Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Gradient boosting learning for fraudulent publisher detection in online advertising

Gradient boosting learning for fraudulent publisher detection in online advertising Analysis of the publisher's behavior plays a vital role in identifying fraudulent publishers in the pay-per-click model of online advertising. However, the vast amount of raw user click data with missing values pose a challenge in analyzing the conduct of publishers. The presence of high cardinality in categorical attributes with multiple possible values has further aggrieved the issue.Design/methodology/approachIn this paper, gradient tree boosting (GTB) learning is used to address the challenges encountered in learning the publishers' behavior from raw user click data and effectively classifying fraudulent publishers.FindingsThe results demonstrate that the GTB effectively classified fraudulent publishers and exhibited significantly improved performance as compared to other learning methods in terms of average precision (60.5 %), recall (57.8 %) and f-measure (59.1%).Originality/valueThe experiments were conducted using publicly available multiclass raw user click dataset and eight other imbalanced datasets to test the GTB's generalizing behavior, while training and testing were done using 10-fold cross-validation. The performance of GTB was evaluated using average precision, recall and f-measure. The performance of GTB learning was also compared with eleven other state-of-the-art individual and ensemble classification models. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Data Technologies and Applications Emerald Publishing

Gradient boosting learning for fraudulent publisher detection in online advertising

Download PDF
17 pages

Loading next page...
 
/lp/emerald-publishing/gradient-boosting-learning-for-fraudulent-publisher-detection-in-kmL9pDP641
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
2514-9288
DOI
10.1108/dta-04-2020-0093
Publisher site
See Article on Publisher Site

Abstract

Analysis of the publisher's behavior plays a vital role in identifying fraudulent publishers in the pay-per-click model of online advertising. However, the vast amount of raw user click data with missing values pose a challenge in analyzing the conduct of publishers. The presence of high cardinality in categorical attributes with multiple possible values has further aggrieved the issue.Design/methodology/approachIn this paper, gradient tree boosting (GTB) learning is used to address the challenges encountered in learning the publishers' behavior from raw user click data and effectively classifying fraudulent publishers.FindingsThe results demonstrate that the GTB effectively classified fraudulent publishers and exhibited significantly improved performance as compared to other learning methods in terms of average precision (60.5 %), recall (57.8 %) and f-measure (59.1%).Originality/valueThe experiments were conducted using publicly available multiclass raw user click dataset and eight other imbalanced datasets to test the GTB's generalizing behavior, while training and testing were done using 10-fold cross-validation. The performance of GTB was evaluated using average precision, recall and f-measure. The performance of GTB learning was also compared with eleven other state-of-the-art individual and ensemble classification models.

Journal

Data Technologies and Applications – Emerald Publishing

Published: Apr 12, 2021

Keywords: Pay-per-click; Fraudulent publishers; Click fraud; Gradient tree boosting; Online advertising

References

  • A novel, gradient boosting framework for sentiment analysis in languages where NLP Resources are not plentiful: a case study for modern Greek †
    Athanasiou, V.; Maragoudakis, M.
  • Random forests for the detection of click fraud in online mobile advertising
    Berrar, D.
  • Learning from automatically labeled data: case study on click fraud prediction
    Berrar, D.
  • Statistical modeling: the two cultures
    Breiman, L.
  • Random forests
    Breiman, L.
  • Support-vector networks
    Cortes, C.; Vapnik, V.
  • Measuring and fingerprinting click-spam in ad networks
    Dave, V.; Guha, S.; Zhang, Y.
  • Fast gradient boosting decision trees with bit-level data structures
    Devos, L.; Meert, W.; Davis, J.
  • Genetics-Based machine learning for rule induction: taxonomy , experimental study and state of the art
    Fern, A.; Garc, S.; Bernad, E.; Herrera, F.
  • International Journal of Approximate Reasoning Hierarchical fuzzy rule based classification systems with genetic rule selection for imbalanced data-sets q
    Fernández, A.; José, M.; Herrera, F.
  • On the 2-tuples based genetic tuning performance for fuzzy rule based classification systems in imbalanced data-sets
    Fernández, A.; José, M.; Herrera, F.
  • Efficient top rank optimization with gradient boosting for supervised anomaly detection
    Frery, J.; Habrard, A.; Sebban, M.; Caelen, O.; He-guelton, L.
  • A short introduction to boosting
    Freund, Y.; Schapire, R.E.
  • Building classifiers using bayesian networks
    Friedman, N.; Goldszmidt, M.
  • Bayesian network classifiers
    Friedman, N.; Geiger, D.; Goldszmit, M.
  • Regularized discriminant analysis
    Friedman, J.H.
  • Greedy function approximation: a gradient boosting machine
    Friedman, J.H.
  • Fighting online click-fraud using bluff ads
    Haddadi, H.
  • An ensemble learning based approach for impression fraud detection in mobile advertising
    Haider, C.M.R.; Iqbal, A.; Rahman, A.H.; Rahman, M.S.
  • Decision trees as possibilistic classifiers
    Jenhani, I.; Amor, N.B.; Elouedi, Z.
  • Improving click fraud detection by real time data fusion
    Kantardzic, M.; Walgampaya, C.; Wenerstrom, B.; Lozitskiy, O.; Higgins, S.; King, D.
  • The effect of using pay per click advertisement on online advertisement effectiveness and attracting customers in E-marketing companies in Jordan
    Khraim, H.S.; Alkrableih, A.A.
  • Light GBM machine learning algorithm to online click fraud detection light GBM machine learning algorithm to online click fraud detection
    Minastireanu, E.A.; Alexandru, U.; Cuza, I.; Mesnita, G.; Alexandru, U.; Cuza, I.
  • Towards a machine learning approach for detecting click fraud in mobile advertizing
    Mouawi, R.; Awad, M.; Chehab, A.; El Hajj, I.H.; Kayssi, A.
  • Gradient boosting machines, a tutorial
    Natekin, A.; Knoll, A.
  • Detecting click fraud in online advertising: a data mining approach
    Oentaryo, R.; Lim, E.-P.; Finegold, M.; Lo, D.; Zhu, F.; Phua, C.; Cheu, E.-Y.; Yap, G.-E.; Sim, K.; Nguyen, M.N.
  • A novel ensemble learning-based approach for click fraud detection in mobile advertising
    Perera, K.S.; Neupane, B.; Faisal, M.A.; Aung, Z.; Woon, W.L.
  • A review of classification problems and algorithms
    Pérez-ortiz, M.; Jiménez-fernández, S.; Gutiérrez, P.A.
  • Induction of decision trees
    Quinlan, J.R.
  • Effectiveness analysis of machine learning classification models for predicting personalized context - aware smartphone usage
    Sarker, I.H.; Kayes, A.S.M.; Watters, P.
  • Boosting the margin: a new explanation for the effectiveness of voting methods
    Schapire, R.E.; Freund, Y.; Bartlett, P.; Lee, S.
  • Evaluation of machine learning models for employee churn prediction
    Sisodia, D.S.; Vishwakarma, S.; Pujahari, A.
  • Ensemble learning approach for clickbait detection using article headline features
    Sisodia, D.S.
  • A systematic analysis of performance measures for classification tasks
    Sokolova, M.; Lapalme, G.
  • Prediction of click frauds in mobile advertising
    Taneja, M.; Garg, K.; Purwar, A.; Sharma, S.
  • k-nearest neighbour method: the influence of data transformations and metrics
    Todeschini, R.
  • Incremental induction of decision trees
    Utgoff, P.E.
  • Data mining approach to filter click-spam in mobile ad networks
    Vasumati, D.; Vani, M.S.; Bhramaramba, R.; Babu, O.Y.
  • Click fraud detection on the advertiser side
    Xu, H.; Liu, D.; Koehl, A.; Wang, H.; Stavrou, A.
  • Detecting click fraud in pay-per-click streams of online advertising networks
    Zhang, L.; Guan, Y.
  • KNN-CF approach: incorporating certainty factor to kNN classification
    Zhang, S.