Abstract: Mining association rules is one of the important tasks in data mining that finds sets of items which come together in many transactions. Ranking the association rules is very important in market basket analysis and decision making. Applying data envelopment analysis for finding the candidate rules and selecting efficient association rules has been an interesting research field in recent years. In this study, we propose a new method for updating the ranked table of association rules, when new transactions are added to the market basket. We apply artificial neural networks for refreshing the ranking table, this prevents repeating all the process of solving the linear programming problem by data envelopment analysis. An illustrative example is presented and the results are compared with the results of an earlier research.