testsetset
Businesses of a certain size that measure clicks, sensor readings, and other event-driven data produce datasets that can exceed millions or even billions of records. It’s no easy feat implementing a system that can derive insights from the deluge, but fortunately for Google Cloud customers, there’s a new plug-and-play solution: Cloud Inference API.
As Google software engineer Emanuel Taropa today explained in a blog post, Cloud Inference API is designed to tap large time series datasets to generate predictions. It’s fully integrated with Google Cloud Storage, and launching this week in public alpha.
Key features include a query language that lets you specify the time windows over which to compute correlations, and a powerful engine that performs those correlations up to “hundreds of thousands of times a second” on datasets with “trillions of events.” Also in tow is a streaming update interface that supports real-time, context-dependent analysis over time series data.
“This can be used in a variety of applications, from suggesting trending topics to detecting anomalies from sensor data,” Taropa wrote. “Many different industries can benefit from time-series data prediction. Retailers can analyze foot traffic to sales conversion rates at brick-and-mortar locations or online. Content providers can use collaborative filtering to offer users high-quality recommendations. And IoT companies can correlate multiple sensor data sources in real-time.”
June 5th: The AI Audit in NYC
Join us next week in NYC to engage with top executive leaders, delving into strategies for auditing AI models to ensure fairness, optimal performance, and ethical compliance across diverse organizations. Secure your attendance for this exclusive invite-only event.
Google said that Snap is using the Cloud Inference API to replace several of its custom data flows.
“[Cloud Inference API promises] very low latency and real-time updates,” Peter Ciccolo, software engineer at Snap, said. “Moreover, the same data can be used for multiple purposes, making it easy to explore new features with minimal custom code.”
The launch of Google’s Cloud Inference API comes a week after the Mountain View company’s publication of a whitepaper explaining its data deletion policies, and about a month after the public launch of Cloud Talent Solution, a development platform for job search workloads that factors in desired commute time, mode of transit, and other preferences in matching employers with job seekers.
