Name
Abstract | ||
|---|---|---|
We design predictors of user dissatisfaction with the performance of applications that use networking. Our approach combines user-level feedback with low level machine and networking metrics. The main challenges of predicting user dissatisfaction, that arises when networking conditions adversely affect applications, comes from the scarcity of user feedback and the fact that poor performance episodes are rare. We develop a methodology to handle these challenges. Our method processes low level data via quantization and feature selection steps. We combine this with user labels and employ supervised learning techniques to build predictors. Using data from 19 personal machines, we show how to build training sets and demonstrate that non-linear SVMs achieve higher true positive rates (around 0.9) than predictors based on linear models. Finally we quantify the benefits of building per-application predictors as compared to general predictors that use data from multiple applications simultaneously to anticipate user dissatisfaction. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/INFCOM.2013.6566770 | INFOCOM |
Keywords | Field | DocType |
computer network performance evaluation,ergonomics,internetworking,learning (artificial intelligence),support vector machines,Internet application performance,data labelling,end-hosts,feature selection,low-level data processing,low-level machine metrics,low-level networking metrics,networking conditions,nonlinear SVM,personal machines,quantization,supervised learning techniques,training sets,true-positive rates,user dissatisfaction prediction,user-level feedback | Scarcity,Feature selection,Linear model,Computer science,Support vector machine,Computer network,Supervised learning,Internetworking,Artificial intelligence,Quantization (signal processing),Machine learning,The Internet | Conference |
ISSN | ISBN | Citations |
0743-166X | 978-1-4673-5944-3 | 4 |
PageRank | References | Authors |
0.52 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joumblatt, D. | 1 | 4 | 0.52 |
| Chandrashekar, J. | 2 | 8 | 0.98 |
| Branislav Kveton | 3 | 455 | 49.32 |
| Nina Taft | 4 | 2109 | 154.92 |