (2020)
- [Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting](https://mlsanity.com/paper/2004.08038/) (2020)
- [Mining large-scale human mobility data for long-term crime prediction](https://mlsanity.com/paper/1806.01400/) (2018)
- [Deep Learning for Real Time Crime Forecasting](https://mlsanity.com/paper/1707.03340/) (2017)
- [Socio-economic, built environment, and mobility conditions associated with crime: A study of multiple cities](https://mlsanity.com/paper/2004.05822/) (2020)
- [Leveraging Mobility Flows from Location Technology Platforms to Test Crime Pattern Theory in Large Cities](https://mlsanity.com/paper/2004.08263/) (2020)
- [A fairness assessment of mobility-based COVID-19 case prediction models](https://mlsanity.com/paper/2210.03901/) (2022)

## Abstract (arXiv)

Deep learning architectures enhanced with human mobility data have been shown to improve the accuracy of short-term crime prediction models trained with historical crime data. However, human mobility data may be scarce in some regions, negatively impacting the correct training of these models. To address this issue, we propose a novel transfer learning framework for short-term crime prediction models, whereby weights from the deep learning crime prediction models trained in source regions with plenty of mobility data are transferred to target regions to fine-tune their local crime prediction models and improve crime prediction accuracy. Our results show that the proposed transfer learning framework improves the F1 scores for target cities with mobility data scarcity, especially when the number of months of available mobility data is small. We also show that the F1 score improvements are pervasive across different types of crimes and diverse cities in the US.