Prelert announced a new feature of its Anomaly Detective machine learning engine that enables multidimensional analysis to be conducted on large volumes of data at high speed. This new feature, Stats Reduce, dramatically shrinks data transfer sizes, making it possible to perform the complex behavioral analysis of terabytes of data per hour.
Accurately identifying anomalous activities to detect the fingerprints of an advanced persistent threat or the cause of very complex IT performance issues requires a cross-correlated analysis of multiple data attributes. Performing this type of analysis at very large data scales has traditionally required a massive data transfer, which made real-time analysis impossible.
By leveraging the statistical aggregation functions already available in platforms like Splunk and Elasticsearch, Prelert’s Stats Reduce overcomes this challenge. The technology provides a 40x reduction in the amount of data that needs to be transferred and employs advanced analytics specifically designed to maintain data fidelity and return accurate results.
Stats Reduce has been tested against data sets from Prelert customers and the technology has been proven to return the same, accurate results whether operating on aggregated or raw data.
“Prelert is committed to providing the most accurate and robust insight into data in real-time, no matter how large or complex,” said Stephen Dodson Ph.D, Prelert’s CTO. “The scale of modern environments present challenges that require careful selection of methods and techniques, and we built our technology to align with these environments from the start. With Stats Reduce, the aggregation techniques we developed allow massive volumes of data to be analyzed in a distributed manner, enabling real-time multidimensional anomaly detection on Big Data.”
“Advanced threats and IT performance issues are becoming harder and harder to detect in part because they’re hidden in the massive amounts of machine data that IT systems generate every second,” said Dennis Drogseth, vice president at EMA. “Relying on the analysis of a single data source is no longer an adequate means to identify significant issues, as capturing increasingly complex interdependencies requires cross-correlated analysis of multiple data sets. Prelert’s ability to do this analysis in real time is a significant step toward providing more optimized and more secure service delivery.”
Keeping with Prelert’s mission to democratize data science and make it easy for everyday users, Stats Reduce is currently available in the latest version of Anomaly Detective, with push button functionality. Users must simply select “Use Stats Reduce” when deploying Anomaly Detective in the Splunk Enterprise environment. Stats Reduce will be available on other Big Data platforms in Q4 2014.
The Latest
For many B2B and B2C enterprise brands, technology isn't a core strength. Relying on overly complex architectures (like those that follow a pure MACH doctrine) has been flagged by industry leaders as a source of operational slowdown, creating bottlenecks that limit agility in volatile market conditions ...
FinOps champions crucial cross-departmental collaboration, uniting business, finance, technology and engineering leaders to demystify cloud expenses. Yet, too often, critical cost issues are softened into mere "recommendations" or "insights" — easy to ignore. But what if we adopted security's battle-tested strategy and reframed these as the urgent risks they truly are, demanding immediate action? ...
Two in three IT professionals now cite growing complexity as their top challenge — an urgent signal that the modernization curve may be getting too steep, according to the Rising to the Challenge survey from Checkmk ...
While IT leaders are becoming more comfortable and adept at balancing workloads across on-premises, colocation data centers and the public cloud, there's a key component missing: connectivity, according to the 2025 State of the Data Center Report from CoreSite ...
A perfect storm is brewing in cybersecurity — certificate lifespans shrinking to just 47 days while quantum computing threatens today's encryption. Organizations must embrace ephemeral trust and crypto-agility to survive this dual challenge ...
In MEAN TIME TO INSIGHT Episode 14, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses hybrid multi-cloud network observability...
While companies adopt AI at a record pace, they also face the challenge of finding a smart and scalable way to manage its rapidly growing costs. This requires balancing the massive possibilities inherent in AI with the need to control cloud costs, aim for long-term profitability and optimize spending ...
Telecommunications is expanding at an unprecedented pace ... But progress brings complexity. As WanAware's 2025 Telecom Observability Benchmark Report reveals, many operators are discovering that modernization requires more than physical build outs and CapEx — it also demands the tools and insights to manage, secure, and optimize this fast-growing infrastructure in real time ...
As businesses increasingly rely on high-performance applications to deliver seamless user experiences, the demand for fast, reliable, and scalable data storage systems has never been greater. Redis — an open-source, in-memory data structure store — has emerged as a popular choice for use cases ranging from caching to real-time analytics. But with great performance comes the need for vigilant monitoring ...
Kubernetes was not initially designed with AI's vast resource variability in mind, and the rapid rise of AI has exposed Kubernetes limitations, particularly when it comes to cost and resource efficiency. Indeed, AI workloads differ from traditional applications in that they require a staggering amount and variety of compute resources, and their consumption is far less consistent than traditional workloads ... Considering the speed of AI innovation, teams cannot afford to be bogged down by these constant infrastructure concerns. A solution is needed ...