Scalable and Efficient Approach for High Temporal Fuzzy Utility Pattern Mining.

Area of Science:

• Data Mining
• Knowledge Discovery
• Artificial Intelligence

Background:

• Fuzzy utility (FU) pattern mining aids human reasoning in knowledge discovery.
• Existing methods incorporate temporal factors but face scalability challenges due to candidate generation.
• Interpreting quantitative data using linguistic terms offers a human-centric perspective.

Purpose of the Study:

• To propose a scalable and efficient approach for mining high temporal fuzzy utility patterns.
• To address the limitations of level-wise approaches in existing FU pattern mining techniques.
• To improve the performance of FU pattern mining by eliminating candidate generation.

Main Methods:

• Developed a novel data structure for efficient temporal FU pattern mining.
• Implemented efficient pruning techniques and algorithms.
• Utilized a level-free approach to avoid candidate generation.

Main Results:

• The proposed approach demonstrates superior performance compared to state-of-the-art algorithms.
• Achieved significant improvements in runtime and memory usage.
• Exhibited enhanced scalability on both real and synthetic datasets.

Conclusions:

• The novel approach offers a scalable and efficient solution for temporal fuzzy utility pattern mining.
• Eliminating candidate generation leads to better performance and scalability.
• This method enhances the interpretability of complex datasets through linguistic terms.