Logistic Regression with Stochastic Gradient Ascent to Estimate Click Through Rate

Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 9)

Abstract

Majority of Web users utilize search engines to locate Web site links. Based upon the search queries provided by the users, search engines display sponsored advertisements together with actual Web site link results to procreate monetary benefits. However, users may click the concerned sponsored advertisements that generate revenue for the search engines based upon a predefined pricing model. Furthermore, by analyzing previous information of users, advertisements, and queries; search engines estimate click-through rate (CTR) for predicting users’ clicks. CTR is a ratio of clicks to number of impressions associated with a particular advertisement. In this paper, we propose a model, based on CTR, to estimate probabilities of clicks using logistic regression that determines parameters using stochastic gradient ascent method (SGA). Moreover, this paper also summarizes the comparative analysis of SGA and batch gradient ascent (BGA) methods, in terms of accuracy and learning time.

Keywords

CTR Internet advertising Logistic regression Stochastic gradient ascent Batch gradient ascent 

References

  1. 1.
    Kumar R, Naik SM, Naik VD, Shirall S, Sunil VG, Husain M (2015) Predicting clicks: CTR estimation of advertisements using logistic regression classifier. In: IEEE International Advance Computing Conference. IEEE, pp 1134–1138Google Scholar
  2. 2.
    IAB (2014) Interactive Advertising Bureau (IAB): internet advertising revenue report 2014 full year. Survey reportGoogle Scholar
  3. 3.
    Langheinrich M, Nakamura A, Abe N, Kamba T, Koseki Y (1999) Unintrusive customization techniques for web advertising. Comput Netw 31:1259–1272CrossRefGoogle Scholar
  4. 4.
    Shatnawi M, Mohamed N (2012) Statistical techniques for online personalized advertising. In: 27th annual ACM symposium on applied computing. ACM, New York, pp 680–687Google Scholar
  5. 5.
    Chowdhury NM (2007) A survey of search advertising. Project report, Information retrieval at University of WaterlooGoogle Scholar
  6. 6.
    Dave V, Guha S, Zhang Y (2012) Measuring and fingerprinting click-spam in ad networks. In: ACM SIGCOMM computer communication review. ACM, New York, pp 175–186Google Scholar
  7. 7.
    Pearce P, Dave V, Grier C, Levchenko K, Guha S, McCoy D, Voelker GM (2014) Characterizing large-scale click fraud in zeroaccess. In: ACM SIGSAC conference on computer and communications security. ACM, New York, pp 141–152Google Scholar
  8. 8.
    Broder A, Fontoura M, Josifovski V, Riedel L (2007) A semantic approach to contextual advertising. In: 30th annual international ACM SIGIR conference on research and development in information retrieval. ACM, New York, pp 559–566Google Scholar
  9. 9.
    Media net digital advertising. http://www.media.net/
  10. 10.
    Moon Y, Kwon C (2011) Online advertisement service pricing and an option contract. Electron Commer Res Appl 10:38–48CrossRefGoogle Scholar
  11. 11.
    Trofimov I, Kornetova A, Topinskiy V (2012) Using boosted trees for click-through rate prediction for sponsored search. In: 6th international workshop on data mining for online advertising and internet economy. ACM, New YorkGoogle Scholar
  12. 12.
    Wang F, Suphamitmongkol W, Wang B (2013) Advertisement click-through rate prediction using multiple criteria linear programming regression model. Procedia Comput. Sci. 17:803–811CrossRefGoogle Scholar
  13. 13.
    Fan T, Chang C (2011) Blogger-centric contextual advertising. Expert Syst Appl 38:1777–1788CrossRefGoogle Scholar
  14. 14.
    Chen Y, Chen Z, Chiu Y, Chang C (2015) An annotation approach to contextual advertising for online ads. J Electron Commerce Res 16:123–137Google Scholar
  15. 15.
    Liu P, Zhang R (2014) Automatic keywords generation for contextual advertising. In: 23rd International conference on world wide web companion. ACM, New York, pp 345–346Google Scholar
  16. 16.
    Jaworska J, Sydow M (2008) Behavioural targeting in on-line advertising: an empirical study. In: Bailey J, Maier D, Schewe KD, Thalheim B, Wang XS (eds) Web information systems engineering—WISE 2008, vol 5175., LNCS Springer, Berlin Heidelberg, pp 62–76CrossRefGoogle Scholar
  17. 17.
    Chen Y, Pavlov D, Canny JF, Ave H (2009) Large-scale behavioral targeting categories and subject descriptors. In: 15th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, New York, pp 209–218Google Scholar
  18. 18.
    Fain DC, Pedersen JO (2006) Sponsored Search: A Brief History. Bulletin of the American Society for Information Science and Technology 32:12–13CrossRefGoogle Scholar
  19. 19.
    Schroedl S, Kesari A, Neumeyer L (2010) Personalized ad placement in web search. In: 4th annual international workshop on data mining and audience intelligence for online advertising. ACM, New YorkGoogle Scholar
  20. 20.
    Gupta R, Khirbat G, Singh S (2014) A novel method to calculate click through rate for sponsored search. Comput Res ReposGoogle Scholar
  21. 21.
    Graepel T, Candela JQ, Borchert T, Herbrich R (2010) Web-scale bayesian click-through rate prediction for sponsored search advertising in microsoft’s bing search engine. In: 27th international conference on machine learning. Omnipress, pp 13–20Google Scholar
  22. 22.
    Gao Z, Gao Q (2013) Ad-centric model discovery for predicting ads’s click-through rate. Procedia Comput Sci 19:155–162CrossRefGoogle Scholar
  23. 23.
    Wang F, Zhang P, Shang Y, Shi Y (2013) The application of multiple criteria linear programming in advertisement clicking events prediction. Procedia Comput Sci 18:1720–1729CrossRefGoogle Scholar
  24. 24.
    Brzezinski JR, Knafl GJ (1999) Logistic regression modeling for context-based classification. In: 10th workshop on database and expert systems applications. IEEE, pp 755–759Google Scholar
  25. 25.
    Yeh I, Lien C (2009) the comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Syst Appl 36:2473–2480CrossRefGoogle Scholar
  26. 26.
    Fitzpatrick T, Mues C (2016) an empirical comparison of classification algorithms for mortgage default prediction: evidence from a aistressed mortgage market. Eur J Oper Res 249:427–439CrossRefMATHGoogle Scholar
  27. 27.
    Ng A (2000) Supervised learning models. machine learning (CS229). Lecture notesGoogle Scholar
  28. 28.
    Barber D (2006) Bayesian reasoning and machine learning. Cambridge University PressGoogle Scholar
  29. 29.
    Elkan C (2014) Maximum likelihood, logistic regression, and stochastic gradient training. principles of artificial intelligence: learning (CSE 250B). Lecture notesGoogle Scholar
  30. 30.
    Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: 19th international conference on computational statistics. Springer, Berlin, pp 177–186Google Scholar
  31. 31.
    Bottou L (2012) Stochastic gradient descent tricks. In: Montavon G, Orr GB, Müller KR (eds) Neural networks: tricks of the trade, LNCS, vol 7000. Springer, Berlin, pp 421–436CrossRefGoogle Scholar
  32. 32.
  33. 33.
    Guha S, Cheng B, Francis P (2010) Challenges in measuring online advertising systems. In: 10th ACM SIGCOMM conference on internet measurement. ACM, New York, pp 81–87Google Scholar
  34. 34.
    Cheng H, Cantú-Paz E (2010) Personalized click prediction in sponsored search. In: 3rd ACM international conference on web search and data mining. ACM, New York, pp 351–360Google Scholar
  35. 35.
    Chen Y, Yan TW (2012) Position-normalized click prediction in search advertising. In: 18th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, New York, pp 795–803Google Scholar
  36. 36.
    Dave KS, Varma V (2010) Pattern based keyword extraction for contextual advertising. In: 19th ACM International conference on information and knowledge management. ACM, New York, pp 1885–1888Google Scholar
  37. 37.
    Chen J, Stallaert J (2014) An economic analysis of online advertising using behavioral targeting. MIS Q 38:429–449CrossRefGoogle Scholar
  38. 38.
    Chen J, Stallaert J (2010) An economic analysis of online advertising using behavioral targeting. Forthcom MIS QGoogle Scholar
  39. 39.
    Mcdonald AM, Cranor LF (2009) An empirical study of how people perceive online behavioral advertising. Technical report, Behavioral advertising at CMU CyLabGoogle Scholar
  40. 40.
    Yan J, Liu N, Wang G, Zhang W (2009) How much can behavioral targeting help online advertising? In: 18th international conference on world wide web. ACM, New York pp 261–270Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Sarvajanik College of Engineering and TechnologySuratIndia

Personalised recommendations