HeatWave AutoML

Oracle HeatWave AutoML provides integrated, automated, and secure machine learning (ML)—helping you build, train, and explain ML models without ML expertise, data movement, or additional cost. It’s available on Oracle Cloud Infrastructure (OCI), Amazon Web Services (AWS), and Microsoft Azure.

チーフ・アーキテクトEdward ScrevenによるOracle CloudWorldの基調講演「生成AIアプリケーションの構築 - HeatWave GenAIとの統合・自動化」のリプレイをご覧ください。

Why use HeatWave AutoML?

  • Build applications faster with integrated ML

    Eliminate complex and time-consuming data movements to a separate ML service with integrated ML. Easily apply ML training, inference, and explanation to data stored either in MySQL Database or object storage.

  • Democratize machine learning

    Automate the ML lifecycle, including algorithm selection, intelligent data sampling for model training, feature selection, and hyperparameter optimization. No ML expertise is required.

  • Support data security

    Keep your data in one data management system with a single security configuration and centralized access controls. All communications are authenticated and encrypted.

  • Get more accurate results at lower cost

    Train ML models faster letting you retrain models more often and get more accurate results.

Key features of HeatWave AutoML

Comprehensive ML capabilities

HeatWave AutoML supports anomaly detection, forecasting, classification, regression, and recommender system tasks, including on text columns.

Built-in recommender system

By considering both implicit feedback (such as past purchases and browsing behavior) and explicit feedback (such as ratings and likes), the HeatWave AutoML recommender system can help, for example, generate personalized next purchase suggestions.

Explanable ML models

All the models trained by HeatWave AutoML are explainable. HeatWave AutoML delivers predictions with an explanation of the results, supporting you with trust, fairness, and regulatory compliance.

Data drift detection

Data drift detection helps analysts determine when to retrain models by detecting the differences between the data used for training and new incoming data.

Interactive console

The interactive console lets business analysts build, train, run, and explain ML models using a visual interface—there’s no need to know SQL commands or coding. They can also easily explore what-if scenarios to evaluate business assumptions.

Integrated with popular tools

HeatWave AutoML is integrated with popular notebooks, such as Jupyter and Apache Zeppelin.

HeatWave AutoML customer successes

Business analysts and developers without ML expertise can use HeatWave AutoML to help predict customer churn. The ML lifecycle is automated and data doesn’t leave the database, helping to reduce security risks. Once built, the model can predict the probability of customer churn.


Predict customer churn diagram, description below:

The user states that his/her use case is “I need the ability to predict customer churn”. He or she can then easily leverage the HeatWave AutoML automation to build a classification machine learning model, which is appropriate in this case. Once done, the user can use the ML model, for example asking, “How likely is this customer to churn?” and getting the answer “The probability that this customer will churn is 72%.”



Business analysts and developers without ML expertise can use HeatWave AutoML to help detect fraudulent transactions. The ML lifecycle is automated and data doesn’t leave the database, helping to reduce security risks. Once built, the model can predict the probability of fraud associated with transactions.


Detect fraudulent transactions diagram, description below:

The user states that his/her use case is “I need to detect potentially fraudulent transactions.”. He or she can then easily leverage the HeatWave AutoML automation to build an anomaly detection machine learning model, which is appropriate in this case. Once done, the user can use the ML model, for example asking, “Which of these transactions are likely to be fraudulent?” and getting the answer “Here are the transactions identified as potentially fraudulent with associated probabilities.”



Developers can build applications leveraging the combined power of built-in ML and generative AI in HeatWave to deliver personalized recommendations. In this example, the application uses the HeatWave AutoML recommender system to help suggest restaurants based on the user’s preferences or what the user previously ordered. With HeatWave Vector Store, the application can help additionally search through restaurants’ menus in PDF format to suggest specific dishes, providing greater value to customers.


RAG enhanced with ML diagram, description below:

A user asks via HeatWave Chat “What vegan dishes do you suggest for me today?”. First, the HeatWave AutoML recommender system suggests a list of restaurants based on what the user previously ordered. Then, HeatWave Vector Store provides an augmented prompt to the LLM based on the restaurants’ menus that it houses. The LLM can then generates a personalized recommendation of dishes in natural language.



See what top industry analysts say about HeatWave AutoML

  • Constellation Research logo

    “HeatWave does machine learning the right way. By bringing ML to the data with HeatWave AutoML in a cost-efficient, automated way, HeatWave accelerates ML adoption.”

    Holger Mueller
    Vice President and Principal Analyst, Constellation Research
  • The Futurum Group logo

    “The in-database HeatWave AutoML makes Redshift ML look like yesterday’s tech in terms of engineering, performance, and cost.”

    Ron Westfall
    Senior Analyst and Research Director, The Futurum Group
  • Moor Insights & Strategy logo

    “I believe the automation built into HeatWave AutoML will make it tangibly easier for customers to use, extending ML beyond the realm of data scientists.”

    Matt Kimball
    Vice President and Principal Analyst, Moor Insights & Strategy
  • Enterprise Strategy Group logo

    “With HeatWave AutoML, machine learning is democratized, it’s fast, uses up-to-date data, and costs less than other cloud database services.”

    Mike Leone
    Practice Director, Data Analytics and AI, Enterprise Strategy Group

Learn more about other HeatWave solutions for your different workloads

Get started with HeatWave AutoML

Documentation

Access the documentation to easily get started with HeatWave AutoML.

Learn with step-by-step guidance

Experience HeatWave AutoML at your own pace with step-by-step instructions.

Get started with HeatWave AutoML

You’ll learn how to build a predictive ML model using HeatWave AutoML.

Start this lab


Build a movie recommendation application with HeatWave AutoML

You’ll build MovieHub, a fictitious movie streaming application that delivers personalized movie recommendations using HeatWave AutoML.

Start this lab

Free HeatWave AutoML workshop

Request a free expert-led workshop to evaluate HeatWave AutoML or get started with it.

Try HeatWave AutoML for free

Sign up for a free trial of HeatWave AutoML. You’ll get access to free resources for an unlimited time.

Contact sales

Interested in learning more about HeatWave AutoML? Let one of our experts help.