2012 | OriginalPaper | Buchkapitel
A One-Phase Method for Mining High Utility Mobile Sequential Patterns in Mobile Commerce Environments
verfasst von : Bai-En Shie, Ji-Hong Cheng, Kun-Ta Chuang, Vincent S. Tseng
Erschienen in: Advanced Research in Applied Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Mobile sequential pattern mining is an emerging topic in data mining fields with wide applications, such as planning mobile commerce environments and managing online shopping websites. However, an important factor, i.e., actual utilities (i.e., profit here) of items, is not considered and thus some valuable patterns cannot be found. Therefore, previous researches [8, 9] addressed the problem of mining
high utility mobile sequential patterns
(abbreviated as
UMSPs
). Nevertheless the tree-based algorithms may not perform efficiently since
mobile transaction sequences
are often too complex to form compress tree structures. A novel algorithm, namely
UM-Span
(
high Utility Mobile Sequential Pattern mining
), is proposed for efficiently mining UMSPs in this work. UM-Span finds UMSPs by a projected database based framework. It does not need additional database scans to find actual UMSPs, which is the bottleneck of utility mining. Experimental results show that UM-Span outperforms the state-of-the-art UMSP mining algorithms under various conditions.