Data mining technologies have been used by marketers to provide personalisation. In other words, the exact placement of the right offer to the right person at the right time. The police can apply this technique for providing the right inquiry to the right perpetrators at the right time, before or after person has committed a crime. The aim of this Thesis is to use data mining in operational policing for crime prediction and detection. Crime data contains rich information. However, it is inconsistent, incomplete and noisy thus making it difficult to get any useful information from it. The goal of this Thesis is to use data mining techniques on Police data, which could be used for analysis while making Police strategies to reduce the crime activities. Volume crimes (such as robbery) are difficult to analyse because of their high number and similarity between their Modus Operandi (MO). The methodological approach developed in this Thesis will help Police analysts to attribute undetected crimes to known offenders who may be responsible, with 72.9% to 93.57% accuracy, for committing the crime. The results obtained are encouraging, which demonstrating that supervised (MLP, and C5.0) and unsupervised techniques (SOM) in combination give greater accuracy compared to the existing Police methods. The same data mining technologies can be used with 53.47% to 58.77% accuracy, for predicting spatial -tempora I features of crime hit by prolific offender's network. With the time series, we were able to predict next month's volume of crimes on the top ten spatial spots with 76.4% accuracy.