FBI CRIME DATA PREDICTION USING MACHINE LEARNING WITH DATA ANALYSIS

Crime is one of the biggest and dominating problem in our society and its forestallment is an important task. diurnal there are huge figures of crimes committed constantly. This bear keeping track of all the crimes and maintaining a database for same which may be used for future reference. The current problem faced are maintaining of proper dataset of crime and assaying this data to help in prognosticating and working crimes in future. The ideal of this design is to dissect dataset which correspond of multitudinous crimes and prognosticating the type of crime which may be in future depending upon colorful conditions. The crime data is uprooted from the sanctioned gate of police. It consists of crime information like position description, type of crime, date, time, latitude, longitude.

Before training of the model data preprocessing will be done following this point selection and scaling will be done so that delicacy gain will be high. The K- Nearest Neighbor( KNN) bracket and colorful other algorithms will be tested for crime vaticination and one with better delicacy will be used for training. Visualization of dataset will be done in terms of graphical representation of numerous cases for illustration at which time the felonious rates are high or at which month the felonious conditioning are high. The soul purpose of this design is to give a idea of how machine literacy can be used by the law enforcement agencies to descry, prognosticate and break crimes at a important faster rate and therefore reduces the crime rate. This can be used in other countries or countries depending upon the vacuity of the dataset.