【正文】 rience. By unified, we want to see how the set of quality metrics taken together impact quality, as opposed to each metric in isolation. This is especially relevant since there are natural tradeoffs between the metrics。 ., lower bitrate can ensure lower buffering but reduces the user experience. Similarly, by quantitative, we want to go beyond a simple correlational understanding of “metric M impacts engagement”, to a stronger statement of the form “changing metric M from x to x’ changes engagement from y to y”’.Unfortunately, the state of the art in our understanding of video QoE is limited to a simple qualitative understanding of how individual metrics impact engagement [19]. This leads to severe shortings for every ponent of the video ecosystem. For example, adaptive video players today resort to ad hoc tradeoffs between bitrate, startup delay, and buffering [16,20,32]. Similarly, frameworks for multiCDN optimization use primitive QoE metrics that only capture buffering effects without accounting for the impact of bitrate or bitrate switching [28, 29]. Finally, content providers do not have systematic ways to evaluate the costperformance tradeoffs that different CDNs or multiCDN optimizations offer [1].We observe that there are three key factors that make it challenging to obtain a unified and quantitative understanding of Internet video QoE:Complex relationships: The relationships between the quality metrics and the effective user experience can be quite plex and even counterintuitive. For example, while one would naturally expect a higher video bitrate leading to better user experience, we observe a nonmonotonic relationship between the two.Metric dependencies: The metrics themselves have subtle interdependencies and have implicit tradeoffs. For example, although switching bitrates to adapt to the bandwidth conditions can reduce buffering, we observe that high rates of switching can annoy users.Impact of content: There are many confounding factors introduced by the nature of the content itself. For example, different genres of content such as live and videoondemand (VOD) show very different viewing patterns. Similarly, users’ interest in content also affects their tolerance nontrivially.Our goal in this paper is to identify a feasible roadmap toward developing a robust, unified and quantitative QoE metric that can address these challenges. We have two intuitive reasons to be hopeful. The challenges raised by plex relationships and subtle interdependencies can be addressed by casting QoE inference as a machine learning problem of building an appropriate model that can predict the user engagement (., play time) as a function of the various quality metrics. The second issue of contentinduced effects can be addressed using domainspecific and measurementdriven insights to carefully set up the learning tasks.Our preliminary results give us reason to be example, a decision tree based classifier can provide close to 50% accuracy in predicting the engagement. Carefully setting up the inputs and features for the learning process could lead to as high as 25% gain in accuracy of the prediction model.Figure 1: Overview of the Internet video ecosystem。 a robust QoE metric is critical for every ponent in this ecosystem.The rest of this paper is organized as follows. Section 2 describes how a standardized QoE metric would impact the different players in the video ecosystem. Section 3 describes the main challenges in developing a QoE metric. Section 4 makes the case for a predictive model for developing a QoE metric. In Section 5, we present some preliminary results before discussing various challenges in Section 6. We conclude in Section 7.2. USE CASES FOR VIDEO QOEWe begin with a brief overview of the Internet video ecosystem today and argue why there is an immediate need for a standardized QoE metric and how this impacts the different players in the video ecosystem (Figure 1).Content providers like HBO, ABC, and Netflix would like to maximize their revenues from subscription and adbased business models while trying to minimize their distribution costs. To this end, content providers have business arrangements with CDNs (., Akamai, Limelight) and also with thirdparty analytics (., Ooyala [8]) and optimization services (., Conviva [5]). A robust QoE metric enables content providers to objectively evaluate the costperformance tradeoffs offered by the CDNs and the value that such thirdparty services offer.Content Distribution Networks need to allocate their distribution resources (., server and bandwidth capacity) across user population. They need standard metrics to demonstrate superior costperformance tradeoffs. CDNs also need such metrics to guide the design of their delivery infrastructures to minimize their delivery costs while maximizing their performance [24].Recent studies have argued the case for crossCDN optimization [28, 29] and there are already mercial services (., Conviva [5]) that provide these capabilities. These services need standard measures to demonstrate quantifiable value to the content providers. An open challenge that such optimization frameworks face is the choice of a suitable quality metric that needs to be optimized [29].Similarly, thirdparty video analytics services need concrete ways to translate their insights with respect to user demographics and user behaviors into quantitative engagement effects.Video player designers have to make conscious tradeoffs in their bitrate adaptation algorithms. For example, moving to a higher bitrate may offer better engagement but increases the risk of buffering that is known to annoy users. Similarly, user studies suggest that users cannot tolerate too frequent bitrate switches as it impacts their perceptual experience [18]. The lack of a systematic understanding of video QoE forces player designers to use ad hoc adaptation strategies without a clear optimization goal [