Analyze streaming data, and take appropriate action instantly.

Analyze high-velocity big data while it’s still in motion – before it is stored – so you can take immediate action on what's relevant, and ignore what isn't.

Built for speed

Engineered for high-volume processing of millions of events per second and low-latency response times. Outperforms other ESP engines. 

Ingests & consolidates streaming IoT sources

Extensive suite of prebuilt connectors and adapters lets you consume today's IoT sources – including structured and unstructured data streams – and extend in the future.

Complete multiphase analytics

Embed SAS at the edge, in the fog and in data at rest, cleansing and analyzing data at each streaming event phase. In-depth SAS models are portable to the stream and the edge. Supports algorithms for vector data description, robust principal component analysis, random forest, gradient boosting and streaming regression analysis.

Flexible, open modeling environment

Intuitive visual interface makes it easy to define, test and refine models – no need for specialized programmers. Access coding environments via the interface. Python developer interfaces support design using familiar interfaces (e.g., Jupyter notebook).

Ready for real-time action 

Customizable alerts, notifications and updates provide situational awareness so you can react appropriately to what's happening or predicted to happen. 

Image & video analytics

Combines streaming analytics, video and image ingestion with powerful neural networks to process video and still image data, including image pre-processing and object detection and classification. 

Cloud ready

Compatible with cloud technologies, including BOSH Cloud Foundry, for large-scale distributed services. Ensures continuous, secure and stable event pattern detection through patented 1+N way failover, guaranteed delivery without persistence, full access to event stream model metadata, live stream queries and dynamic streaming model updates.

In-stream learning model windows

Use different window types – Train, Score, Calculate, Model Supervisor, Model Reader – for different tasks (e.g., specifying data stream input sources, patterns of interest and derived output actions).

Unified project deployment and server management

Use SAS Event Stream Manager to construct and manage reusable deployment templates, easily add new ESP servers, load and unload ESP projects, and automatically discover new servers using ESP agent technology for automated monitoring. When ESP servers are offline or unavailable, retry capabilities support redeploying models when connectivity resumes.

Seize opportunities and spot red flags hidden in torrents of fast-moving data flowing through your business.

SAS Event Stream Processing showing real-time dashboard on desktop monitor

Use machine learning to gain insights for taking the right action.

Streaming data from operations, transactions, sensors and IoT devices is valuable – when it's well-understood. Event stream processing from SAS includes streaming data quality and analytics – and a vast array of SAS and open source machine learning and high-frequency analytics for connecting, deciphering, cleansing and understanding streaming data – in one solution. No matter how fast your data moves, how much data you have, or how many data sources you’re pulling from, it’s all under your control via a single, intuitive interface. You can define patterns and address scenarios from all aspects of your business, giving you the power to stay agile and tackle issues as they arise. 

Make sound big data decisions.

Filter, normalize, categorize, aggregate, standardize and cleanse big data before you store it – saving significant staff and computing resources from having to clean up data lakes. Prebuilt data quality routines and text processing execution are applied to data in motion so big data is filtered and ready for consumption.

SAS Event Stream Processing, shown on desktop monitor, supports collaboration
SAS Event Stream Processing showing easy-to-use design interface on desktop monitor

Scale economically from edge to enterprise for growing data volumes. 

Faster, better and more powerful stream processing from edge to enterprise for high-volume throughput (millions of events per second) means low-latency response times, running in distributed, in-memory grid processing commodity hardware environments. Analyze a variety of structured and unstructured data sources – including video, text, and image classification and identification – using advanced analytic techniques that include machine learning and artificial intelligence.

Look Who's Working Smarter With SAS®

Rogers Communications logo
SciSports logo
Bank of America logo

Get to Know SAS® Event Stream Processing


Cisco logo
SAS Gold Partner

Cisco & SAS

Cisco and SAS are partnering in several strategic areas to help customers modernize their analytics architectures. SAS® Analytics on the Cisco Unified Computing System (UCS) integrates high-velocity delivery of information in real time. The benefits that result from conducting proofs of concepts of SAS applications with Cisco technology include reliable scalability, reduced data center costs, and improved efficiencies that allow staff to focus on strategic business initiatives.


Explore More on SAS® Event Stream Processing & Beyond

Back to Top