Cloud Inference API^Alpha

Quickly run large-scale correlations over typed time-series datasets.

Illustration with open laptop networked to a server, with the Cloud Inference product icon. Sever networked to a data stack and the cloud

Overview

Time-series analysis is essential for day-to-day operation of many companies. Most popular use cases include analyzing foot traffic and conversion for retailers, detecting data anomalies, identifying correlations in real time over sensor data, or generating high-quality recommendations. With Cloud Inference API Alpha, you can gather insights in real time from your typed time-series datasets.

Computer monitor with lines of data leading out of it, over which hover 3 magnifying glasses and the Cloud Inference product icon

Easy to use

Get everything you need to understand your API query results, such as groups of events that were examined, number of groups of events, and the background probability of each returned event.

Computer monitor with lines of code, a stopwatch, and the Cloud Inference icon

Real-time analysis

Stream data in real time, making it possible to compute correlations for real-time events.

Monitor with Google Cloud Platform icon on it and icons for Google Maps, Gmail, and Search surrounding it, with a blue shield bearing a checkmark in the foreground

Secure

Rely on Google Cloud’s end-to-end infrastructure and defense-in-depth approach to security that’s been innovated on for over 15 years through consumer apps like Gmail and Search.

Illustration of a monitor with the Google Cloud Platform icon, a server stack, an API, and the Cloud Inference icon

Integrated

At its core, Cloud Inference API is fully integrated with other Google Cloud Storage services, providing you with a consistent method of access across all storage products.

Features

Anomaly and trend detection

Detect trends and anomalies with event time markers.

Large scale

Handle datasets consisting of up to tens of billions of events. Run thousands of queries per second.

Low latency for queries

Rely on low latency and use the API as a recommendation back end for interactive, user-facing applications.

Serverless and fully managed

Cloud Inference API is fully managed so you can focus on insights, not infrastructure.

Cloud Inference API promises to replace several custom dataflows with a single system that offers very low latency and real-time updates. Moreover, the same data can be used for multiple purposes, making it easy to explore new features with minimal custom code.
Peter Ciccolo, Software Engineer, Snapchat