2017 | OriginalPaper | Buchkapitel
Cost-sensitive Association Rule Modeling for Predicting Sequential Event
verfasst von : Hai-yan YU, Meng-li YANG, Jie JIAN
Erschienen in: Proceedings of the 23rd International Conference on Industrial Engineering and Engineering Management 2016
Verlag: Atlantis Press
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
To capture the behavior trends and relationships among the entities in the data, a cost-sensitive association rule model was built to achieve robust decisions. This model was trained through the imbalanced data and the reasoning loss was formulated on the concept of loss rate under uncertainty. This model distinguished the cost-sensitive losses between false negative rate and false positive rate. Considering the characteristic of ROC curve, the minimization principle of reasoning loss was obtained through a gradient descent method according to the sufficient condition for the cost-insensitive reasoning, and this approach established the mechanism of robust association rule inferences. Finally, the effectiveness of the proposed approach was validated by the simulation with real decision data sets.