Random Forest Algorithm Based on Genetic Algorithm Optimization for Property-Related Crime Prediction

DOI

10.2991/cnci-19.2019.73How to use a DOI?

Keywords

Genetic Algorithm, Random Forest, property-related property-related crime Prediction,intelligence-led policing.

Abstract

The property-related crime is an important type of crime, which affects the stability of social order, and presents the characteristic of "high-occurrence but low-breakage". In order to realize the precise prevention against the property-related crime, this paper constructs a large-scale environmental factors data set based on real official data, and proposes a random forest algorithm based on genetic algorithm optimization. This algorithm constructs a classification model according to the data of environmental factors that affect the property-related crime, and predicts the trend of the property-related crime in the region.Experimental results show that, the algorithm proposed in this paper achieves a good performance in forecasting the trend of property-related crime, and significantly improves the efficiency of searching for the optimal solution with low computational complexity. It has a strong application prospect in forecasting property-related crime, it could provide early warning to the future trend of the crime.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tuo Shi
AU  - Gao He
AU  - Yulei Mu
PY  - 2019/05
DA  - 2019/05
TI  - Random Forest Algorithm Based on Genetic Algorithm Optimization for Property-Related Crime Prediction
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 526
EP  - 531
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.73
DO  - 10.2991/cnci-19.2019.73
ID  - Shi2019/05
ER  -