TY - JOUR
T1 - Predictive models and analysis for webpage depth-level dwell time
AU - Wang, Chong
AU - Zhao, Shuai
AU - Kalra, Achir
AU - Borcea, Cristian
AU - Chen, Yi
N1 - Funding Information:
This work is partially supported by NSF under grants No. CAREER IIS-1322406, CNS 1409523, and DGE 1565478, by a Google Research Award, and by an endowment from the Leir Charitable Foundations. Any opinions, findings, and conclusions expressed in this material are those of the authors and do not necessarily reflect the views of the funding agencies
Publisher Copyright:
© 2018 ASIS&T
PY - 2018/8
Y1 - 2018/8
N2 - A half of online display ads are not rendered viewable because the users do not scroll deep enough or spend sufficient time at the page depth where the ads are placed. In order to increase the marketing efficiency and ad effectiveness, there is a strong demand for viewability prediction from both advertisers and publishers. This paper aims to predict the dwell time for a given ‹user, page, depth› triplet based on historic data collected by publishers. This problem is difficult because of user behavior variability and data sparsity. To solve it, we propose predictive models based on Factorization Machines and Field-aware Factorization Machines in order to overcome the data sparsity issue and provide flexibility to add auxiliary information such as the visible area of a user's browser. In addition, we leverage the prior dwell time behavior of the user within the current page view, that is, time series information, to further improve the proposed models. Experimental results using data from a large web publisher demonstrate that the proposed models outperform comparison models. Also, the results show that adding time series information further improves the performance.
AB - A half of online display ads are not rendered viewable because the users do not scroll deep enough or spend sufficient time at the page depth where the ads are placed. In order to increase the marketing efficiency and ad effectiveness, there is a strong demand for viewability prediction from both advertisers and publishers. This paper aims to predict the dwell time for a given ‹user, page, depth› triplet based on historic data collected by publishers. This problem is difficult because of user behavior variability and data sparsity. To solve it, we propose predictive models based on Factorization Machines and Field-aware Factorization Machines in order to overcome the data sparsity issue and provide flexibility to add auxiliary information such as the visible area of a user's browser. In addition, we leverage the prior dwell time behavior of the user within the current page view, that is, time series information, to further improve the proposed models. Experimental results using data from a large web publisher demonstrate that the proposed models outperform comparison models. Also, the results show that adding time series information further improves the performance.
UR - http://www.scopus.com/inward/record.url?scp=85047477511&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047477511&partnerID=8YFLogxK
U2 - 10.1002/asi.24025
DO - 10.1002/asi.24025
M3 - Article
AN - SCOPUS:85047477511
SN - 2330-1635
VL - 69
SP - 1007
EP - 1022
JO - Journal of the Association for Information Science and Technology
JF - Journal of the Association for Information Science and Technology
IS - 8
ER -