@inproceedings{GrassiEtAl:Infocom21,
  author	= {Grassi, Giulio and Barakat, Chadi and Crovella, Mark and Teixeira, Renata},
  title		= {Leveraging Website Popularity Differences to Identify Performance Anomalies},
  booktitle	= {Proceedings of Infocom 2021},
  year		= {2021},
  month		= may,
  address	= {Online},
  URL		= {http://www.cs.bu.edu/faculty/crovella/paper-archive/infocom21-website-anomalies.pdf},
  doi		= {10.1109/INFOCOM42981.2021.9488832},
  abstract	= {Web performance anomalies (time periods when metrics like page load time are abnormally high) have significant impact on user experience and revenue of web service providers. Existing methods to automatically detect web performance anomalies focus on popular websites (eg, with tens of thousands of visits per minute). However, across a more representative set of websites, passive measurement volume varies enormously, and some sites will only have small numbers of measurements per hour. Low rates of measurement creates gaps and noise that prevent the use of existing methods. This paper develops WMF, a web performance anomaly detection method applicable across a range of websites with highly variable measurement volume. To demonstrate our method, we leverage data from a website monitoring company, which allows us to leverage cross-site measurements. WMF uses matrix factorization to mine patterns that emerge from a subset of the websites to ``fill in'' missing data on other websites. Our validation using both a controlled website and synthetic anomalies shows that WMF's F1-score is more than double that of the state-of-the-art method. We then apply WMF to three months of web performance measurements to shed light on performance anomalies across a variety of 125 small to medium websites.}
}