Prediction of a school's progress as Above Average/Average/Below Average based on the crime rate in its locality by building Machine learning algorithms. Data preprocessing techniques like removing NaN, Binarization(label encoding and one-hot encoding) on attributes and data cleaning were done before feeding them to algorithms Random Forest and XGBoost classifiers were built and fine tuned to perform the prediction for each year of Chicago's schools' progress based on crime data from 2013 to 2017. These algorithms learn the attributes of schools and the crime data in their respective localities for the prediction of progress. The accuracy in classifying the schools' progress is used to determine the most efficient algorithm.