Optimization of frequent itemset mining based on FP-growth algorithm

Frequent itemset mining plays an important role in many important data mining tasks.However, with the rapid development of big data, the demand for valuable information in data is increasing.Aiming at the problems of inefficiency and load unevenness of traditional FP-Growth algorithm for mining in big data environment, an improved parallel FP-Growth algorithm is proposed in this paper.The load balancing strategy is chosen as the solution to the problem, the optimized computational volume model is constructed considering the shortcomings that the computational volume model cannot reflect the characteristics of the data itself, and the optimized parallel FP-Growth algorithm is implemented under the Spark computing framework.The load-balancing based PFP algorithm is optimized to a great extent in terms of the energy consumption of the algorithm operation, and the energy consumption is reduced by up to 63.73% compared to the PFP algorithm.Excellent runtime distribution is obtained for a large number of tasks, and the runtime share of tasks is in a balanced distribution state.It illustrates the performance advantage of the algorithm in this paper, which can be effectively adapted to the frequent itemset mining of big data.