Please note that the contents of this offline web site may be out of date. To access the most recent documentation visit the online version .
Note that links that point to online resources are green in color and will open in a new window.
We would love it if you could give us feedback about this material by filling this form (You have to be online to fill it)



Getting Started

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.

Contents

  1. Introduction
  2. What Can the Prediction API Do?
  3. Prerequisites
  4. Questions, Feedback, and Notifications
  5. Recommended Reading Order

Introduction

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.

Prerequisites

Questions, Feedback, and Notifications

The Prediction API offers several ways to become involved in the Prediction API community:

Recommended Reading Order

  1. Try the Hello World application to see the Prediction API in action.
  2. Read the developer guide and reference to learn how to use the API.
  3. Read the pricing and terms of service page to learn about free quota and pricing.
  4. Look at the example applications for end-to-end code examples that use the API to solve (simple) real-world problems.
  5. Look over the list of helper libraries that you can use to call the API in a variety of languages.

Authentication required

You need to be signed in with Google+ to do that.

Signing you in...

Google Developers needs your permission to do that.