This paper is about comparing several different supervised machine learning techniques to the “mammographic masses” public data set from the UCI repository, and see which one yields the highest accuracy as measured with K-Fold cross validation (K=10 A lot of needless pain and surgery occurs from the subsequent false positives of mammogram performance. If we can create a better way of understanding them through supervised machine learning, it will make many lives easier .We have applied Decision tree, Random forest, KNN, Naive Bayes, SVM, Logistic Regression and also neural network using Keras. The data was cleaned as many rows were contain missing data, and as there were erroneous data identifiable as outliers as well. Some techniques such as SVM that we have employed requires the input data to be normalized first. Many techniques also had "hyperparameters" that had to be tuned. So here we have approached a better way to make it even better by tuning its hyperparameters.