Build Systems that Drive Business
June 11–12, 2018: Training
June 12–14, 2018: Tutorials & Conference
San Jose, CA

Using AI to solve performance problems (sponsored by Salesforce)

Jasmin Nakic (Salesforce ), Jackie Chu (Salesforce)
9:00am–12:30pm Tuesday, June 12, 2018
Location: LL20 D Level: Beginner
Average rating: ****.
(4.67, 3 ratings)

Prerequisite knowledge

  • A working knowledge of scripting

Materials or downloads needed in advance

  • A laptop (Windows or macOS) with Python and scikit-learn or the Anaconda Development Environment installed

What you'll learn

  • Learn techniques to identify performance challenges by analyzing production data from Salesforce and other sources


In today’s cloud applications, performance is a critical factor for success in the market. Salesforce is working to ensure that customers have a good experience and that applications can scale to support billions of transactions and millions of active users each day.

Jasmin Nakic and Jackie Chu share techniques to identify performance challenges by analyzing production data from Salesforce and other sources and explore the AI models to predict trends, detect anomalies, and troubleshoot performance problems. You’ll learn how to visualize data created using predictive analytics and share them via an Einstein Analytics dashboard throughout your organization—all in just a few steps.


Production performance metric analysis

  • Time series trends
  • Capacity planning
  • Anomaly detection in production performance

Performance test result analysis

  • Response time analysis
  • Variance and anomalies in test results

Application log analysis

  • Detect patterns in log files
  • Troubleshooting performance issues

All conference type pass holders are welcome to attend this session.

This tutorial is sponsored by Salesforce.

Photo of Jasmin Nakic

Jasmin Nakic


Jasmin Nakic is lead software engineer on Salesforce’s Sales Cloud performance engineering team, where he helps optimize cloud-based applications and build solutions to analyze and predict performance. Jasmin focuses on bringing advanced predictive analytics and machine learning methods to massive amounts of system performance data. Previously, he did database and application development at Teradata, KickFire, KLA-Tencor, and Oracle. Jasmin started his computer science adventure in high school in his small hometown in Bosnia, where he wrote short programs to analyze results from astronomical observations on HP calculators. Later, at the University of Sarajevo, he studied system programming, compilers, advanced architectures, and networks and wrote a thesis on object-oriented approaches to database programming.

Photo of Jackie Chu

Jackie Chu


Jackie Chu is a lead software engineer at Salesforce, where he focuses on identifying performance bottlenecks, developing performance monitoring tools, tuning server-side components, and designing scalable solutions. Jackie has seven years of software engineering experience specializing in performance tuning and optimization in cloud distributed systems. He holds a degree in computer science from the University of California, San Diego.