A Multi-time-scale Time Series Analysis for Click Fraud Forecasting using Binary Labeled Imbalanced Dataset

Thejas, G. S.; Soni, Jayesh; Boroojeni, Kianoosh G.; Iyengar, S. Sitharama; Srivastava, Kanishk; Badrinath, Prajwal; Sunitha, N. R.; Prabakar, Nagarajan; Upadhyay, Himanshu

doi:10.1109/csitss47250.2019.9031036

Cited by 10 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To automatically detect mobile advertising fraud behaviors, machine learning methods have been successfully applied to find fraud patterns in data, distinguishing suspicious advertising fraud operation from normal one [10][11][12][13][14]. As for learning model with attribute features, researchers usually use several attributes from each sample to train a learning model to identify the fraud behaviors.…”

Section: Introductionmentioning

confidence: 99%

GFD: A Weighted Heterogeneous Graph Embedding Based Approach for Fraud Detection in Mobile Advertising

Zhuang

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

Online mobile advertising plays a vital role in the mobile app ecosystem. The mobile advertising frauds caused by fraudulent clicks or other actions on advertisements are considered one of the most critical issues in mobile advertising systems. To combat the evolving mobile advertising frauds, machine learning methods have been successfully applied to identify advertising frauds in tabular data, distinguishing suspicious advertising fraud operation from normal one. However, such approaches may suffer from labor-intensive feature engineering and robustness of the detection algorithms, since the online advertising big data and complex fraudulent advertising actions generated by malicious codes, botnets, and click-firms are constantly changing. In this paper, we propose a novel weighted heterogeneous graph embedding and deep learning-based fraud detection approach, namely, GFD, to identify fraudulent apps for mobile advertising. In the proposed GFD approach, (i) we construct a weighted heterogeneous graph to represent behavior patterns between users, mobile apps, and mobile ads and design a weighted metapath to vector algorithm to learn node representations (graph-based features) from the graph; (ii) we use a time window based statistical analysis method to extract intrinsic features (attribute-based features) from the tabular sample data; (iii) we propose a hybrid neural network to fuse graph-based features and attribute-based features for classifying the fraudulent apps from normal apps. The GFD approach was applied on a large real-world mobile advertising dataset, and experiment results demonstrate that the approach significantly outperforms well-known learning methods.

show abstract

Section: Introductionmentioning

confidence: 99%

GFD: A Weighted Heterogeneous Graph Embedding Based Approach for Fraud Detection in Mobile Advertising

Zhuang

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…The study shows the best model for forecasting fraudulent and non-fraudulent click behaviour was the Probability-based model approach compared with the Learning-based probabilistic estimator model. [91] Impression Fraud Ensemble Learning, Decision Tree classifier and Support Vector Machine…”

mentioning

confidence: 99%

Ads and Fraud: A Comprehensive Survey of Fraud in Online Advertising

Sadeghpour

Vlajic

2021

JCP

View full text Add to dashboard Cite

Over the last two decades, we have witnessed a fundamental transformation of the advertising industry, which has been steadily moving away from the traditional advertising mediums, such as television or direct marketing, towards digital-centric and internet-based platforms. Unfortunately, due to its large-scale adoption and significant revenue potential, digital advertising has become a very attractive and frequent target for numerous cybercriminal groups. The goal of this study is to provide a consolidated view of different categories of threats in the online advertising ecosystems. We begin by introducing the main elements of an online ad platform and its different architecture and revenue models. We then review different categories of ad fraud and present a taxonomy of known attacks on an online advertising system. Finally, we provide a comprehensive overview of methods and techniques for the detection and prevention of fraudulent practices within those system—both from the scientific as well as the industry perspective. The main novelty of our work lies in the development of an innovative taxonomy of different types of digital advertising fraud based on their actual executors and victims. We have placed different advertising fraud scenarios into real-world context and provided illustrative examples thereby offering an important practical perspective that is very much missing in the current literature.

show abstract

Forecasting Click Fraud via Machine Learning Algorithms

Sahllal

Souidi

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Multi-time-scale Time Series Analysis for Click Fraud Forecasting using Binary Labeled Imbalanced Dataset

Cited by 10 publications

References 29 publications

GFD: A Weighted Heterogeneous Graph Embedding Based Approach for Fraud Detection in Mobile Advertising

GFD: A Weighted Heterogeneous Graph Embedding Based Approach for Fraud Detection in Mobile Advertising

Ads and Fraud: A Comprehensive Survey of Fraud in Online Advertising

Forecasting Click Fraud via Machine Learning Algorithms

Contact Info

Product

Resources

About