The selection of the relevant association rules using the ELECTRE method with multiple criteria

Abstract

The extraction of association rules is a very attractive data mining task and the most widespread in the business world and in modern society, trying to obtain the interesting relationship and connection between collections of articles, products or items in high transactional databases. The immense quantity of association rules obtained expresses the main obstacle that a decision maker can handle. Consequently, in order to establish the most interesting association rules, several interestingness measures have been introduced. Currently, there is no optimal measure that can be chosen to judge the selected association rules. To avoid this problem we suggest to apply ELECTRE method one of the multi-criteria decision making, taking into consideration a formal study of measures of interest according to structural properties, and intending to find a good compromise and select the most interesting association rules without eliminating any measures. Experiments conducted on reference data sets show a significant improvement in the performance of the proposed strategy.

A genetic algorithm coupled with tree-based pruning for mining closed association rules

“…Outliers may sometimes become a separate cluster instead of being ignored MCDA-ELECTRE [33] -Apply the ELECTRE method to find the best association rule -Measures are taken as attributes and association rules as alternatives and a decision matrix is constructed -Desired rules are obtained with maximum interestingness Redundancy of the rules is not addressed FP-Growth [35] -Uses Association Rule Mining to analyze skill-job relationships -Jobs are analyzed using the FP-Growth algorithm able to retrieve and process large amounts of data posted online -Construction of FP-tree is difficult -The memory may be insufficient if the database is large TAR [36] -Uses Apriori and FP-growth to generate itemsets -Generates association rules to find the relation between weather data variables accompanied by time scale parameters.…”

“…The proposed approach uses the divide and conquers approach along with graph theory to enhance the process of association rule learning. The best association rules were extracted using the Élimination Et Choix Traduisant La Realité (Elimination and Choice Translating Reality/ELECTRE) method [33]. A modified frequent pattern (FP)-growth algorithm is put forth by Shawkat et al [34] to overcome the performance gap while handling large datasets.…”

Decision‐making support for an autonomous software‐defined network orchestrator

“…This article dealt with the fact that there are numerous rules and stakeholders for decision making and smart energy system introduction, whereas the rules of the game, that is, who does what and when, are seriously missing. In [6], the Electre method makes it possible to create and choose the best association rules and limit their number to improve the decision making in application areas such as business or scientific studies. One of the ideas is to weigh the rules to select the most relevant ones.…”

“…As described in related work [12,13], different methods for calculating the SLA and comparing it to the signed SLA between the customer and the operator, exist. In our function (6), the SLA calculated after applying the rule is compared to the signed SLA (absolute), considering that the random decision SLA (relatively, j = 1) is part of the function. Services such as gaming, browsing, or video streaming require a minimum bandwidth to run correctly.…”

“…We then analyse articles detailing the contributions of the orchestration and rules to enhance the decision-making process and network autonomy (see Section 2.3). Considering the originality of our approach, we extend our research to broader fields unrelated to telecommunications [5][6][7].…”