16,664 Hits in 5.9 sec

User Behavior Retrieval for Click-Through Rate Prediction [article]

Jiarui Qin, Weinan Zhang, Xin Wu, Jiarui Jin, Yuchen Fang, Yong Yu
2020 pre-print
Click-through rate (CTR) prediction plays a key role in modern online personalization services.  ...  To tackle these issues, in this paper we consider it from the data perspective instead of just designing more sophisticated yet complicated models and propose User Behavior Retrieval for CTR prediction  ...  As shown in Figure 2 , when we need to predict the click-through rate between the target user and target item in a certain context, all of the three parts of information are combined to form a prediction  ... 
doi:10.1145/3397271.3401440 arXiv:2005.14171v1 fatcat:26d3u6xhrjf7lgfcp5i2mnxdki

Improving Relevance of Information Retrieval Systems and User's Preferred Search Language

Ghada Refaat El Said
2017 Information Technology Journal  
Conclusion: The current study provides a cost-effective method for understanding user behavior in the context of different languages through the use of implicit feedback.  ...  Results: Results suggested that the prediction level of implicit feedback for result relevance is enhanced when users are given the option to select a preferred language.  ...  The current study investigates post-click user search behaviors (dwell time, amount of clicks and amount of scrolling) and relates them with explicit relevance rating, while looking at the effect of userʼs  ... 
doi:10.3923/itj.2017.71.78 fatcat:vxnykc7r7fbx5jliwc5qjx7yom

EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search [article]

Wenjin Wu, Guojun Liu, Hui Ye, Chenshuang Zhang, Tianshu Wu, Daorui Xiao, Wei Lin, Xiaoyu Zhu
2018 arXiv   pre-print
Under the deep matching framework, vector-based ad retrieval harnesses user recent behavior sequence to retrieve relevant ad candidates without the constraint of keyword bidding.  ...  E-commerce sponsored search contributes an important part of revenue for the e-commerce company.  ...  ACKNOWLEDGMENT e authors would like to thank the colleagues for their valuable supports, such as Yan Zhang, Genbao Chen, Yuping Jiang, Hao Wan, Sheng Xu, Zhenkui Huang, Qing Ye, Tao Ma, Hang Xiang, Di  ... 
arXiv:1812.01190v4 fatcat:qlg2miqiofc4nncucgulrknuj4

How does clickthrough data reflect retrieval quality?

Filip Radlinski, Madhu Kurup, Thorsten Joachims
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
Automatically judging the quality of retrieval functions based on observable user behavior holds promise for making retrieval evaluation faster, cheaper, and more user centered.  ...  However, the relationship between observable user behavior and retrieval quality is not yet fully understood.  ...  Using absolute metrics for evaluation follows the hypothesis that retrieval quality impacts observable user behavior in an absolute sense (e.g. better retrieval leads to higher-ranked clicks, better retrieval  ... 
doi:10.1145/1458082.1458092 dblp:conf/cikm/RadlinskiKJ08 fatcat:kfdvw7cbjjaw7gwmclem3v4x7u

Predicting implicit search behaviors usinglog analysis

L LeemaPriyadharshini, S Florence, K Prema, C Shyamala Kumari
2018 International Journal of Engineering & Technology  
For increasing the web page utility and ranking the URLs predicting implicit user behavior is a needed task.  ...  Search engines provide ranked information based on the query given by the user. Understanding user search behavior is an important task for satisfaction of the users with the needed information.  ...  This paper proposed the concept of increasing the web page visibility to the user using some optimization technique. They have proposed the click through rate and the bouncing rate.  ... 
doi:10.14419/ijet.v7i1.7.9582 fatcat:x5bzqwhu4vdi7osarrvid3bisy

A Survey: Searching Techniques

Miss Mangala S. Teli, Asst. Prof. Priti S. Subramanium
2017 IOSR Journal of Computer Engineering  
In day to day life as we are using internet mostly for to search every one want answer within short time.  ...  Any user who doesn't know how to search can get result by simply typing related words in search engine.  ...  This query log is analyzed by calculating success rate by absence of click-through data and user behaviors.  ... 
doi:10.9790/0661-1903064748 fatcat:dki5qs5n6fa4jee6edkgoivkvy

Did We Get It Right? Predicting Query Performance in E-commerce Search [article]

Rohan Kumar, Mohit Kumar, Neil Shah, Christos Faloutsos
2018 arXiv   pre-print
While this question is traditionally answered using simple metrics like query click-through rate (CTR), we observe that in e-commerce search, such metrics can be misleading.  ...  We study large-scale user interaction logs from Flipkart's search engine, analyze behavioral patterns and build models to classify queries based on user behavior signals.  ...  Subhadeep Maji for their helpful comments.  ... 
arXiv:1808.00239v1 fatcat:5k5ap2ztfzdqhbimfzw5by5fo4

Advertisement Mining using Hidden Markov Model
IJARCCE - Computer and Communication Engineering

K. Sathiyamurthy, P. Dhivya, DJ. Panimalar
2015 IJARCCE  
Initially we need to collect a log of datasets with user behavior attributes. Hidden Markov Model is used to derive a pattern for predicting the behavior of the users on the web.  ...  Predicting the individual's web-browsing behavior on the internet is more important for advertisement mining.  ...  From the experiment results over a period of seven days, they have drawn three important conclusions: (1) Users who clicked the same ad will truly have similar behaviors on the Web; (2) Click-Through Rate  ... 
doi:10.17148/ijarcce.2015.4353 fatcat:gccyux52tbbjhnne3g4m2cl754

The sum of its parts: reducing sparsity in click estimation with query segments

Dustin Hillard, Eren Manavoglu, Hema Raghavan, Chris Leggetter, Erick Cantú-Paz, Rukmini Iyer
2011 Information retrieval (Boston)  
We then propose methods to improve click and relevance models for sponsored search by mining click behavior for partial user queries.  ...  The critical task of predicting clicks on search advertisements is typically addressed by learning from historical click data.  ...  ads for the query, and (3) click through rate prediction: estimating click through rate for the retrieved ads and ranking ads on the search page.  ... 
doi:10.1007/s10791-010-9152-6 fatcat:pmf4elunh5hdhpiudnf6oay53i

Implementation of Short Video Click-Through Rate Estimation Model Based on Cross-Media Collaborative Filtering Neural Network

Ying Feng, Guisheng Zhao, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
In this paper, we analyze the construction of cross-media collaborative filtering neural network model to design an in-depth model for fast video click-through rate projection based on cross-media collaborative  ...  behaviors of users on current behaviors using the attention mechanism.  ...  Click-through rate prediction is an integral part of this task, and how to improve the accuracy of click-through rate prediction for short videos has attracted extensive attention from academia and the  ... 
doi:10.1155/2022/4951912 pmid:35685157 pmcid:PMC9173947 fatcat:tq3tdoj5qzha3ltxvpaz7thge4

Personalization of search results using interaction behaviors in search sessions

Chang Liu, Nicholas J. Belkin, Michael J. Cole
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
In this paper, we propose methods for analyzing and modeling user search behavior in search sessions to predict document usefulness and then using information to personalize search results.  ...  Personalization of search results offers the potential for significant improvement in information retrieval performance.  ...  Thanks to Si Sun for assistance in TREC 2011 Session Track. Thanks to Jingjing Liu for validating task classification as the third coder.  ... 
doi:10.1145/2348283.2348314 dblp:conf/sigir/LiuBC12 fatcat:jfo7wtrg5vg3lp7iv5exee67je

Identifying machine learning techniques for classification of target advertising

Jin-A Choi, Kiho Lim
2020 ICT Express  
Twenty-three machine learning-based online targeted advertising strategies are identified and classified largely into two categories, user-centric and content-centric approaches.  ...  The paper also identifies an underexamined area, algorithm-based detection of click frauds, to illustrate how machine learning approaches can be integrated to preserve the viability of online advertising  ...  Therefore, predicting the probability that a user will click on an advertisement, click-through rate (CTR), is unmistakably important [7] .  ... 
doi:10.1016/j.icte.2020.04.012 fatcat:5qnbssw625chhfeeqkwzkgcjxm

Talking the talk vs. walking the walk

Mikhail Bilenko, Ryen W. White, Matthew Richardson, G. Craig Murray
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
source of information for user modeling and personalization.  ...  In this poster, we consider Web browsing behavior outside of interactions with retrieval systems (i.e., users' "walk") as an alternative source of signal describing users' information needs, and compare  ...  Relevance feedback (RF) [4] has been proposed as a methodology for improving retrieval performance by capturing users' implicit or explicit relevance judgments through interactions that follow a query  ... 
doi:10.1145/1390334.1390461 dblp:conf/sigir/BilenkoWRM08 fatcat:xrupwc3ilvhk3frtoye55x43n4

End-to-End User Behavior Retrieval in Click-Through RatePrediction Model [article]

Qiwei Chen, Changhua Pei, Shanshan Lv, Chao Li, Junfeng Ge, Wenwu Ou
2021 arXiv   pre-print
Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair.  ...  Two-stage methods are proposed to push the limit for better performance. At the first stage, an auxiliary task is designed to retrieve the top-k similar items from long-term user behavior sequence.  ...  Among all those deep learning models used in RS, Click-Through Rate (CTR) prediction model is one of the most important one.  ... 
arXiv:2108.04468v1 fatcat:sustjgfzvnbspib65fa2t2finy

Users' behavioral prediction for phishing detection

Lung-Hao Lee, Kuei-Ching Lee, Yen-Cheng Juan, Hsin-Hsi Chen, Yuen-Hsien Tseng
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
We extract discriminative features of each clicked URL, i.e., domain name, bag-of-words, generic Top-Level Domains, IP address, and port number, to develop a linear chain CRF model for users' behavioral  ...  This study explores the users' web browsing behaviors that confront phishing situations for context-aware phishing detection.  ...  We are also grateful to Trend Micro research laboratory for the support of click-through data.  ... 
doi:10.1145/2567948.2577320 dblp:conf/www/LeeLJCT14 fatcat:hnivqhmw3zcpxjjo5egyoif3t4
« Previous Showing results 1 — 15 out of 16,664 results