Advertisement

How Click-Fraud Shapes Traffic: A Case Study

  • Dmytro Pavlov
  • Oleg Chertov
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 836)

Abstract

This paper provides a real-life case-study of click-fraud. We aim to investigate the influence of invalid clicks on the time series of advertising parameters, such as the number of clicks and click-through-rate. Our results show that it can be challenging to visually identify click-fraud in real traffic. However, using powerful methods of signal analysis such as ‘Caterpillar’-SSA allows efficiently discovering fraudulent components. Finally, our findings confirm the hypothesis from previous works that attacks can be discovered via behavioral modeling of an attacker.

Keywords

Internet advertising Click-fraud ‘Caterpillar’-SSA 

References

  1. 1.
    Richter, F.: 25 percent of global ad spend goes to google or facebook (2017). https://www.statista.com/chart/12179/google-and-facebook-share-of-ad-revenue/. Accessed 10 Mar 2018
  2. 2.
    Fain, D.C., Pedersen, J.O.: Sponsored search: a brief history. Bull. Assoc. Inf. Sci. Technol. 32(2), 12–13 (2006)CrossRefGoogle Scholar
  3. 3.
    Jansen, B.J., Mullen, T.: Sponsored search: an overview of the concept, history, and technology. Int. J. Electron. Bus. 6(2), 114–131 (2008)CrossRefGoogle Scholar
  4. 4.
    Chertov, O., Malchykov, V., Pavlov, D.: Non-dyadic wavelets for detection of some click-fraud attacks. In: 2010 International Conference on Signals and Electronic Systems (ICSES), pp. 401–404. IEEE (2010)Google Scholar
  5. 5.
    Gerbing, D.: Time series components. Portland State University, p. 9 (2016)Google Scholar
  6. 6.
    Hamilton, J.D.: Time Series Analysis, vol. 2. Princeton University Press, Princeton (1994)MATHGoogle Scholar
  7. 7.
    Gorshkov, V., Miller, N., Persiyaninova, N., Prudnikova, E.: Principal component analysis for geodinamical time series. Commun. Russ. Acad. Sci. 214, 173–180 (2000). (in Russian)Google Scholar
  8. 8.
    Ghil, M., Allen, M., Dettinger, M., Ide, K., Kondrashov, D., Mann, M., Robertson, A.W., Saunders, A., Tian, Y., Varadi, F., et al.: Advanced spectral methods for climatic time series. Rev. Geophys. 40(1) (2002)Google Scholar
  9. 9.
    Antoniou, I., Ivanov, V., Ivanov, V.V., Zrelov, P.: Principal component analysis of network traffic measurements: the Caterpillar-SSA approach. In: VIII International Workshop on Advanced Computing and Analysis Techniques in Physics Research, ACAT, pp. 24–28 (2002)Google Scholar
  10. 10.
    Golyandina, N., Osipov, E.: ‘Caterpillar’-SSA for analysis of time series with missing values. Math. Model. Theor. Appl. 6, 50–61 (2005). (in Russian)MATHGoogle Scholar
  11. 11.
    Golandian, N., Nekrutkin, V., Stepanov, D.: Variants of ‘Caterpillar’-SSA method for multidimensional time series analysis. In: II International Conference on Systems Identification and Control Processes, SICPRO , vol. 3, pp. 2139–2168 (2003). (in Russian)Google Scholar
  12. 12.
    Hassani, H.: Singular spectrum analysis: methodology and comparison. J. Data Sci. 5, 239–257 (2007)Google Scholar
  13. 13.
    Aleksandrov, F.: Development of a software complex for automatic identification and forecasting of additive components of time series within the framework of the approach ‘Caterpillar’-SSA. Ph.D. thesis (2006). (in Russian)Google Scholar
  14. 14.
    Furashev, V., Lande, D.: Practical basics of possible thread prediction via analysing interconnections of events and information space. Open information and computer integrated technologies, 42, 194–203 (2009). (in Ukrainian)Google Scholar
  15. 15.
    Chertov, O., Tavrov, D., Pavlov, D., Alexandrova, M., Malchikov, V.: Group Methods of Data Processing. LuLu.com, Raleigh (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Igor Sikorsky Kyiv Polytechnic InstituteKyivUkraine

Personalised recommendations