Project for EECS6893 Big Data Analytics - Medicare Fraud Detection
Data is available publicly at "https://data.cms.gov/provider-summary-by-type-of-service/medicare-physician-other-practitioners/medicare-physician-other-practitioners-by-provider-and-service/data".
All code has been appropriately commented for its usage , download codebase as ZIP and start running files via Pyspark initially for setup.
After pyspark is configured with GCP bucket, setup Apache Machine Learning Libraries, BigQuery and DataStudio.
Refer to report in /docs section for detailed information