The invention discloses an item set mining method and apparatus, and belongs to the technical field of data mining. The method comprises the steps of obtaining a self-defined minimum utility threshold, a price table and a discount table, wherein the price table contains cost prices and sales prices corresponding to data items, and the discount table contains discount types and discount parameters corresponding to the data items; for each item set in a database, calculating an actual utility value of the item set according to the cost prices, the sales prices, the discount types and the discount parameters corresponding to the data items contained in the item set, wherein the item set contains at least one data item; and when the actual utility value is greater than or equal to the minimum utility threshold, determining the item set as a high-utility item set. According to the method and the apparatus, the effect of enabling the calculated actual utility value of the item set in the database to be more accurate in combination with a discount policy corresponding to the data items so as to increase the actual useful value of the mined high-utility item set is achieved.