Abstract: 

As part of Salesforce's Platform performance engineering team, we use Python to employ anomaly detection techniques and other analytics methods for monitoring customer data. This helps us gain real-time insights into the performance of our production data and its impact on customers. By promptly identifying anomalies and extracting valuable insights, we improve system reliability, reduce downtime, and enhance customer trust—core values at Salesforce.

Our efficient data processing capabilities enable faster modeling, analytics, and anomaly detection. In our technical talk, we'll demonstrate the value of machine learning and analytical visualizations in solving real-world data analytics challenges. We'll showcase how our data-driven production system addresses these challenges, emphasizing the importance of data analytics in ensuring reliable systems and building customer trust.
Key Points:

1. Anomaly Detection: We use techniques to detect abnormal patterns in customer data, ensuring prompt identification and resolution of anomalies for system reliability.
2. Real-time Insights: Our data analytics techniques provide immediate insights into production data performance, enabling proactive measures for optimization.
3. System Reliability and Reduced Downtime: Data analytics minimizes system downtime by actively monitoring and resolving performance issues.
4. Enhanced Customer Trust: Our data-driven approach shows our commitment to delivering a trustworthy platform that customers can rely on.
5. Efficient Data Processing: We efficiently collect, aggregate, and process large volumes of data, facilitating faster modeling, analytics, and anomaly detection.

By sharing the value of machine learning and analytical visualizations, we aim to inspire attendees with practical insights and strategies for their own performance engineering efforts.

Bio: 

Tuli Nivas is a Software Engineering Architect at Salesforce with extensive experience in design and implementation of test automation and monitoring frameworks. Her interests lie in software testing, cloud computing, big data analytics, systems engineering, and architecture. Tuli holds a PhD in computer science with a focus on building processes to set up robust and fault-tolerant performance engineering systems. Her recent area of expertise has been around machine learning and building data analytics for better and faster troubleshooting of performance problems and anomaly detection in production.