The Utility of Point of Interest Data for Crime Risk Prediction

Paweł Cichosz , Zbigniew M. Wawrzyniak , Radosław Pytlak , Grzegorz Borowik , Eliza Szczechla , Paweł Michalak , Dobiesław Ircha , Wojciech Olszewski , Emilian Perkowski


This paper examines the utility of Point of Interest (POI) data for learning crime prediction models. Crime event locations for a Polish city are aggregated into a grid and merged with selected data layers from OpenStreetMap. The resulting dataset contains crime count attributes and POI count attributes for particular areas of the city, obtained by aggregating over a rectangular grid. After identifying high-risk areas based on crime counts, POI count attributes are used for learning crime risk prediction models with the logistic regression, support vector machines, and random forest algorithms. The experimental results suggest that POI attributes have high predictive utility. Classiffcation models using these attributes, without any form of location identiffication, exhibit very good predictive performance, which makes it possible to reuse them over different cities.
Author Paweł Cichosz (FEIT / IN)
Paweł Cichosz,,
- The Institute of Computer Science
, Zbigniew M. Wawrzyniak (FEIT / PE)
Zbigniew M. Wawrzyniak,,
- The Institute of Electronic Systems
, Radosław Pytlak (FMIS / DAICM)
Radosław Pytlak,,
- Department of Artificial Intelligence and Computational Methods
, Grzegorz Borowik
Grzegorz Borowik,,
, Eliza Szczechla
Eliza Szczechla,,
, Paweł Michalak
Paweł Michalak,,
, Dobiesław Ircha
Dobiesław Ircha,,
, Wojciech Olszewski
Wojciech Olszewski,,
, Emilian Perkowski
Emilian Perkowski,,
Publication size in sheets0.3
Book Valenzuela Olga, Rojas Fernando, Pomares Héctor, Rojas Ignacio (eds.): ITISE 2018 International Conference on Time Series and Forecasting, Proceedings of papers, vol. 3, 2018, Godle Impresiones Digitales S.L., ISBN 978-84-17293-57-4
Keywords in Polishprognozowanie przestępczości, poi
Keywords in Englishcrime prediction, point of interests
Abstract in PolishPraca omawia zastosowanie koncepcji POI dla kalibracji modeli do prognozowania przestępczości.
projectCreating a system for forecasting the development of crime, as an element of building a security strategy and public policy. Project leader: Wawrzyniak Zbigniew M., , Phone: +48 22 234 7738, application date 15-09-2015, start date 21-12-2015, end date 20-12-2018, ISE/2015/4/NCBiR/7-2015/Prokrym, Completed
WEiTI Projects financed by NCRD [Projekty finansowane przez NCBiR (NCBR)]
Languageen angielski
cichosz_utility.pdf 448 KB
Score (nominal)0
ScoreMinisterial score = 0.0, 28-05-2019, ChapterFromConference
Ministerial score (2013-2016) = 15.0, 07-05-2019, ChapterFromConference
Citation count*
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.