Targeting Factors that Predict Clearance of Non-domestic Assaults
- 128 Downloads
The research described in this chapter identifies solvability factors for non-domestic violent offences and then develops this research by building an algorithmic prediction model for the solvability of violent crime before testing it against an existing experiential model. It is based on a complete population of 29,105 violent offences reported to the UK’s West Midlands Police between 1 March 2012 and 31 December 2013. The data set was split in half, with one half being used to build the model and the other to test its accuracy. Twenty-five solvability factors were identified, along with thirteen case-limiting factors, which allowed a logit model to be built to predict the solvability of cases. Despite the cut-off point for inclusion being adjusted to minimise the impact of incorrectly filed reports, and additional opt-in factors being included to reduce damage to public confidence, the new algorithmic model was 22.16% more accurate than the existing experiential crime-screening model used by West Midlands Police.
KeywordsClearance Solvability Violent crime Prediction Algorithmic prediction Experiential prediction Predictive accuracy
- Ayres, I. (2007). Supercrunchers: How anything can be predicted. London: Murray.Google Scholar
- Bieck, W., & Kessler, D. A. (1977). Response time analysis. Kansas City: Missouri Board of Police Commissioners.Google Scholar
- Brand, S., & Price, R. (2000). The economic and social costs of crime (Home Office Research Study 217). London: Home Office.Google Scholar
- Burrows, J., Hopkins, M., Hubbard, R., Robinson, A., Speed, M., & Tilley, N. (2005). Understanding the attrition process in volume crime investigations (Home Office Research Study 295). London: Home Office.Google Scholar
- Clawson, C., & Chang, S. K. (1977). Relationship of response delays and arrest rates. Journal of Police Science and Administration, 5(1), 53–68.Google Scholar
- Coupe, T., & Griffiths, M. (1996). Solving residential burglary (Police Research Group Crime Detection and Prevention Services, Paper 77). London: Home Office.Google Scholar
- Dhiri, S., & Brand, S. (1999). Analysis of costs and benefits: guidance for evaluators. London: Home Office.Google Scholar
- Eck, J. E. (1979). Managing case assignments: The burglary investigation decision model replication. Washington, DC: Police Executive Research Forum.Google Scholar
- Gill, M., Hart, J., Livingstone, K., & Stevens, J. (1996). The crime allocation system: Police investigations into burglary and auto crime (Police Research Series, Paper 16). London: Home Office.Google Scholar
- Greenberg, B., Elliot, C. V., Kraft, L. P., & Procter, S. H. (1977). Felony investigation decision model—An analysis of investigation elements of information. Washington, DC: US Government Printing Office.Google Scholar
- Greenwood, P. W., Chaiken, J. M., Petersilia, J., & Prusoff, L. (1975). The criminal investigation process: Volume III: Observations and analysis. Santa Monica, CA: The RAND Corporation.Google Scholar
- Her Majesty’s Inspectorate of Constabulary and Fire & Rescue Services. (2012). Review of police crime and incident reports: West Midlands Police. London: HMIC.Google Scholar
- Jansson, K. (2005). Volume crime investigations—A review of the research literature (Home Office Online Report OLR 44/05). London: Home Office.Google Scholar
- Lipsey, M. W., & Wilson, D. B. (2001). Practical meta-analysis. Thousand Oaks, CA: SAGE Publications.Google Scholar
- Lösel, F. (2007). Doing evaluation research in criminology: Balancing scientific and practical demands. In R. D. King & E. Wincup (Eds.), Doing research on crime and justice (pp. 141–170). Oxford: Oxford University Press.Google Scholar
- MedCalc Software. (2014a). MedCalc manual: Logistic regression, version 14.12.0—last modified December 3, 2014. http://www.medcalc.org/manual/logistic_regression.php. Accessed December 31, 2014.
- MedCalc Software. (2014b). MedCalc manual: Logit transformation, version 14.12.0—last modified December 3, 2014. http://www.medcalc.org/manual/logit_transformation_table.php. Accessed December 31, 2014.
- Meehl, P. (1954). Clinical vs. statistical prediction: A theoretical analysis and a review of the evidence. Minneapolis: University of Minnesota Press.Google Scholar
- Newiss, G. (2002). Responding to and investigating street robbery. In K. Jansson (Ed.), Volume crime investigations—A review of the research literature (Home Office Online Report OLR 44/05). London: Home Office.Google Scholar
- Paine, C. (2012). Solvability factors in dwelling burglaries in Thames Valley (unpublished MSt thesis). University of Cambridge.Google Scholar
- Peterson, J., Sommers, I., Baskin, D., & Johnson, D. (2010). The role and impact of forensic evidence in the criminal justice process. Washington, D.C.: National Institute of Justice.Google Scholar
- Random.org. (n.d.). Random sequence generator. https://www.random.org/sequences/. Accessed September 12, 2014.
- Smith, K., Taylor, P., & Elkin, M. (2013). Crimes detected in England and Wales 2012/13. London: Home Office.Google Scholar
- Spelman, W., & Brown, D. K. (1981). Calling the police: Citizen reporting of serious crime. Washington, DC: Police Research Executive Forum.Google Scholar
- Stevens, J. M., & Stipak, B. (1982). Factors associated with police apprehension productivity. Police Science and Administration, 10(1), 52–57.Google Scholar
- Tilley, N., Robinson, A., & Burrows, J. (2007). The investigation of high volume crime. In T. Newburn, T. Williamson, & A. Wright (Eds.), Handbook of criminal investigation (pp. 226–254). London: Willan Publishing.Google Scholar
- United States Naval Observatory. (2014). Sun or moon rise/set table for one year. http://aa.usno.navy.mil/data/docs/RS_OneYear.php. Accessed December 13, 2014.