Filters








5,610 Hits in 7.0 sec

Denoising User-aware Memory Network for Recommendation [article]

Zhi Bian, Shaojun Zhou, Hao Fu, Qihong Yang, Zhenqi Sun, Junjie Tang, Guiquan Liu, Kaikui Liu, Xiaolong Li
2021 arXiv   pre-print
Meanwhile, the existing methods utilize item sequence for capturing the evolution of user interest.  ...  Based on this observation, we propose a novel CTR model named denoising user-aware memory network (DUMN).  ...  of users and items, and capture the evolution of users' interests through LSTM/GRU network modeling click sequence [18, 22, 37] .  ... 
arXiv:2107.05474v1 fatcat:nfrvl5epi5fztm4r6qfqcqa6qu

Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction

Yikai Wang, Liang Zhang, Quanyu Dai, Fuchun Sun, Bo Zhang, Yang He, Weipeng Yan, Yongjun Bao
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems.  ...  With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities.  ...  In order to take advantage of such temporal information in users' historical clicking records, we propose a time-aware a ention model for CTR prediction. e time-aware a ention model contains absolute temporal  ... 
doi:10.1145/3357384.3357936 dblp:conf/cikm/WangZDSZHYB19 fatcat:d7rkkd2izjaizfszrxuohhulhe

Deep User Segment Interest Network Modeling for Click-through Rate Prediction of Online Advertising

Kyungwon Kim, Eun Kwon, Jaram Park
2021 IEEE Access  
INDEX TERMS Online advertising, click-through rate prediction, user interest, segment interest, gated recurrent unit, segment interest activation unit, deep neural networks. 9812 This work is licensed  ...  Moreover, predicting the click-through rate (CTR) can increase advertisement revenue and user satisfaction. However, advertising data contains many features, and the amount is growing rapidly.  ...  Therefore, to solve the time evolution problem, the authors developed a deep time-aware item evolution network (TIEN) algorithm using a time-interval attention layer. Moreover, Feng et al.  ... 
doi:10.1109/access.2021.3049827 fatcat:hywvqdbxd5fwvnkcikam6u5loa

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
to products, purchases of items, or explicit user feedback through online surveys.  ...  What type of data are available for user response prediction? How to predict user response in a reliable and/or transparent way?  ...  time on landing page for a conversion rate prediction task.  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

Value-aware Recommendation based on Reinforced Profit Maximization in E-commerce Systems [article]

Changhua Pei, Xinru Yang, Qing Cui, Xiao Lin, Fei Sun, Peng Jiang, Wenwu Ou, Yongfeng Zhang
2019 arXiv   pre-print
Specifically, we propose value-aware recommendation based on reinforcement learning, which directly optimizes the economic value of candidate items to generate the recommendation list.  ...  Traditional recommendation targets such as rating prediction and top-k recommendation are not directly related to this goal.  ...  to this goal. ey mostly focus on whether or not the algorithm can predict accurate ratings (rating prediction), or if the system can rank the clicked items correctly (top-k recommendation).  ... 
arXiv:1902.00851v1 fatcat:blxceftpsvgplje3b37llq7syu

Time-weighted Attentional Session-Aware Recommender System [article]

Mei Wang, Weizhi Li, Yan Yan
2019 arXiv   pre-print
We integrate the time changes in session RNN and add user preferences as model drifting; and (2) a novel triangle parallel attention network that enhances the original RNN model by incorporating time information  ...  Such triangle parallel network is also specially designed for realizing data argumentation in sequence-to-scalar RNN architecture, and thus it can be trained very efficiently.  ...  is the click gap time, which is also the view dwell time of an item.  ... 
arXiv:1909.05414v1 fatcat:wprgje6jsbh33a4djewf3r5qda

A Non-sequential Approach to Deep User Interest Model for CTR Prediction [article]

Keke Zhao, Xing Zhao, Qi Cao, Linjian Mo
2021 arXiv   pre-print
Click-Through Rate (CTR) prediction plays an important role in many industrial applications, and recently a lot of attention is paid to the deep interest models which use attention mechanism to capture  ...  Next, we enhance the Deep Interest Network to take such rich information into account by a novel attention network.  ...  INTRODUCTION Click-Through Rate (CTR) prediction is a core task in e-commerce such as online advertising and recommendation system, because it is directly related to revenues of the whole platform and  ... 
arXiv:2104.06312v2 fatcat:n7nkhmawjrfw3gtldsgfxiwea4

Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction [article]

Kailun Wu, Weijie Bian, Zhangming Chan, Lejian Ren, Shiming Xiang, Shuguang Han, Hongbo Deng, Bo Zheng
2021 arXiv   pre-print
Nowadays, data-driven deep neural models have already shown remarkable progress on Click-through Rate (CTR) prediction.  ...  In the context of Exploitation-and-Exploration for CTR prediction, recent studies have attempted to utilize the prediction uncertainty along with model prediction as the reward score.  ...  Deep interest evolution network for click-through rate proved Thompson sampling for logistic contextual bandits. arXiv preprint prediction.  ... 
arXiv:2112.11136v1 fatcat:uxa34sx3sba4rkicchkuzhin24

Usability and Security Testing of Online Links: A Framework for Click-Through Rate Prediction Using Deep Learning

Robertas Damaševičius, Ligita Zailskaitė-Jakštė
2022 Electronics  
Many internet applications, such as internet advertising and recommendation systems, rely on click-through rate (CTR) prediction to anticipate the possibility that a user would click on an ad or product  ...  As a case study, we analyse a CTR prediction task, using deep learning methods (factorization machines) to predict online fraud through clickbait.  ...  Therefore, the methods for predicting the behaviour of users when interacting with internet systems, expressed through a variety of quantitative metrics such as click-through rate (CTR), are relevant  ... 
doi:10.3390/electronics11030400 fatcat:nmgvjbvpnbgk5kebmvp4xubrce

MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction [article]

Wentao Ouyang, Xiuwu Zhang, Lei Zhao, Jinmei Luo, Yu Zhang, Heng Zou, Zhaojie Liu, Yanlong Du
2020 arXiv   pre-print
Click-through rate (CTR) prediction is a critical task in online advertising systems.  ...  In order to effectively leverage news data for predicting CTRs of ads, we propose the Mixed Interest Network (MiNet) which jointly models three types of user interest: 1) long-term interest across domains  ...  Deep Interest Network (DIN) [37] and Deep Interest Evolution Network (DIEN) [36] model user interest based on historical click behavior. Xiong et al. [31] and Yin et al.  ... 
arXiv:2008.02974v1 fatcat:lhxuowldd5apvhq5wlojgkfbkq

News Session-Based Recommendations using Deep Neural Networks

Gabriel de Souza Pereira Moreira, Felipe Ferreira, Adilson Marques da Cunha
2018 Proceedings of the 3rd Workshop on Deep Learning for Recommender Systems - DLRS 2018  
The recommendation task addressed in this work is next-item prediction for users sessions: "what is the next most likely article a user might read in a session?"  ...  Neural Networks.  ...  ACKNOWLEDGMENTS The authors would like to thank Globo.com for providing context on its challenges for large-scale news recommender systems and for sharing a dataset to make those experiments possible.  ... 
doi:10.1145/3270323.3270328 dblp:conf/recsys/MoreiraFC18 fatcat:rurrhe35b5dhjl7xiu2j4cdg2i

DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction [article]

Yule Wang, Qiang Luo, Yue Ding, Dong Wang, Hongbo Deng
2021 arXiv   pre-print
In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network}) to address the above two issues.  ...  To be specific, we first consider various dependency types between item nodes and perform dependency-aware heterogeneous attention for denoising and obtaining accurate sequence item representations.  ...  havior sequence, we perform multi-dependency-aware heterogeneous attention and self-supervised interest learning.  ... 
arXiv:2109.12512v1 fatcat:vznmni5xfzhsnjkfnxh5kfyhsa

A Hierarchical User Intention-Habit Extract Network for Credit Loan Overdue Risk Detection [article]

Hao Guo, Xintao Ren, Rongrong Wang, Zhun Cai, Kai Shuang, Yue Sun
2020 arXiv   pre-print
Then, we propose a hierarchical network composed of time-aware GRU and user-item-aware GRU to capture users' short-term intentions and users' long-term habits, which can be regarded as a supplement to  ...  Due to the diversity of users' behaviors, we divide behavior sequences into sessions according to the time interval, and use the field-aware method to extract the intra-field information of behaviors.  ...  We would also like to thank Lamei Zhao and Yilin Guo for the constructive suggestions and the anonymous reviewers for their insightful comments.  ... 
arXiv:2008.07796v1 fatcat:rr4ej4u2orf7lbkzxx74j5ax2u

Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation [article]

Shu Wu, Mengqi Zhang, Xin Jiang, Ke Xu, Liang Wang
2020 arXiv   pre-print
The problem of session-aware recommendation aims to predict users' next click based on their current session and historical sessions.  ...  Existing session-aware recommendation methods have defects in capturing complex item transition relationships.  ...  Generally, the users' identifications and past behaviors can be utilized for the next-click prediction, which is called session-aware recommendation.  ... 
arXiv:1910.08887v3 fatcat:jkkiqvthtbghlpaqlq7556crte

Scenario Adaptive Mixture-of-Experts for Promotion-Aware Click-Through Rate Prediction [article]

Xiaofeng Pan, Yibin Shen, Jing Zhang, Keren Yu, Hong Wen, Shui Liu, Chengjun Mao, Bo Cao
2022 arXiv   pre-print
However, Click-Through Rate (CTR) prediction methods in recommender systems are not able to handle such circumstances well since: 1) they can't generalize well to serving because the online data distribution  ...  To the best of our knowledge, this is the first study for promotion-aware CTR prediction. Experimental results on real-world datasets validate the superiority of SAME.  ...  . • TIEN [16] develops a time-interval attention layer to calculate the importance weight for each user in item behaviors and captures the popularity of the items by a time-aware evolution layer.  ... 
arXiv:2112.13747v2 fatcat:qu7qtomqfbc47j4wrwbb2d7quq
« Previous Showing results 1 — 15 out of 5,610 results