Crime Data Mining : A General Framework and Approach to Identify Crime Pattern Using Machine Learning

Abstract

Crime data mining has been a hot topic in the law-enforcement sector as it can solve crime related problems more effectively. In this thesis, we have focused in determining crime patterns using effective data mining algorithms. To classify our raw data we used Naïve Bayes classifier along with NER (Named Entity Recognition) and Co-reference Resolution concept. In order to get higher accuracy, we have trained numerous train data with required keywords. To get the related keywords and train data, both online and offline data are used. For the validation of the process, filed work like talking to “Adabor Thana Police Station” is also performed. Test results are generated based on sample input and results. Our thesis results generates the report which represents crimes stativity of different divisions of Bangladesh. The output data also shows how much crimes are occurring in certain place which can be used for crime pattern analysis for a specific location like an individual district or even for a police station. Upon successful implementation, it our thought that law-enforcement authority will find our findings useful to detect crime sensitive zones of Bangladesh and take precautions so that number of crimes can be reduced.