In India, the crime rate is increasing each day. In the current situation, recent technological influence, effects of social media and modern approaches help the offenders to achieve their crimes. Both analysis and prediction of crime is a systematized method that classifies and examines the crime patterns. There exist various clustering algorithms for crime analysis and pattern prediction but they do not reveal all the requirements. Among these, K means algorithm provides a better way for predicting the results. The proposed research work mainly focused on predicting the region with higher crime rates and age groups with more or less criminal tendencies. We propose an optimized K means algorithm to lower the time complexity and improve efficiency in the result.