TY - JOUR
T1 - Grid-based crime prediction using geographical features
AU - Lin, Ying Lung
AU - Yen, Meng Feng
AU - Yu, Liang Chih
N1 - Funding Information:
This work was supported by the Ministry of Science and Technology, R.O.C. (Taiwan), under Grant No. MOST 105-2221-E-155-059-MY2, MOST 106-3114-E-006-013, and the Center for Innovative FinTech Business Models, NCKU, under the Higher Education Sprout Project, Ministry of Education, R.O.C. (Taiwan).
Funding Information:
Funding: This work was supported by the Ministry of Science and Technology, R.O.C. (Taiwan), under Grant No. MOST 105-2221-E-155-059-MY2, MOST 106-3114-E-006-013, and the Center for Innovative FinTech Business Models, NCKU, under the Higher Education Sprout Project, Ministry of Education, R.O.C. (Taiwan).
Publisher Copyright:
© 2018 by the authors.
PY - 2018/8
Y1 - 2018/8
N2 - Machine learning is useful for grid-based crime prediction. Many previous studies have examined factors including time, space, and type of crime, but the geographic characteristics of the grid are rarely discussed, leaving prediction models unable to predict crime displacement. This study incorporates the concept of a criminal environment in grid-based crime prediction modeling, and establishes a range of spatial-temporal features based on 84 types of geographic information by applying the Google Places API to theft data for Taoyuan City, Taiwan. The best model was found to be Deep Neural Networks, which outperforms the popular Random Decision Forest, Support Vector Machine, and K-Near Neighbor algorithms. After tuning, compared to our design's baseline 11-month moving average, the F1 score improves about 7% on 100-by-100 grids. Experiments demonstrate the importance of the geographic feature design for improving performance and explanatory ability. In addition, testing for crime displacement also shows that our model design outperforms the baseline.
AB - Machine learning is useful for grid-based crime prediction. Many previous studies have examined factors including time, space, and type of crime, but the geographic characteristics of the grid are rarely discussed, leaving prediction models unable to predict crime displacement. This study incorporates the concept of a criminal environment in grid-based crime prediction modeling, and establishes a range of spatial-temporal features based on 84 types of geographic information by applying the Google Places API to theft data for Taoyuan City, Taiwan. The best model was found to be Deep Neural Networks, which outperforms the popular Random Decision Forest, Support Vector Machine, and K-Near Neighbor algorithms. After tuning, compared to our design's baseline 11-month moving average, the F1 score improves about 7% on 100-by-100 grids. Experiments demonstrate the importance of the geographic feature design for improving performance and explanatory ability. In addition, testing for crime displacement also shows that our model design outperforms the baseline.
UR - http://www.scopus.com/inward/record.url?scp=85051722855&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051722855&partnerID=8YFLogxK
U2 - 10.3390/ijgi7080298
DO - 10.3390/ijgi7080298
M3 - Article
AN - SCOPUS:85051722855
VL - 7
JO - ISPRS International Journal of Geo-Information
JF - ISPRS International Journal of Geo-Information
SN - 2220-9964
IS - 8
M1 - 298
ER -