This project is entitled as “Arrhythmia Detection with Deep Learning” is a dataset analysis. Cardiac Arrhythmia is a life-threatening disease, causing serious health issues in patients, when left untreated. An existing diagnosis of arrhythmias would be helpful in save millions of lives. This data set contains large amount of feature dimensions which are reduced using dimensionality reduction techniques. Kernelized SVM are employed over original data to identify the presence and absence of arrhythmia diseases. The accuracies are then improved by using Principal Component Analysis (PCA) over the original dataset. The models are then evaluated and compared using their accuracy and recall values. The results showed that on applying PCA over the data, Kernelized SVM outperforms the other classifiers with an accuracy rate