DOI QR코드

DOI QR Code

A study to Predictive modeling of crime using Web traffic information

웹 검색 트래픽 정보를 이용한 범죄 예측 모델링에 관한 연구

  • Park, Jung-Min (Dept. of Computer Science & Engineering, Kongju national University) ;
  • Chung, Young-Suk (Dept. of Computer Science & Engineering, Kongju national University) ;
  • Park, Koo-Rack (Dept. of Computer Science & Engineering, Kongju national University)
  • 박정민 (공주대학교 컴퓨터공학과) ;
  • 정영석 (공주대학교 컴퓨터공학과) ;
  • 박구락 (공주대학교 컴퓨터공학과)
  • Received : 2014.09.27
  • Accepted : 2014.11.10
  • Published : 2015.01.31

Abstract

In modern society, various crimes is occurred. It is necessary to predict the criminal in order to prevent crimes, various studies on the prediction of crime is in progress. Crime-related data, is announced to the statistical processing of once a year from the Public Prosecutor's Office. However, relative to the current point in time, data that has been statistical processing is a data of about two years ago. It does not fit to the data of the crime currently being generated. In This paper, crime prediction data was apply with Naver trend data. By using the Web traffic Naver trend, it is possible to obtain the data of interest level for crime currently being generated. It was constructed a modeling that can predict the crime by using traffic data of the Naver web search. There have been applied to Markov chains prediction theory. Among various crimes, murder, arson, rape, predictive modeling was applied to target. And the result of predictive modeling value was analyzed. As a result, it got the same results within 20%, based on the value of crime that actually occurred. In the future, it plan to advance research for the predictive modeling of crime that takes into the characteristics of the season.

현대 사회는 다양한 범죄가 발생하고 있다. 범죄를 예방하기 위해서는 범죄를 예측 하는 것이 필요하고, 범죄 예측에 관한 다양한 연구가 진행 중에 있다. 범죄 관련 데이터는 검찰청에서 1년에 한번 통계처리를 하여 발표하고 있다. 그러나 통계처리 된 자료는 현재 시점을 기준으로 약 2년 전의 자료로 현재 발생하는 범죄에 대한 데이터로 적합하지 않다. 본 논문은 범죄를 예측하는 데이터로 네이버 트랜드를 적용했다. 네이버 트랜드의 웹 검색 트래픽을 이용하면, 현재 발생하는 범죄에 대한 관심도 데이터를 얻을 수 있다. 네이버 웹 검색 트래픽 데이터를 이용하여 범죄를 예측할 수 있는 모델링을 구성하였고, 예측 이론으로 마코프 체인을 적용하였다. 다양한 범죄 중 살인, 방화, 강간을 대상으로 예측 모델링에 적용하였고, 결과 값을 분석하였다. 그 결과 실제 발생한 범죄 발생 빈도수를 기준으로 20%이내의 유사한 결과를 얻었다. 향후에는 계절의 특성을 고려한 범죄 예측 모델링에 대한 연구를 진행할 예정이다

Keywords

References

  1. Statistics Korea, http://www.index.go.kr/potal/main/EachDtlPageDetail.do?idx_cd=2809
  2. Il-Yeob Joo "A Case Study on Crime Prediction using Time Series Models" Korean security science review, No.30 pp.139-169, 2012.
  3. Chan-Sook Noe, Dong-Hyun Kim, "A Crime Occurrence Risk Probability Map Generation Model based on the Markov Chain", The Journal of Korean Institute of Information Technology, Vol. 10, No.10, pp.89-98, 10, 2012.
  4. Google trends, http://www.google.co.kr/trends/
  5. Charles M. Grinstead, "Introduction to Probability: Second Revised Edition", American Mathematical Society, pp405-406, 1997.
  6. The top 10 emerging technologies for 2012 http://forumblog.org/2012/02/the-2012-top-10 -emerging-technologies/
  7. John Gantz, David Reinsel, " Extracting Value from Chaos ", IDC IVIEW June, 2011.
  8. Jeremy Ginsberg, Matthew H. Mohebbi, Rajan S. Patel, Lynnette Brammer, Mark S. Smolinski, Larry Brilliant "Detecting influenza epidemics using search engine query data", Nature, 457, pp.1012-1014, February 2009. https://doi.org/10.1038/nature07634
  9. Seung-Pyo Jun, You Eil Kim, Hyoung Sun Yoo, "A Comparative Study of Consumer's Hype Cycles Using Web Search Traffic of Naver and Google", Journal of Korea Technology Innovation Society, pp.1109-1133, December 2013.
  10. Seung-Pyo Jun Do-Hyung Park," Intelligent Brand Positioning Visualization System Based on Web Search Traffic Information : Focusing on Tablet PC", Journal of Intelligence and Information Systems , Vol.19, No.3, 93-111, 9. 2013. https://doi.org/10.13088/jiis.2013.19.3.093
  11. Young-Gab Kim, Young-kyo Baek, Hoh Peter In, Doo-Kwon Baik, "A Probabilistic Model of Damage Propagation based on the Markov Process", Journal of KIISE, Vol33, No8, pp.524-535, 8. 2006.
  12. Won-Hyung Park, Young-Jin Kim, Dong-Hwi Lee, Kui-Nam J Kim, "A Study on Prediction of Mass SQL Injection Worm Propagation Using The Markov Chain", Journal of the Korea Institute of Information Security and Cryptology, Vol 8, No4, pp.174-181, 12. 2008.
  13. Kim Hyun-Woo, Shin Seong-Jun, Lee Seung-Min, Jeong Seok- Bong,"Network-based Intrusion Detection Scheme using Markov Chain Model",Journal of Decision Science, Vol.20, No.1, pp.75-88, 2012.
  14. Crime statistics, SUPREME PROSECUTORS' OFFICE, http://www.spo.go.kr/spo/info/stats/stats02.jsp
  15. naver trand help, http://help.naver.com/ops/step2/faq.nhn?fcatid=13953

Cited by

  1. 시·공간 데이터를 활용한 머신러닝 기반 범죄예측모형 비교 vol.37, pp.1, 2015, https://doi.org/10.5659/jaik.2021.37.1.135