Saved in:
Bibliographic Details
Main Authors: Jin, Jiahui, Hong, Yi, Xu, Guandong, Zhang, Jinghui, Tang, Jun, Wang, Hancheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.01134
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916465880334336
author Jin, Jiahui
Hong, Yi
Xu, Guandong
Zhang, Jinghui
Tang, Jun
Wang, Hancheng
author_facet Jin, Jiahui
Hong, Yi
Xu, Guandong
Zhang, Jinghui
Tang, Jun
Wang, Hancheng
contents Predicting crime hotspots in a city is a complex and critical task with significant societal implications. Numerous spatiotemporal correlations and irregularities pose substantial challenges to this endeavor. Existing methods commonly employ fixed-time granularities and sequence prediction models. However, determining appropriate time granularities is difficult, leading to inaccurate predictions for specific time windows. For example, users might ask: What are the crime hotspots during 12:00-20:00? To address this issue, we introduce FlexiCrime, a novel event-centric framework for predicting crime hotspots with flexible time intervals. FlexiCrime incorporates a continuous-time attention network to capture correlations between crime events, which learns crime context features, representing general crime patterns across time points and locations. Furthermore, we introduce a type-aware spatiotemporal point process that learns crime-evolving features, measuring the risk of specific crime types at a given time and location by considering the frequency of past crime events. The crime context and evolving features together allow us to predict whether an urban area is a crime hotspot given a future time interval. To evaluate FlexiCrime's effectiveness, we conducted experiments using real-world datasets from two cities, covering twelve crime types. The results show that our model outperforms baseline techniques in predicting crime hotspots over flexible time intervals.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01134
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Event-centric Framework for Predicting Crime Hotspots with Flexible Time Intervals
Jin, Jiahui
Hong, Yi
Xu, Guandong
Zhang, Jinghui
Tang, Jun
Wang, Hancheng
Machine Learning
Computers and Society
Predicting crime hotspots in a city is a complex and critical task with significant societal implications. Numerous spatiotemporal correlations and irregularities pose substantial challenges to this endeavor. Existing methods commonly employ fixed-time granularities and sequence prediction models. However, determining appropriate time granularities is difficult, leading to inaccurate predictions for specific time windows. For example, users might ask: What are the crime hotspots during 12:00-20:00? To address this issue, we introduce FlexiCrime, a novel event-centric framework for predicting crime hotspots with flexible time intervals. FlexiCrime incorporates a continuous-time attention network to capture correlations between crime events, which learns crime context features, representing general crime patterns across time points and locations. Furthermore, we introduce a type-aware spatiotemporal point process that learns crime-evolving features, measuring the risk of specific crime types at a given time and location by considering the frequency of past crime events. The crime context and evolving features together allow us to predict whether an urban area is a crime hotspot given a future time interval. To evaluate FlexiCrime's effectiveness, we conducted experiments using real-world datasets from two cities, covering twelve crime types. The results show that our model outperforms baseline techniques in predicting crime hotspots over flexible time intervals.
title An Event-centric Framework for Predicting Crime Hotspots with Flexible Time Intervals
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2411.01134