Towards a unified symbolic AI framework for mining high utility itemsets - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Towards a unified symbolic AI framework for mining high utility itemsets

Résumé

This paper deals with the task of mining high utility itemsets. The proposed approach presents a unified framework for efficiently mining high utility patterns from transaction databases while handling effectively various condensed representations. In addition, this approach offers a way to integrate multiple constraints, including closedness, minimality, and maximality, while maintaining flexibility in the mining process. This allows to significantly enhance the efficiency and effectiveness of mining high utility patterns, making it a valuable tool for various data mining applications. Finally, we show through an extensive campaign of experiments on several popular real-life datasets the efficiency of our proposed approach.
Fichier non déposé

Dates et versions

hal-04430612 , version 1 (01-02-2024)

Identifiants

Citer

Amel Hidouri, Badran Raddaoui, Saïd Jabbour. Towards a unified symbolic AI framework for mining high utility itemsets. International Conference on Information Integration and Web Intelligence, Dec 2023, Bali, Indonesia, Indonesia. pp.77-91, ⟨10.1007/978-3-031-48316-5_11⟩. ⟨hal-04430612⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More