Towards a Machine Learning Approach for Detecting Click Fraud in Mobile Advertizing

Mouawi, Riwa; Awad, Mariette; Chehab, Ali; Hajj, Imad H. El; Kayssi, Ayman

doi:10.1109/innovations.2018.8605973

Cited by 27 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forest algorithm based novel mobile money transaction fraud detection have better accuracy compared to logistic regression algorithm based mobile money transactions fraud detection (Sadineni 2020) et al have implemented random forest and logistic regression algorithms to detect the frauds in credit card systems and obtained accuracy 98% (Sadineni 2020). (Mouawi et al 2018) introduced a new framework to implement logistic regression and random forest algorithms to find the types of frauds, they used the transaction history as an ensemble classifier to detect the frauds and obtained accuracy 93% (Mouawi et al 2018).…”

Section: Discussionmentioning

confidence: 99%

“…The identification ability of the model is completely dependent on the data and its attributes; a small size of the datasets with less null values and outliers performs better convergence. Aim of this research is to develop the simple networks to reduce the computational cost (Mouawi et al 2018;G.s. et al 2021), these networks produce good results against large datasets.…”

Section: Discussionmentioning

confidence: 99%

“…high accuracy ((Saha, Sadi, and Islam 2021;Apostolopoulos and Mpesiana 2020) (Mouawi et al 2018;. G.s.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Accuracy Analysis for Logistic Regression Algorithm and Random Forest Algorithm to Detect Frauds in Mobile Money Transaction

Kumar¹,

Nalini²

2021

revistageintec

View full text Add to dashboard Cite

Aim:The main motto of the study is to detect the frauds in mobile money transactions using logistic regression and random forest algorithms and comparing their accuracy. Materials and Methods: Logistic regression (N=10) and random forest algorithm(N=10) was iterated 20 times and detected the frauds. Results and Discussion: Random forest has significantly better accuracy (99.6%) compared to logistic regression (92.6%). The statistical significance of random forest algorithm (p<0.018 Independent sample T-test) is high. Conclusion: Within the limits of this study, random forest algorithm offers better accuracy to detect frauds in mobile money transactions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy Analysis for Logistic Regression Algorithm and Random Forest Algorithm to Detect Frauds in Mobile Money Transaction

Kumar¹,

Nalini²

2021

revistageintec

View full text Add to dashboard Cite

show abstract

“…In the second part of the paper, we propose a new mobile ad charging model that benefits from our CFC system to charge advertisers based on the duration spent in the advertiser's website. Our proposed model in this paper is an enhancement of our previous work [48] where we briefly introduced our model and compared multiple classification methods; our model since then has matured and is following a different click fraud detection analysis method.…”

Section: Mobile Ad Click Fraud Detectionmentioning

confidence: 99%

Crowdsourcing for click fraud detection

Mouawi

Elhajj

Chehab

et al. 2019

EURASIP J. on Info. Security

Self Cite

View full text Add to dashboard Cite

Mobile ads are plagued with fraudulent clicks which is a major challenge for the advertising community. Although popular ad networks use many techniques to detect click fraud, they do not protect the client from possible collusion between publishers and ad networks. In addition, ad networks are not able to monitor the user's activity for click fraud detection once they are redirected to the advertising site after clicking the ad. We propose a new crowdsource-based system called Click Fraud Crowdsourcing (CFC) that collaborates with both advertisers and ad networks in order to protect both parties from any possible click fraudulent acts. The system benefits from both a global view, where it gathers multiple ad requests corresponding to different ad network-publisher-advertiser combinations, and a local view, where it is able to track the users' engagement in each advertising website. The results demonstrated that our approach offers a lower false positive rate (0.1) when detecting click fraud as opposed to proposed solutions in the literature, while maintaining a high true positive rate (0.9). Furthermore, we propose a new mobile ad charging model that benefits from our system to charge advertisers based on the duration spent in the advertiser's website.

show abstract

“…Not only non-stationary traffic, but also stealth occurrences of malicious behaviors both introduce issues to analyse anomalous network traffic [22]. Machine learning frameworks have been used to help analyse network behaviour, identify click fraud and adapt to changes in traffic [22,36]. However, most of of this research is done on botnet-induced click traffic, and does not identify the effectiveness of these methods on other forms of fraudulent clicks.…”

Section: Related Workmentioning

confidence: 99%

Clicktok

Nagaraja

Shah

2019

Proceedings of the 12th Conference on Security and Privacy in Wireless and Mobile Networks

View full text Add to dashboard Cite

Advertising is a primary means for revenue generation for millions of websites and smartphone apps. Naturally, a fraction abuse ad networks to systematically defraud advertisers of their money. Modern defences have matured to overcome some forms of click fraud but measurement studies have reported that a third of clicks supplied by ad networks could be clickspam. Our work develops novel inference techniques which can isolate click fraud attacks using their fundamental properties. We propose two defences, mimicry and bait-click, which provide clickspam detection with substantially improved results over current approaches. Mimicry leverages the observation that organic clickfraud involves the reuse of legitimate click traffic, and thus isolates clickspam by detecting patterns of click reuse within ad network clickstreams. The bait-click defence leverages the vantage point of an ad network to inject a pattern of bait clicks into a user's device. Any organic clickspam generated involving the bait clicks will be subsequently recognisable by the ad network. Our experiments show that the mimicry defence detects around 81% of fake clicks in stealthy (low rate) attacks, with a false-positive rate of 110 per hundred thousand clicks. Similarly, the bait-click defence enables further improvements in detection, with rates of 95% and a reduction in false-positive rates of between 0 and 30 clicks per million-a substantial improvement over current approaches.

show abstract

Towards a Machine Learning Approach for Detecting Click Fraud in Mobile Advertizing

Cited by 27 publications

References 11 publications

Accuracy Analysis for Logistic Regression Algorithm and Random Forest Algorithm to Detect Frauds in Mobile Money Transaction

Accuracy Analysis for Logistic Regression Algorithm and Random Forest Algorithm to Detect Frauds in Mobile Money Transaction

Crowdsourcing for click fraud detection

Clicktok

Contact Info

Product

Resources

About