A data mining method for determining association rules within a multitude of N transactions. Each transaction includes up to p different items. A sample size n of the multitude of N transactions is computed based on precision requirements such that n is at least an estimated sample size n*. Association rules are computed based on a sample of the multitude of N transactions with sample size n according to a methodology for mining of association rules, using the association rules as estimated association rules of the multitude of N transactions.