Filters








50,629 Hits in 3.7 sec

Incorporating revisiting behaviors into click models

Danqing Xu, Yiqun Liu, Min Zhang, Shaoping Ma, Liyun Ru
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
If a user clicks on a higher ranked document after having clicked on a lower-ranked one, we call this scenario a revisiting pattern, and we believe that the revisiting patterns are important signals regarding  ...  Most of these models share the sequential examination hypothesis, which is that users examine search results from the top to the bottom.  ...  Thus, according to the Bayes principle, the posterior probability is calculated as follows. p(R|C 1,...,N ) ∝ p(R)p(C 1,...  ... 
doi:10.1145/2124295.2124334 dblp:conf/wsdm/XuLZMR12 fatcat:ykmvilihd5ervdqizjth43jlum

Revisit Prediction by Deep Survival Analysis [chapter]

Sundong Kim, Hwanjun Song, Sejin Kim, Beomyoung Kim, Jae-Gil Lee
2020 Lecture Notes in Computer Science  
It generates the predicted event rate of the next k days rather than directly predicting revisit interval and revisit intention.  ...  In this paper, we introduce SurvRev, a next-generation revisit prediction model that can be tested directly in business. The SurvRev model offers many advantages.  ...  by the ranking loss function [13] and c-index [14] , we introduce the pairwise ranking loss to compare the orderings between the predicted revisit intervals.  ... 
doi:10.1007/978-3-030-47436-2_39 fatcat:qwh2gpn6encstjzt6q5xzj2ivy

Revisiting Francis Galton's Forecasting Competition

Kenneth F. Wallis
2014 Statistical Science  
One is forecast combination, with the mean forecast here exactly coinciding with the outcome, and the second is the use of two-piece frequency and probability distributions to describe asymmetry.  ...  Following the correction of some errors, it is shown that this forecasting competition is an interesting precursor of two more recent developments in the statistical forecasting literature.  ...  Note: facsimiles of the Galton and Pearson items are available at http://www.galton.org/.  ... 
doi:10.1214/14-sts468 fatcat:iqg536cjjnenxlurijkbbzkepu

Probabilistic models in IR and their relationships

Robin Aly, Thomas Demeester, Stephen Robertson
2013 Information retrieval (Boston)  
First, the belief probability ranking principle (BPRP), which considers uncertain relevance between known documents and the current query, and second, the popularity probability ranking principle (PPRP  ...  In this paper, we revisit Probability Ranking Principle (PRP)-based models, Probability of Relevance (PR) models, and language models, finding conceptual differences in their definition and interrelationships  ...  For example P X : E → [0 : 1] is a probability measure defined on the event space E for the process connected with event space X. 11 A conditional probability is the probability of an event e 1 given a  ... 
doi:10.1007/s10791-013-9226-3 fatcat:7uxtahlfxrfa7otv47z4go3f4i

Theory of Fuzzy Sets: An Overview

Mamoni Dhar, Hemanta .K. Baruah
2013 International Journal of Information Engineering and Electronic Business  
Furthermore, the existing probability-possibility consistency principles are also revisited and related results are v iewed fro m the standpoint of the Randomness-Fuzziness consistency principles.  ...  It is found that the existing definition of complementation as well as the probability -possibility consistency principles is not well defined.  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their careful read ing of this art icle and for their helpfu l co mments.  ... 
doi:10.5815/ijieeb.2013.03.03 fatcat:nse2ngnonvhsplafjrxlhjbppi

Emergence of scaling in human-interest dynamics

Zhi-Dan Zhao, Zimo Yang, Zike Zhang, Tao Zhou, Zi-Gang Huang, Ying-Cheng Lai
2013 Scientific Reports  
certain interest, and (3) interest ranking and transition.  ...  In particular, from the data sets we uncover fat-tailed (possibly power-law) distributions associated with the three basic quantities: (1) the length of continuous interest, (2) the return time of visiting  ...  Acknowledgments We thank Dr Junming Huang for the Douban data. This work was supported by the NSF of China (  ... 
doi:10.1038/srep03472 pmid:24326949 pmcid:PMC3858797 fatcat:jznayfc3vnftrhn2idi4xged4e

On the Condorcet Efficiency of Approval Voting and Extended Scoring Rules for Three Alternatives [chapter]

Mostapha Diss, Vincent Merlin, Fabrice Valognes
2010 Studies in Choice and Welfare  
On the Condorcet Efficiency of Approval Voting and Extended Scoring Rules for Three Alternatives  ...  ranking on a pair Interest: Estimate the probability of aMb, given that aΘb.  ...  The main objective: Revisit the Condorcet efficiency in this context.  ... 
doi:10.1007/978-3-642-02839-7_11 fatcat:wbi2g5rw5zbvtbld7zfpraluvi

Penalized polytomous ordinal logistic regression using cumulative logits. Application to network inference of zero-inflated variables [article]

Aurélie Deveau, Anne Gégout-Petit, Clémence Karmann
2019 arXiv   pre-print
We then introduce the Lasso estimation of the regression coefficients using the Frank-Wolfe algorithm.  ...  To deal with the choice of the penalty parameter, we use the stability selection method and we develop a new method based on the knockoffs idea.  ...  The principle of the former is to estimate the probability for a variable to be in the model using bootstraps.  ... 
arXiv:1805.10097v2 fatcat:7ecuud727rhrhhuzgan5mhzwkq

Non-Markovian Character in Human Mobility: Online and Offline [article]

Zhi-Dan Zhao, Shi-Min Cai, Yang Lu
2014 arXiv   pre-print
The dynamics of human mobility characterizes the trajectories humans follow during their daily activities and is the foundation of processes from epidemic spreading to traffic prediction and information  ...  The non-Markovian character observed from both online and offline cases is suggested by the scaling law in the distribution of dwelling time at individual and collective levels, respectively.  ...  Its principle makes the desired probability distribution be the best fit of observed data, and its methodology tries to do two things.  ... 
arXiv:1406.2685v1 fatcat:jylqv7qr2rbl3p34gujjxxxhoi

Representing personal web information using a topic-oriented interface

Zhigang Hua, Hao Liu, Xing Xie, Hanqing Lu, Wei-Ying Ma
2005 Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05  
In our approach, we proposed to utilize anchor, title and URL information to represent content information for the browsed Web pages rather than the content body.  ...  The experimental results demonstrated that users could visit the pages that have been browsed previously more easily with our approach than existing solutions.  ...  Further, the clusters are ranked according to their salience scores, thus the more likely a cluster required by users, the higher it ranks.  ... 
doi:10.1145/1062745.1062909 dblp:conf/www/HuaLXLM05 fatcat:oipql4fnzffhbm6mrveufnpd6q

Ranking Alternatives by Pairwise Comparisons Matrix and Priority Vector

Jaroslav Ramík
2017 Scientific Annals of Economics and Business  
The decision making problem considered here is to rank n alternatives from the best to the worst, using information given by the decision maker(s) in the form of an n×n pairwise comparisons (PC) matrix  ...  Here, we deal with two essential elements of AHP: measuring consistency of PC matrix and the method of eliciting the priority vector by which the final ranking of alternatives is derived.  ...  Acknowledgements This paper was supported by the Ministry of Education, Youth and Sports Czech Republic within the Institutional Support for Long-term Development of a Research Organization in 2017.  ... 
doi:10.1515/saeb-2017-0040 fatcat:e6vpd5vsevbudk4ao3yftlllba

Optimal coding and the origins of Zipfian laws [article]

Ramon Ferrer-i-Cancho, Christian Bentz, Caio Seguin
2020 arXiv   pre-print
Optimal non-singular coding in combination with the maximum entropy principle also predicts Zipf's rank-frequency distribution.  ...  Optimal non-singular coding predicts that the length of a word should grow approximately as the logarithm of its frequency rank, which is again consistent with Zipf's law of abbreviation.  ...  CB is supported by the DFG Center for Advanced Studies Words, Bones, Genes, Tools at the University of Tübingen, and by the Swiss National Foundation Grant on "Non-randomness in Morphological Diversity  ... 
arXiv:1906.01545v4 fatcat:l32xrr6pczfuvhaymahyasv2tq

Rejoinder: Harold Jeffreys's Theory of Probability Revisited

Christian P. Robert, Nicolas Chopin, Judith Rousseau
2009 Statistical Science  
Further discussions with them and other leading statisticians showed that the legacy of Theory of Probability is alive and lasting. [arXiv:0804.3173]  ...  Nowadays, this is certainly the most standard example that illustrates how the principle for constructing Jeffreys' priors may violate the likelihood principle (Berger and Wolpert, 1988) .  ...  The point about §3.10 and the integration over the sample space was missed in our analysis but is indeed crucial in its link with the likelihood principle that does not appear per se in Theory of Probability  ... 
doi:10.1214/09-sts284rej fatcat:7u4lha7t4jgmrafscgmdn5bhry

Page 7 of AMC Journal Vol. 77, Issue 1 [page]

1991 AMC Journal  
This activity was targeted as a probable way to force the Lecky principle into a “higher gear” by the Republican party, which has hopes of taking control of the U.S.  ...  Lecky Revisited But let’s go back to the Lecky principle and to see whether the 1990 election results portend any more decided U.S. societal changes in 1992 and beyond.  ... 

Page 168 of The Westminster Review Vol. 82, Issue 161 [page]

1864 The Westminster Review  
It is impossible to determine the absolute rank of living authors. ‘“ Fénélon was unjust to Moliére, and Bossuet cruel ; Madame de Sévigny ranked Bourdaloue too high, and Racine too low.”  ...  Two principles, both thoroughly French yet both contradic- tory, alternately influence the Home administration and the Foreign. policy of France.  ... 
« Previous Showing results 1 — 15 out of 50,629 results