| Paper title: |
Crime Prediction and Socio-Demographic Factors: A Comparative Study of Machine Learning Regression-Based Algorithms |
| DOI: | https://doi.org/10.4316/JACSM.201901002 |
| Published in: | Issue 1, (Vol. 13) / 2019 |
| Publishing date: | 2019-04-16 |
| Pages: | 13-18 |
| Author(s): | GONZALEZ Joana J., LEBOULLUEC Aera |
| Abstract. | Abstract–Machine learning and data mining have been used for numerous society enrichment purposes, one of them being the prediction of crime. Detecting crime can aid in preventing crime, which can lead to offering people a better quality of life. In this research SAS (Statistical Analysis System) and Python are utilized to identify and study crime patterns based on social demographics, including per capita income and education level, using the dataset titled Communities and Crime supplied by the University of California Irvine Machine Learning Repository. Four machine learning algorithms were implemented to the dataset: Multiple Linear Regression, Random Forest Regression, Neural Network Regression, and Bayesian Regression, with Random Forest having the highest performance (R2=0.791). The objective of this study is to perform a comparative examination of the machine learning algorithms and to seek an effective model to predict the total number of violent crimes |
| Keywords: | Bayesian Regression, Linear Regression, Machine Learning, Neural Network, Predictive Crime, Random Forest, Regression |
| References: | 1. Mittal, M., Goyal, L.M., Sethi, J.K., Hemanth, D.J., 2018. Monitoring the Impact of Economic Crisis on Crime in India Using Machine Learning. Comput. Econ. https://doi.org/10.1007/s10614-018-9821-x 2. U.S. Department of Justice —Federal Bureau of Investigation, 2010. Variables Affecting Crime - Crime in the United States 2009 WWW Document. URL https://www2.fbi.gov/ucr/cius2009/about/variables_affecting_crime.html (accessed 9.24.18). 3. Wilson, S.R., 2004. Machine Learning. Encycl. Biostat. 4, 2923.-2924. 4. Nath, S.V., 2007. Crime pattern detection using data mining, in: Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2006 Workshops Proceedings). https://doi.org/10.1109/WI-IATW.2006.55 5. Tayal, D.K., Jain, A., Arora, S., Agarwal, S., Gupta, T., Tyagi, N., 2014. Crime detection and criminal identification in India using data mining techniques. AI Soc. 30, 117–127. https://doi.org/10.1007/s00146-014-0539-6 6. Iqbal, R., Murad, M.A.A., Mustapha, A., Panahy, P.H.S., Khanahmadliravi, N., 2013. An experimental study of classification algorithms for crime prediction. Indian J. Sci. Technol. 6, 4219–4225. https://doi.org/10.7763/IJKE.2015.V1.18 7. Osgood, D.W., Chambers, J.M., 2000. Social Disorganization Outside the Metropolis: an Analysis of Rural Youth Violence*. Criminology. https://doi.org/10.1111/j.1745-9125.2000.tb00884.x 8. Marchant, R., Haan, S., Clancey, G., Cripps, S., 2018. Applying machine learning to criminology: semi-parametric spatial-demographic Bayesian regression. Secur. Inform. 7. https://doi.org/10.1186/s13388-018-0030-x 9. Kutner, M.H., Nachtsheim, C.J., Neter, J., Li, W., 2002. Applied Linear Statistical Models, 5th Editio. ed. McGraw-Hill/Irwin. 10. Fitzmaurice, G.M., 2016. Regression. Diagnostic Histopathol. 22, 271–278 https://doi.org/10.1016/j.mpdhp.2016.06.004 11. Zahedi, P., Parvandeh, S., Asgharpour, A., McLaury, B.S., Shirazi, S.A., McKinney, B.A., 2018. Random forest regression prediction of solid particle Erosion in elbows. Powder Technol https://doi.org/10.1016/j.powtec.2018.07.055 12. Efendi, A., Effrihan, 2017. A simulation study on Bayesian Ridge regression models for several collinearity levels, in: AIP Conference Proceedings. https://doi.org/10.1063/1.5016665 13. Kirmani, M.M., n.d. Heart Disease Prediction using Multilayer Perceptron Algorithm. Int. J. Adv. Res. Comput. Sci. 8. 14. [dataset]. Redmond, Michael. Communities and Crime Unnormalized Data Set. UCI Machine Learning Repository, 2011. |
| Back to the journal content | |
