Fraud Detection using PySpark

Big data is a massive amount of information on a given topic. Big data includes information that is generated, stored, and analyzed on a vast scale too vast to manage with traditional information storage systems. In health care, the move to digitize records and the rapid improvement of medical technologies have paved the way for big data to have a big impact in the field.

Many industries use big data to learn about their customers and tailor their products or services accordingly. In health care, big data sources include patient medical records, hospital records, medical exam results, and information collected by healthcare testing machines (such as those used to perform electrocardiograms, also known as EKGs). Big data collection and analysis enables doctors and health administrators to make more informed decisions about treatment and services.

We aimed to develop a model that will accurately predict a patient’s survival based on this information. Intensive Care Units are meant for individuals who are extremely sick or hurt and require intensive treatment and close monitoring. We used ml in pyspark and build support vector machine model to predict a patient’s survival. The accuracy of the model is 91.1%.