Modeling and predicting user behavior in sponsored search

Josh Attenberg, Sandeep Pandey, Torsten Suel

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine's browser toolbar.

    Original languageEnglish (US)
    Title of host publicationKDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
    Pages1067-1075
    Number of pages9
    DOIs
    StatePublished - 2009
    Event15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '09 - Paris, France
    Duration: Jun 28 2009Jul 1 2009

    Other

    Other15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '09
    CountryFrance
    CityParis
    Period6/28/097/1/09

    Fingerprint

    Search engines
    Navigation
    Classifiers
    Feedback
    Experiments

    Keywords

    • Implicit feedback
    • Sponsored search
    • User behavior

    ASJC Scopus subject areas

    • Software
    • Information Systems

    Cite this

    Attenberg, J., Pandey, S., & Suel, T. (2009). Modeling and predicting user behavior in sponsored search. In KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1067-1075) https://doi.org/10.1145/1557019.1557135

    Modeling and predicting user behavior in sponsored search. / Attenberg, Josh; Pandey, Sandeep; Suel, Torsten.

    KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009. p. 1067-1075.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Attenberg, J, Pandey, S & Suel, T 2009, Modeling and predicting user behavior in sponsored search. in KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 1067-1075, 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '09, Paris, France, 6/28/09. https://doi.org/10.1145/1557019.1557135
    Attenberg J, Pandey S, Suel T. Modeling and predicting user behavior in sponsored search. In KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009. p. 1067-1075 https://doi.org/10.1145/1557019.1557135
    Attenberg, Josh ; Pandey, Sandeep ; Suel, Torsten. / Modeling and predicting user behavior in sponsored search. KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009. pp. 1067-1075
    @inproceedings{51e6f419f7c74188a3f93e68cbf1560f,
    title = "Modeling and predicting user behavior in sponsored search",
    abstract = "Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine's browser toolbar.",
    keywords = "Implicit feedback, Sponsored search, User behavior",
    author = "Josh Attenberg and Sandeep Pandey and Torsten Suel",
    year = "2009",
    doi = "10.1145/1557019.1557135",
    language = "English (US)",
    isbn = "9781605584959",
    pages = "1067--1075",
    booktitle = "KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

    }

    TY - GEN

    T1 - Modeling and predicting user behavior in sponsored search

    AU - Attenberg, Josh

    AU - Pandey, Sandeep

    AU - Suel, Torsten

    PY - 2009

    Y1 - 2009

    N2 - Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine's browser toolbar.

    AB - Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine's browser toolbar.

    KW - Implicit feedback

    KW - Sponsored search

    KW - User behavior

    UR - http://www.scopus.com/inward/record.url?scp=70350663002&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70350663002&partnerID=8YFLogxK

    U2 - 10.1145/1557019.1557135

    DO - 10.1145/1557019.1557135

    M3 - Conference contribution

    AN - SCOPUS:70350663002

    SN - 9781605584959

    SP - 1067

    EP - 1075

    BT - KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

    ER -