A systematic review on spatial crime forecasting
Abstract Background Predictive policing and crime analytics with a spatiotemporal focus get increasing attention among a variety of scientific communities and are already being implemented as effective policing tools. The goal of this paper is to provide an overview and evaluation of the state of th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-05-01
|
| Series: | Crime Science |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s40163-020-00116-7 |
| _version_ | 1818289748847886336 |
|---|---|
| author | Ourania Kounadi Alina Ristea Adelson Araujo Michael Leitner |
| author_facet | Ourania Kounadi Alina Ristea Adelson Araujo Michael Leitner |
| author_sort | Ourania Kounadi |
| collection | DOAJ |
| description | Abstract Background Predictive policing and crime analytics with a spatiotemporal focus get increasing attention among a variety of scientific communities and are already being implemented as effective policing tools. The goal of this paper is to provide an overview and evaluation of the state of the art in spatial crime forecasting focusing on study design and technical aspects. Methods We follow the PRISMA guidelines for reporting this systematic literature review and we analyse 32 papers from 2000 to 2018 that were selected from 786 papers that entered the screening phase and a total of 193 papers that went through the eligibility phase. The eligibility phase included several criteria that were grouped into: (a) the publication type, (b) relevance to research scope, and (c) study characteristics. Results The most predominant type of forecasting inference is the hotspots (i.e. binary classification) method. Traditional machine learning methods were mostly used, but also kernel density estimation based approaches, and less frequently point process and deep learning approaches. The top measures of evaluation performance are the Prediction Accuracy, followed by the Prediction Accuracy Index, and the F1-Score. Finally, the most common validation approach was the train-test split while other approaches include the cross-validation, the leave one out, and the rolling horizon. Limitations Current studies often lack a clear reporting of study experiments, feature engineering procedures, and are using inconsistent terminology to address similar problems. Conclusions There is a remarkable growth in spatial crime forecasting studies as a result of interdisciplinary technical work done by scholars of various backgrounds. These studies address the societal need to understand and combat crime as well as the law enforcement interest in almost real-time prediction. Implications Although we identified several opportunities and strengths there are also some weaknesses and threats for which we provide suggestions. Future studies should not neglect the juxtaposition of (existing) algorithms, of which the number is constantly increasing (we enlisted 66). To allow comparison and reproducibility of studies we outline the need for a protocol or standardization of spatial forecasting approaches and suggest the reporting of a study’s key data items. |
| first_indexed | 2024-12-13T02:17:13Z |
| format | Article |
| id | doaj.art-b3879bc03aa5424f8756b004b4776c20 |
| institution | Directory Open Access Journal |
| issn | 2193-7680 |
| language | English |
| last_indexed | 2024-12-13T02:17:13Z |
| publishDate | 2020-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Crime Science |
| spelling | doaj.art-b3879bc03aa5424f8756b004b4776c202022-12-22T00:02:51ZengBMCCrime Science2193-76802020-05-019112210.1186/s40163-020-00116-7A systematic review on spatial crime forecastingOurania Kounadi0Alina Ristea1Adelson Araujo2Michael Leitner3Department of Geoinformation Processing, University of TwenteDoctoral College GIScience, Department of Geoinformatics-Z_GIS, University of SalzburgDepartment of Informatics and Applied Mathematics, Federal University of Rio Grande do NorteDoctoral College GIScience, Department of Geoinformatics-Z_GIS, University of SalzburgAbstract Background Predictive policing and crime analytics with a spatiotemporal focus get increasing attention among a variety of scientific communities and are already being implemented as effective policing tools. The goal of this paper is to provide an overview and evaluation of the state of the art in spatial crime forecasting focusing on study design and technical aspects. Methods We follow the PRISMA guidelines for reporting this systematic literature review and we analyse 32 papers from 2000 to 2018 that were selected from 786 papers that entered the screening phase and a total of 193 papers that went through the eligibility phase. The eligibility phase included several criteria that were grouped into: (a) the publication type, (b) relevance to research scope, and (c) study characteristics. Results The most predominant type of forecasting inference is the hotspots (i.e. binary classification) method. Traditional machine learning methods were mostly used, but also kernel density estimation based approaches, and less frequently point process and deep learning approaches. The top measures of evaluation performance are the Prediction Accuracy, followed by the Prediction Accuracy Index, and the F1-Score. Finally, the most common validation approach was the train-test split while other approaches include the cross-validation, the leave one out, and the rolling horizon. Limitations Current studies often lack a clear reporting of study experiments, feature engineering procedures, and are using inconsistent terminology to address similar problems. Conclusions There is a remarkable growth in spatial crime forecasting studies as a result of interdisciplinary technical work done by scholars of various backgrounds. These studies address the societal need to understand and combat crime as well as the law enforcement interest in almost real-time prediction. Implications Although we identified several opportunities and strengths there are also some weaknesses and threats for which we provide suggestions. Future studies should not neglect the juxtaposition of (existing) algorithms, of which the number is constantly increasing (we enlisted 66). To allow comparison and reproducibility of studies we outline the need for a protocol or standardization of spatial forecasting approaches and suggest the reporting of a study’s key data items.http://link.springer.com/article/10.1186/s40163-020-00116-7CrimeForecastingPredictionPredictive policingSpatiotemporalSpatial analysis |
| spellingShingle | Ourania Kounadi Alina Ristea Adelson Araujo Michael Leitner A systematic review on spatial crime forecasting Crime Science Crime Forecasting Prediction Predictive policing Spatiotemporal Spatial analysis |
| title | A systematic review on spatial crime forecasting |
| title_full | A systematic review on spatial crime forecasting |
| title_fullStr | A systematic review on spatial crime forecasting |
| title_full_unstemmed | A systematic review on spatial crime forecasting |
| title_short | A systematic review on spatial crime forecasting |
| title_sort | systematic review on spatial crime forecasting |
| topic | Crime Forecasting Prediction Predictive policing Spatiotemporal Spatial analysis |
| url | http://link.springer.com/article/10.1186/s40163-020-00116-7 |
| work_keys_str_mv | AT ouraniakounadi asystematicreviewonspatialcrimeforecasting AT alinaristea asystematicreviewonspatialcrimeforecasting AT adelsonaraujo asystematicreviewonspatialcrimeforecasting AT michaelleitner asystematicreviewonspatialcrimeforecasting AT ouraniakounadi systematicreviewonspatialcrimeforecasting AT alinaristea systematicreviewonspatialcrimeforecasting AT adelsonaraujo systematicreviewonspatialcrimeforecasting AT michaelleitner systematicreviewonspatialcrimeforecasting |