Minimally Complete Retrieval in Recommender Systems

DMG McSherry

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

    Abstract

    Most retrieval algorithms in recommender systems are incomplete in the sense that the existence of a product that satisfies a given subset of the constraints in a user’s query does not guarantee that such a product will be retrieved. Moreover, no existing retrieval algorithm is minimally complete (i.e., always produces a retrieval set of the smallest possible size required for completeness). In this paper, we present an algorithm for minimally complete retrieval called MCR-1 and show how similarity can also be used to inform the retrieval process. We also present theoretical results that enable the maximum possible size of the MCR-1 retrieval set to be determined for a given query, and show empirically that the algorithm tends to produce much smaller retrieval sets than are possible in theory as query size increases.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Pages83-92
    Number of pages10
    Publication statusPublished - Aug 2008
    Event19th Irish Conference on Artificial Intelligence and Cognitive Science - Cork, Ireland
    Duration: 1 Aug 2008 → …
    http://www.cs.ucc.ie/aics08/Welcome.html

    Conference

    Conference19th Irish Conference on Artificial Intelligence and Cognitive Science
    Period1/08/08 → …
    Internet address

    Fingerprint

    Recommender systems

    Cite this

    McSherry, DMG. (2008). Minimally Complete Retrieval in Recommender Systems. In Unknown Host Publication (pp. 83-92)
    McSherry, DMG. / Minimally Complete Retrieval in Recommender Systems. Unknown Host Publication. 2008. pp. 83-92
    @inproceedings{f18dbe86a95548b9a7be17e32615a25e,
    title = "Minimally Complete Retrieval in Recommender Systems",
    abstract = "Most retrieval algorithms in recommender systems are incomplete in the sense that the existence of a product that satisfies a given subset of the constraints in a user’s query does not guarantee that such a product will be retrieved. Moreover, no existing retrieval algorithm is minimally complete (i.e., always produces a retrieval set of the smallest possible size required for completeness). In this paper, we present an algorithm for minimally complete retrieval called MCR-1 and show how similarity can also be used to inform the retrieval process. We also present theoretical results that enable the maximum possible size of the MCR-1 retrieval set to be determined for a given query, and show empirically that the algorithm tends to produce much smaller retrieval sets than are possible in theory as query size increases.",
    author = "DMG McSherry",
    note = "In D. Bridge et al. (eds) AICS 08: Proceedings of the 19th Irish Conference on Artificial Intelligence and Cognitive Science",
    year = "2008",
    month = "8",
    language = "English",
    pages = "83--92",
    booktitle = "Unknown Host Publication",

    }

    McSherry, DMG 2008, Minimally Complete Retrieval in Recommender Systems. in Unknown Host Publication. pp. 83-92, 19th Irish Conference on Artificial Intelligence and Cognitive Science, 1/08/08.

    Minimally Complete Retrieval in Recommender Systems. / McSherry, DMG.

    Unknown Host Publication. 2008. p. 83-92.

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

    TY - GEN

    T1 - Minimally Complete Retrieval in Recommender Systems

    AU - McSherry, DMG

    N1 - In D. Bridge et al. (eds) AICS 08: Proceedings of the 19th Irish Conference on Artificial Intelligence and Cognitive Science

    PY - 2008/8

    Y1 - 2008/8

    N2 - Most retrieval algorithms in recommender systems are incomplete in the sense that the existence of a product that satisfies a given subset of the constraints in a user’s query does not guarantee that such a product will be retrieved. Moreover, no existing retrieval algorithm is minimally complete (i.e., always produces a retrieval set of the smallest possible size required for completeness). In this paper, we present an algorithm for minimally complete retrieval called MCR-1 and show how similarity can also be used to inform the retrieval process. We also present theoretical results that enable the maximum possible size of the MCR-1 retrieval set to be determined for a given query, and show empirically that the algorithm tends to produce much smaller retrieval sets than are possible in theory as query size increases.

    AB - Most retrieval algorithms in recommender systems are incomplete in the sense that the existence of a product that satisfies a given subset of the constraints in a user’s query does not guarantee that such a product will be retrieved. Moreover, no existing retrieval algorithm is minimally complete (i.e., always produces a retrieval set of the smallest possible size required for completeness). In this paper, we present an algorithm for minimally complete retrieval called MCR-1 and show how similarity can also be used to inform the retrieval process. We also present theoretical results that enable the maximum possible size of the MCR-1 retrieval set to be determined for a given query, and show empirically that the algorithm tends to produce much smaller retrieval sets than are possible in theory as query size increases.

    M3 - Conference contribution

    SP - 83

    EP - 92

    BT - Unknown Host Publication

    ER -

    McSherry DMG. Minimally Complete Retrieval in Recommender Systems. In Unknown Host Publication. 2008. p. 83-92