This page describes the basics of what the Google Prediction API is, how to use it, and how to get the most from the documentation.
- What Can the Prediction API Do?
- Questions, Feedback, and Notifications
- Recommended Reading Order
This documentation includes a quick "Hello World" application that you can follow to try out the API in just a few minutes. We also provide two complete example web sites that use the API for spam detection and movie preference prediction.
The API is fairly simple to use; it exposes only a few basic calls. Most of the work for you will be restructuring your problem into a format that the API can answer, and then designing training data appropriate for the question.
The Prediction API is accessed by a RESTful interface. You can use your own tools for sending API calls, but we provide several libraries or scripts to access the API using different languages.
What Can the Prediction API Do?
The Prediction API provides pattern-matching and machine learning capabilities. Given a set of data examples to train against, you can create applications that can perform the following tasks:
- Given a user's past viewing habits, predict what other movies or products a user might like.
- Categorize emails as spam or non-spam.
- Analyze posted comments about your product to determine whether they have a positive or negative tone.
- Guess how much a user might spend on a given day, given his spending history.
- You must have a Google Account.
- You must have an Google Developers Console project with both the Google Prediction API and Google Cloud Storage API activated.
Questions, Feedback, and Notifications
The Prediction API offers several ways to become involved in the Prediction API community:
- For general questions and discussions, visit the Prediction API Discuss Forum.
- For announcements such as new version releases, new features, or service availability notifications, visit the Prediction API Announce Forum.
- For feature suggestions, or to give feedback or file bugs, see the Suggestions, Feedback, and Bugs page.
Recommended Reading Order
- Try the Hello World application to see the Prediction API in action.
- Read the developer guide and reference to learn how to use the API.
- Read the pricing and terms of service page to learn about free quota and pricing.
- Look at the example applications for end-to-end code examples that use the API to solve (simple) real-world problems.
- Look over the list of helper libraries that you can use to call the API in a variety of languages.