Aiming at the shortcomings of the existing association classification algorithm, such as large resource consumption, difficult rule pruning, and complex classification model, an improved classification scheme ACCP based on classification and pruning is proposed. The algorithm mines the fore items of classification rules respectively according to the different classification attribute values, and improves the frequent item set mining process and rule pruning, which effectively improves the classification accuracy and algorithm operation efficiency. The experimental results show that the improved algorithm has higher classification accuracy than traditional CBA algorithm and C4.5 decision tree algorithm, and has achieved satisfied application results.