Abstract: 

Oracle MySQL HeatWave is a fully managed database service, powered by the integrated HeatWave in-memory query accelerator. It’s the only cloud database service that combines transactions, analytics, and machine learning services into one MySQL Database, delivering real-time, secure analytics without the complexity, latency, and cost of ETL duplication. HeatWave Machine Learning (HeatWave ML) fully automates the process to train a model, generate inferences and invoke explanations, all without extracting data or model out of the database. The user can use familiar SQL interfaces to invoke all the machine learning capabilities. HeatWave ML leverages Oracle AutoML which automates model generation by replacing complex and time-consuming tasks such as data preprocessing, algorithm selection, feature selection and hyperparameter optimization that a data scientist is otherwise expected to perform. With MySQL HeatWave ML, developers and data analysts can build, train, and explain machine learning models in a fully automated way—25X faster than Amazon Redshift ML at 1% of the cost.

Bio: 

Sandeep Agrawal leads the HeatWave Machine Learning (HeatWave ML) project within MySQL HeatWave. HeatWave ML is the product of years of research and advanced development, and aims to help both data scientists and non-data scientists quickly apply ML to a given problem. Prior to HeatWave, Sandeep led the Oracle AutoML project within Oracle labs, creating a state-of-the-art distributed AutoML engine. He is passionate about Machine Learning and Systems Architecture, and a project like HeatWave ML that combines the two is heaven for him. Prior to Oracle, he completed his PhD in Computer Science from Duke University in 2015.