An Approach For Optimize Rule Mining Based on Domain Problem Information and Pareto Front
An Approach For Optimize Rule Mining Based on Domain Problem Information and Pareto Front
milad gholipoor moghaddam1
1) Department of computer engineering, south Tehran branch, Islamic Azad University, Tehran, Iran
IOI Code
:
XYDK-AHBDG
Publication :
International Conference On Research Science And Technology(restconf.com)
Abstract :
Having a look at growing amount of stored data on different information systems such as shopping centers and medical data we certainly need a method to make use of these stored data in the most efficient way in order to help making decisions based on them. But because of vast amount of data, we must choose some parts of them to use. In the most of time we decide on this data with two factor: support and confidence but we don’t notice to another important factors like volume of purchased items. When these factors grow up, a multi-value decision making method can be quite helpful. In this paper we put forward a new method for discovering association rules by notice to volume and benefit of sold items, finally for have a good decision based on this rules a ranking approach which is based on pareto-front is going to be introduced, It is used to measure efficiency of association rules for multi-goal purposes.
Keywords : data mining multi goal decision making pareto front association rules