What is it about?
Data mining techniques for pattern discovery greatly help decision-makers in identifying the best patterns. This study simulates how the modified FP-Growth algorithm performs two pruning phases prior to the generation of a frequent pattern. With the use of this dual pruning process, the data source is further cleaned from less important items that were included in the pattern, leading to the creation of more interesting patterns.
Featured Image
Photo by Andrew Ridley on Unsplash
Why is it important?
The improved FP-Growth algorithm's dual pruning steps further eliminate weak and uninteresting patterns, leaving a more significant pattern for decision-making.
Perspectives
This research is based on my earlier publication about improving the FP-Growth algorithm. This work focuses on testing and simulating the model using weblogs to identify user access patterns to websites. However, the model can be used to simulate different datasets for similar purpose - generating frequent patterns.
Roseclaremath Caroro
Misamis University
Read the Original
This page is a summary of: Modified Anti-Monotone Support Pruning on FP Tree for Improved Frequent Pattern Generation, January 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3305160.3305185.
You can read the full text:
Contributors
The following have contributed to this page
