Cancer has been characterized as one of the leading diseases that cause death in humans. Breast cancer, being a subtype of cancer, causes death in one out of every eight women worldwide. The solution to counter this is by conducting early and accurate diagnosis for faster treatment. To achieve such accuracy in a short span of time proves difficult with existing techniques. Also, the medical tests conducted in hospitals for detecting cancer is expensive and is difficult for any common man to afford. To counter these problems, in this paper, we use the concept of applying Support Vector machine a Machine Learning algorithm to predict whether a person is prone to breast cancer. We evaluate the performance of this algorithm by calculating its accuracy and apply a min-max scaling method so as to counter and overcome the problem of overfitting and outliers. After scaling of the dataset, we apply a feature selection method called Principle component analysis to improve the algorithms accuracy by decreasing the number of parameters. The final algorithm has improved accuracy with the absence of overfitting and outliers, thus this algorithm can be used to develop and build systems that can be deployed in clinics, hospitals and medical centers for early and quick diagnosis of breast cancer. The training dataset is from the University of Wisconsin (UCI) Machine Learning Repository which is used to evaluate the performance of the Support vector machine by calculating its accuracy.