Elastic principal data scientist Susan Chang leverages her background in econometrics to develop machine learning models that help organizations detect anomalous behavior within large-scale security data sets.

Key Points

• Susan Chang applies statistical modeling techniques from econometrics to identify complex patterns in high-volume security logs for Elastic Security.
• Her team develops evaluation frameworks to measure AI model performance, specifically focusing on reducing false positives and improving threat detection accuracy.
• Elastic’s architecture enables the training and deployment of machine learning models directly within Elasticsearch to monitor network activity and server behavior.
• Chang utilizes a minimalist workspace featuring an Apple M4 Pro, a 34-inch Acer ultrawide monitor, and a compact 65% mechanical keyboard to maintain productivity.
• She bridges the gap between machine learning and cybersecurity by presenting research on AI-driven security features at industry conferences.

Why it Matters

The integration of advanced machine learning into security operations allows organizations to process massive, time-series data streams that would be impossible to analyze manually. By focusing on rigorous evaluation frameworks, data scientists like Chang are helping to make AI-driven threat detection more reliable and actionable for enterprise security teams.