Splunk on Tuesday outlined the latest versions of its flagship analytic suites with an focus on machine learning advances.
The company updated Splunk Enterprise, Splunk IT Service Intelligence (ITSI), Splunk Enterprise Security (ES) and Splunk User Behavior Analytics (UBA) for both cloud and on-premises deployments.
Splunk’s algorithms are focused on investigations for security incidents, alerting, predictive tools for operations and maintenance and business optimization for demand, inventory and analysis of historical data. Splunk says the machine learning advancements rely on these algorithms to help customers better monitor, investigate and build intelligence with their data.
Key updates include Splunk Enterprise cloud 7.0, which aims to boost performance and scale with faster metrics to speed up monitoring and alerting as well as optimizations to core search technology.
The latest version of Splunk ITSI builds in more machine learning for advanced anomaly detection, adaptive thresholds and event correlation. The new version of Splunk UBA integrates with custom machine learning models and also includes greater privacy controls with identity masking for PII information.
The Splunk Machine Learning Toolkit was updated to include a visual interface for creating and managing models, as well as public APIs for custom algorithms. The platform also features Spark (MLLiB) support for algorithmic training. Splunk also introduced a new anti-fraud product that uses machine learning to detect and investigate anomalies that might signal fraud.