A Fast Web Transaction Pattern Mining Algorithm
In this paper, the authors explore a new algorithm for obtain valuable web transaction patterns from EC environment. The method is based on the pattern-growth framework. During the process, both the traversing and purchasing behaviors of customers are considered simultaneously. Different prune methods are adopted to increase the mining speed and accuracy, the web site structure is used to optimize the algorithm. The synthetic data is generated to validate their method. The experimental results show that the algorithm WTPM is correct and efficient.