CAT-RFE: ensemble detection framework for click fraud

Yixiang LU; Guanggang GENG; Zhiwei YAN; Xiaomin ZHU; Xinchang ZHANG

doi:10.11959/j.issn.2096-109x.2022065

您当前的位置：

首页 >

文章列表页 >

CAT-RFE: ensemble detection framework for click fraud

Papers | 更新时间：2024-06-03

- CAT-RFE: ensemble detection framework for click fraud
- Chinese Journal of Network and Information Security Vol. 8, Issue 5, Pages: 158-166(2022)
- 作者机构：
  
  1. 暨南大学网络空间安全学院，广东广州510632
  2. 中国互联网络信息中心，北京 100190
  3. 山东齐鲁大数据研究院，山东济南 250001
  4. 山东省科学院，山东济南 250001
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2022065
  CLC： TP393
- Online First：2022-10，
  
  Published：15 October 2022
- 稿件说明：
移动端阅览
Yixiang LU, Guanggang GENG, Zhiwei YAN, et al. CAT-RFE: ensemble detection framework for click fraud[J]. Chinese Journal of Network and Information Security, 2022, 8(5): 158-166.
DOI：

Yixiang LU, Guanggang GENG, Zhiwei YAN, et al. CAT-RFE: ensemble detection framework for click fraud[J]. Chinese Journal of Network and Information Security, 2022, 8(5): 158-166. DOI： 10.11959/j.issn.2096-109x.2022065.

摘要

点击欺诈是近年来最常见的网络犯罪手段之一，互联网广告行业每年都会因点击欺诈而遭受巨大损失。为了能够在海量点击中有效地检测欺诈点击，构建了多种充分结合广告点击与时间属性关系的特征，并提出了一种点击欺诈检测的集成学习框架——CAT-RFE集成学习框架。CAT-RFE集成学习框架包含3个部分：基分类器、递归特征消除（RFE，recursive feature elimination）和voting集成学习。其中，将适用于类别特征的梯度提升模型——CatBoost（categorical boosting）作为基分类器；RFE是基于贪心策略的特征选择方法，可在多组特征中选出较好的特征组合；Voting集成学习是采用投票的方式将多个基分类器的结果进行组合的学习方法。该框架通过CatBoost和RFE在特征空间中获取多组较优的特征组合，再在这些特征组合下的训练结果通过voting进行集成，获得集成的点击欺诈检测结果。该框架采用了相同的基分类器和集成学习方法，不仅克服了差异较大的分类器相互制约而导致集成结果不理想的问题，也克服了 RFE 在选择特征时容易陷入局部最优解的问题，具备更好的检测能力。在实际互联网点击欺诈数据集上的性能评估和对比实验结果显示，CAT-RFE集成学习框架的点击欺诈检测能力超过了CatBoost模型、CatBoost和RFE组合的模型以及其他机器学习模型，证明该框架具备良好的竞争力。该框架为互联网广告点击欺诈检测提供一种可行的解决方案。

Abstract

Click fraud is one of the most common methods of cybercrime in recent years

and the Internet advertising industry suffers huge losses every year because of click fraud.In order to effectively detect fraudulent clicks within massive clicks

a variety of features that fully combine the relationship between advertising clicks and time attributes were constructed.Besides

an ensemble learning framework for click fraud detection was proposed

namely CAT-RFE ensemble learning framework.The CAT-RFE ensemble learning framework consisted of three parts: base classifier

recursive feature elimination (RFE) and voting ensemble learning.Among them

the gradient boosting model suitable for category features-CatBoost was used as the base classifier.RFE was a feature selection method based on greedy strategy

which can select a better feature combination from multiple sets of features.Voting ensemble learning was a learning method that combined the results of multiple base classifiers by voting.The framework obtained multiple sets of optimal feature combinations in the feature space through CatBoost and RFE

and then integrated the training results under these feature combinations through voting to obtain integrated click fraud detection results.The framework adopted the same base classifier and ensemble learning method

which not only overcame the problem of unsatisfactory integrated results due to the mutual constraints of different classifiers

but also overcame the tendency of RFE to fall into a local optimal solution when selecting features

so that it had better detection ability.The performance evaluation and comparative experimental results on the actual Internet click fraud dataset show that the click fraud detection ability of the CAT-RFE ensemble learning framework exceeds that of the CatBoost method

the combined method of CatBoost and RFE

and other machine learning methods

proving that the framework has good competitiveness.The proposed framework provides a feasible solution for Internet advertising click fraud detection.

关键词

Keywords

references

BORGI M , DESSAI P , MALIK V , et al . Advertisement click fraud detection system:a survey [J ] . International Journal of Engineering Research ＆ Technology (IJERT) , 2021 , 10 ( 5 ): 553 - 560 .

GOHIL N , MENIYA A D . A survey on online advertising and click fraud detection [J ] . Nayanaba Gohil Department of Information Technology Shantilal Shah Engineering , 2020 .

DOROGUSH A V , ERSHOV V , GULIN A . CatBoost:gradient boosting with categorical features support [J ] . arXiv preprint arXiv:1810.11363 , 2018 .

NAGARAJA S , SHAH R . Clicktok:click fraud detection using traffic analysis [C ] // Proceedings of the 12th Conference on Security and Privacy in Wireless and Mobile Networks . 2019 : 105 - 116 .

GABRYEL M , . Data analysis algorithm for click fraud recognition [C ] // International Conference on Information and Software Technologies . 2018 : 437 - 446 .

MOUAWI R , AWAD M , CHEHAB A , et al . Towards a machine learning approach for detecting click fraud in mobile advertizing [C ] // 2018 International Conference on Innovations in Information Technology (IIT) . 2018 : 88 - 92 .

董亚楠 , 刘学军 , 李斌 . 一种基于用户行为特征选择的点击欺诈检测方法 [J ] . 计算机科学 , 2016 , 43 ( 10 ): 145 - 149 .

DONG Y , LIU X , LI B . Click fraud detection method based on user behavior feature selection [J ] . Computer Science , 2016 , 43 ( 10 ): 145 - 149 .

TANEJA M , GARG K , PURWAR A , et al . Prediction of click frauds in mobile advertising [C ] // 2015 Eighth International Conference on Contemporary Computing (IC3) . 2015 : 162 - 166 .

张欣 , 刘学军 , 李斌 , 等 . 一种网络广告点击欺诈检测的 SVM集成方法 [J ] . 小型微型计算机系统 , 2018 , 39 ( 5 ): 951 - 956 .

ZHANG X , LIU X J , LI B , et al . Application of SVM ensemble method to click fraud detection [J ] . Journal of Chinese Computer Systems , 2018 , 39 ( 5 ): 951 - 956 .

BERRAR D , . Random forests for the detection of click fraud in online mobile advertising [C ] // Proceedings of the 1st International Workshop on Fraud Detection in Mobile Advertising . 2012 : 1 - 10 .

SHAOHUI D , QIU G W , MAI H , et al . Customer transaction fraud detection using random forest [C ] // 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) . 2021 : 144 - 147 .

PERERA K S , NEUPANE B , FAISAL M A , et al . A novel ensemble learning-based approach for click fraud detection in mobile advertising [M ] // Mining Intelligence and Knowledge Exploration , 2013 : 370 - 382 .

GOHIL N P , MENIYA A D . Click Ad fraud detection using xgboost gradient boosting algorithm [C ] // International Conference on Computing Science,Communication and Security . 2021 : 67 - 81 .

VIRUTHIKA B , DAS S S , KUMAR E M , et al . Detection of advertisement click fraud using machine learning [J ] . International Journal of Advanced Science and Technology , 2020 , 29 ( 5 ): 3238 - 3245 .

MINASTIREANU E A , MESNITA G . Light GBM machine learning algorithm to online click fraud detection [J ] . J Inform Assur Cybersecur , 2019 ,( 2019 ): 263928 .

ZHANG Y , TONG J , WANG Z , et al . Customer transaction fraud detection using Xgboost model [C ] // 2020 International Conference on Computer Engineering and Application (ICCEA) . 2020 : 554 - 558 .

THEJAS G S , DHEESHJITH S , IYENGAR S S , et al . A hybrid and effective learning approach for Click Fraud detection [J ] . Machine Learning with Applications , 2021 ,3:100016.

HADDADI H . Fighting online click-fraud using bluff ads [J ] . ACM SIGCOMM Computer Communication Review , 2010 , 40 ( 2 ): 21 - 25 .

KE G , MENG Q , FINLEY T , et al . Lightgbm:a highly efficient gradient boosting decision tree [J ] . Advances in neural information processing systems , 2017 , 30 : 3146 - 3154 .

CHEN T , HE T , BENESTY M , et al . Xgboost:extreme gradient boosting [J ] . R Package Version 0.4-2 , 2015 , 1 ( 4 ): 1 - 4 .

Views

487

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Webshell malicious traffic detection method based on multi-feature fusion

Related Author

Yuan LI

Yunpeng WANG

Tao LI

Baoqiang MA

Related Institution

No data

⁰