Rank-aware clustering of structured datasets

Julia Stoyanovich, Sihem Amer-Yahia

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

    Abstract

    In online applications such as Yahoo! Personals and Yahoo! Real Estate users define structured profiles in order to find potentially interesting matches. Typically, profiles are evaluated against large datasets and produce thousands of matches. In addition to filtering, users also specify ranking in their profile, and matches are returned in a ranked list. Top results in a list are typically homogeneous, which hinders data exploration. For example, a user looking for 1- or 2-bedroom apartments sorted by price will see a large number of cheap 1-bedrooms in undesirable neighborhoods before seeing a different apartment. An alternative to ranking is to group matches on common attribute values, e.g., cheap 1-bedrooms in good neighborhoods, 2-bedrooms with 2 baths, and choose groups in relationship with ranking. In this paper, we present a novel paradigm of rank-aware clustering, and demonstrate its effectiveness on a large dataset from Yahoo! Personals, a leading online dating site.

    Original languageEnglish (US)
    Title of host publicationACM 18th International Conference on Information and Knowledge Management, CIKM 2009
    Pages1429-1432
    Number of pages4
    DOIs
    StatePublished - Dec 1 2009
    EventACM 18th International Conference on Information and Knowledge Management, CIKM 2009 - Hong Kong, China
    Duration: Nov 2 2009Nov 6 2009

    Other

    OtherACM 18th International Conference on Information and Knowledge Management, CIKM 2009
    CountryChina
    CityHong Kong
    Period11/2/0911/6/09

    Fingerprint

    Ranking
    Clustering
    Paradigm
    Real estate

    Keywords

    • Information filtering
    • Information presentation
    • Rank-aware clustering
    • Structured datasets

    ASJC Scopus subject areas

    • Decision Sciences(all)
    • Business, Management and Accounting(all)

    Cite this

    Stoyanovich, J., & Amer-Yahia, S. (2009). Rank-aware clustering of structured datasets. In ACM 18th International Conference on Information and Knowledge Management, CIKM 2009 (pp. 1429-1432) https://doi.org/10.1145/1645953.1646137

    Rank-aware clustering of structured datasets. / Stoyanovich, Julia; Amer-Yahia, Sihem.

    ACM 18th International Conference on Information and Knowledge Management, CIKM 2009. 2009. p. 1429-1432.

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

    Stoyanovich, J & Amer-Yahia, S 2009, Rank-aware clustering of structured datasets. in ACM 18th International Conference on Information and Knowledge Management, CIKM 2009. pp. 1429-1432, ACM 18th International Conference on Information and Knowledge Management, CIKM 2009, Hong Kong, China, 11/2/09. https://doi.org/10.1145/1645953.1646137
    Stoyanovich J, Amer-Yahia S. Rank-aware clustering of structured datasets. In ACM 18th International Conference on Information and Knowledge Management, CIKM 2009. 2009. p. 1429-1432 https://doi.org/10.1145/1645953.1646137
    Stoyanovich, Julia ; Amer-Yahia, Sihem. / Rank-aware clustering of structured datasets. ACM 18th International Conference on Information and Knowledge Management, CIKM 2009. 2009. pp. 1429-1432
    @inproceedings{87581f24b8e5422b9262dd3d242d480d,
    title = "Rank-aware clustering of structured datasets",
    abstract = "In online applications such as Yahoo! Personals and Yahoo! Real Estate users define structured profiles in order to find potentially interesting matches. Typically, profiles are evaluated against large datasets and produce thousands of matches. In addition to filtering, users also specify ranking in their profile, and matches are returned in a ranked list. Top results in a list are typically homogeneous, which hinders data exploration. For example, a user looking for 1- or 2-bedroom apartments sorted by price will see a large number of cheap 1-bedrooms in undesirable neighborhoods before seeing a different apartment. An alternative to ranking is to group matches on common attribute values, e.g., cheap 1-bedrooms in good neighborhoods, 2-bedrooms with 2 baths, and choose groups in relationship with ranking. In this paper, we present a novel paradigm of rank-aware clustering, and demonstrate its effectiveness on a large dataset from Yahoo! Personals, a leading online dating site.",
    keywords = "Information filtering, Information presentation, Rank-aware clustering, Structured datasets",
    author = "Julia Stoyanovich and Sihem Amer-Yahia",
    year = "2009",
    month = "12",
    day = "1",
    doi = "10.1145/1645953.1646137",
    language = "English (US)",
    isbn = "9781605585123",
    pages = "1429--1432",
    booktitle = "ACM 18th International Conference on Information and Knowledge Management, CIKM 2009",

    }

    TY - GEN

    T1 - Rank-aware clustering of structured datasets

    AU - Stoyanovich, Julia

    AU - Amer-Yahia, Sihem

    PY - 2009/12/1

    Y1 - 2009/12/1

    N2 - In online applications such as Yahoo! Personals and Yahoo! Real Estate users define structured profiles in order to find potentially interesting matches. Typically, profiles are evaluated against large datasets and produce thousands of matches. In addition to filtering, users also specify ranking in their profile, and matches are returned in a ranked list. Top results in a list are typically homogeneous, which hinders data exploration. For example, a user looking for 1- or 2-bedroom apartments sorted by price will see a large number of cheap 1-bedrooms in undesirable neighborhoods before seeing a different apartment. An alternative to ranking is to group matches on common attribute values, e.g., cheap 1-bedrooms in good neighborhoods, 2-bedrooms with 2 baths, and choose groups in relationship with ranking. In this paper, we present a novel paradigm of rank-aware clustering, and demonstrate its effectiveness on a large dataset from Yahoo! Personals, a leading online dating site.

    AB - In online applications such as Yahoo! Personals and Yahoo! Real Estate users define structured profiles in order to find potentially interesting matches. Typically, profiles are evaluated against large datasets and produce thousands of matches. In addition to filtering, users also specify ranking in their profile, and matches are returned in a ranked list. Top results in a list are typically homogeneous, which hinders data exploration. For example, a user looking for 1- or 2-bedroom apartments sorted by price will see a large number of cheap 1-bedrooms in undesirable neighborhoods before seeing a different apartment. An alternative to ranking is to group matches on common attribute values, e.g., cheap 1-bedrooms in good neighborhoods, 2-bedrooms with 2 baths, and choose groups in relationship with ranking. In this paper, we present a novel paradigm of rank-aware clustering, and demonstrate its effectiveness on a large dataset from Yahoo! Personals, a leading online dating site.

    KW - Information filtering

    KW - Information presentation

    KW - Rank-aware clustering

    KW - Structured datasets

    UR - http://www.scopus.com/inward/record.url?scp=74549199357&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=74549199357&partnerID=8YFLogxK

    U2 - 10.1145/1645953.1646137

    DO - 10.1145/1645953.1646137

    M3 - Conference contribution

    AN - SCOPUS:74549199357

    SN - 9781605585123

    SP - 1429

    EP - 1432

    BT - ACM 18th International Conference on Information and Knowledge Management, CIKM 2009

    ER -