This is a dedicated watch page for a single video.
A financial services company is building a customer churn prediction model on AWS. The dataset includes call logs, customer interaction history, and transactional data from an on-premises PostgreSQL database. The call logs and interaction history are stored in Amazon S3, while the PostgreSQL tables remain on-premises. The data science team needs to aggregate and preprocess data from these various sources to ensure it is ready for machine learning model training. They must also resolve challenges such as feature inconsistencies and ensure schema alignment across the data sources. Which AWS service or feature can efficiently connect and aggregate the data from these sources?