Catalog
- Results include
-
Mechanisms to manage incentives in online systems
Aperjis, Christina2009.Online Search ProQuest Dissertations & Theses. Not all titles available.
-
A buffer-based approach to video rate adaptation [electronic resource]
Huang, Te-Yuan (Engineer)2014.During peak viewing time, well over 50% of US Internet traffic is streamed video from Netflix and YouTube. To provide a better streaming experience, these services adapt their video rates by observing and estimating the available capacity. However, accurate capacity estimation is difficult due to highly variable throughput and complex interactions between layers. As a result, existing rate adaptation algorithms often lead to suboptimal video quality and unnecessary rebuffers. This thesis proposes an alternative buffer-based approach to adapt video rate. Rather than presuming that capacity estimation is always required, this approach starts the design by only using the playback buffer occupancy, and then ask when capacity estimation can be helpful. This design process leads to two separate phases of operation: during the steady-state phase, when the buffer encodes adequate information, we choose the video rate based only on the playback buffer; during the startup phase, when the buffer contains little information, we augment the buffer-based design with capacity estimation. This approach is tested with a series of field experiments spanning millions of Netflix users from May to September, 2013. The results demonstrate that although a simple capacity estimation is important during the startup phase, it is unnecessary in the steady state. The buffer-based approach allows us to reduce the rebuffer rate by 10-20% compared to a commercial algorithm used in Netflix, while delivering a similar overall average video rate and a higher video rate in steady state.
-
How to design and analyze online A/B tests within decentralized organizations
Walsh, David Jonathan Max[Stanford, California] : [Stanford University], 2019.From e-commerce to digital media to social networks, essentially any company that does business online is using A/B tests -- randomized experiments on its customers -- in order to optimize its service. A standard approach to designing and analyzing these experiments, based on classical statistical theory, is ubiquitous in industrial practice. Namely, a sample size for each test should be set in advance, and the data collected should be analyzed in isolation through p-values and confidence intervals that are computed based on a 2-sample t-test of means. This thesis investigates four ways that this default approach proves insufficient, due to the decentralized manner in which A/B tests at these companies are run. For each of the four, we empower experimenters to continue their current behavior, while we offer novel methodology that is simple to implement and ensures inferential reliability. Some of our methods are now in use in industry. We supplement our theoretical results with empirical data from these industrial deployments.
Guides
Library website
Exhibits
EarthWorks
More search tools
Tools to help you discover resources at Stanford and beyond.
