A time series is a sequence of observations usually ordered in time. The time series is analyzed for prediction of the future based on the past, controlling the process producing the series, understanding the mechanism generating the series and for describing the salient features of the series. In this paper, various prediction methods are compared based on performance for an example time series. Given the crime data and demographic features like the sex ratio, population density and religious composition of a region, this paper delivers a method to predict the region-specific crime rate for the future. The demographic features are distributed normally and significance tests for the normal distribution have been computed. Two random predictors have been proposed for the sole purpose of bolstering the accuracy of the predictor built from statistical auto regressive linear regression modeling. This model outlines a method to understand crime trends of a region given the demographic features.