Conference archive


Thursday, October 6, 2016 - 9:45am to 10:45am

Understanding Complex Web Performance Measurement

Add to calendar

In performance testing we run a suite of tests, modify the system in an attempt to improve its performance, and then repeat the tests. We want to know if the performance is “better.” However, no single performance measure exists; we must consider and evaluate many variables. Although viewing a full histogram of various test runs is more helpful, quantifying the change between the tests becomes the challenge. Parvez Ahammad introduces the relative divergence index (RDI), a multidimensional statistical method to compare differences between two sets of performance data. Sharing a case study, Parvez analyzes results from a variety of tests and scenarios. Exploring the web performance of highly rated Internet retailer websites, you’ll see how various tests measure up and how RDI provides a more insightful measurement. Because traditional methods of comparing two sets of performance data have limitations, Parvez provides pointers on how to remedy the limitations for your own systems and gain new perspectives on improving web performance.

Instart Logic

With expertise in computer vision, machine learning, statistics, and signal processing, Parvez Ahammad leads the data science and machine learning group at Instart Logic Inc. Parvez has worked on a wide array of problems in domains of web application delivery, neuroscience, bioinformatics, and heterogeneous sensor networks. He is the creator of novel algorithmic technologies such as SmartVision at Instart Logic, OpSIN and Salient Watershed at HHMI–Janelia, and fast video activity recognition at UC-Berkeley.