Which song will Smith listen to next? Which restaurant will Alice go to
tomorrow? Which product will John click next? These applications have in common
the prediction of user trajectories that are in a constant state of flux over a
hidden network (e.g. website links, geographic location). What users are doing
now may be unrelated to what they will be doing in an hour from now. Mindful of
these challenges we propose TribeFlow, a method designed to cope with the
complex challenges of learning personalized predictive models of
non-stationary, transient, and time-heterogeneous user trajectories. TribeFlow
is a general method that can perform next product recommendation, next song
recommendation, next location prediction, and general arbitrary-length user
trajectory prediction without domain-specific knowledge. TribeFlow is more
accurate and up to 413x faster than top competitors.
%0 Generic
%1 Figueiredo2015TribeFlow
%A Figueiredo, Flavio
%A Ribeiro, Bruno
%A Almeida, Jussara
%A Faloutsos, Christos
%D 2015
%K preprint predictive-models human-behaviour marketing
%T TribeFlow: Mining & Predicting User Trajectories
%U http://arxiv.org/abs/1511.01032
%X Which song will Smith listen to next? Which restaurant will Alice go to
tomorrow? Which product will John click next? These applications have in common
the prediction of user trajectories that are in a constant state of flux over a
hidden network (e.g. website links, geographic location). What users are doing
now may be unrelated to what they will be doing in an hour from now. Mindful of
these challenges we propose TribeFlow, a method designed to cope with the
complex challenges of learning personalized predictive models of
non-stationary, transient, and time-heterogeneous user trajectories. TribeFlow
is a general method that can perform next product recommendation, next song
recommendation, next location prediction, and general arbitrary-length user
trajectory prediction without domain-specific knowledge. TribeFlow is more
accurate and up to 413x faster than top competitors.
@misc{Figueiredo2015TribeFlow,
abstract = {{Which song will Smith listen to next? Which restaurant will Alice go to
tomorrow? Which product will John click next? These applications have in common
the prediction of user trajectories that are in a constant state of flux over a
hidden network (e.g. website links, geographic location). What users are doing
now may be unrelated to what they will be doing in an hour from now. Mindful of
these challenges we propose TribeFlow, a method designed to cope with the
complex challenges of learning personalized predictive models of
non-stationary, transient, and time-heterogeneous user trajectories. TribeFlow
is a general method that can perform next product recommendation, next song
recommendation, next location prediction, and general arbitrary-length user
trajectory prediction without domain-specific knowledge. TribeFlow is more
accurate and up to 413x faster than top competitors.}},
added-at = {2019-06-10T14:53:09.000+0200},
archiveprefix = {arXiv},
author = {Figueiredo, Flavio and Ribeiro, Bruno and Almeida, Jussara and Faloutsos, Christos},
biburl = {https://www.bibsonomy.org/bibtex/2da61cdcb8efde673f67c31611daf6379/nonancourt},
citeulike-article-id = {13827750},
citeulike-linkout-0 = {http://arxiv.org/abs/1511.01032},
citeulike-linkout-1 = {http://arxiv.org/pdf/1511.01032},
day = 3,
eprint = {1511.01032},
interhash = {589d5e8effdd8a5441bcb52dc88c5bd2},
intrahash = {da61cdcb8efde673f67c31611daf6379},
keywords = {preprint predictive-models human-behaviour marketing},
month = nov,
posted-at = {2015-11-04 13:44:03},
priority = {2},
timestamp = {2019-08-22T16:20:33.000+0200},
title = {{TribeFlow: Mining \& Predicting User Trajectories}},
url = {http://arxiv.org/abs/1511.01032},
year = 2015
}