Content recommendation systems (recommenders) are pervasive. Although recommenders have been primarily devised to account for users interests with respect to the content catalog, it is a matter of fact that mobile users are typically served by unreliable networks, subject to losses and low QoS. Can content recommenders compensate for low QoS? We conducted measurements over the Internet, and verify that making requests a bit trendier can hit much closer content, suggesting conditions under which recommenders can compensate for low QoS, at zero costs for the operator.
Can recommenders compensate for QoS?
IMC 2021, ACM SIGCOMM Internet Measurement Conference, 2-4 November 2021, New York, NY, USA (Online Event)
Poster / Demo
© ACM, 2021. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in IMC 2021, ACM SIGCOMM Internet Measurement Conference, 2-4 November 2021, New York, NY, USA (Online Event)
PERMALINK : https://www.eurecom.fr/publication/6729