In order to solve the problem that the large amount of marketing data of power supply company reduces the processing efficiency of data frequent itemsets, a marketing data mining system of power supply company based on Apriori algorithm was designed. The hardware design deploys through the physical architecture of the marketing data mining system, builds the hardware environment of the system, and realizes the synchronization of database information; the software design of the power marketing data warehouse, uses Apriori algorithm to process frequent itemsets through mapping and pruning, mines association rules, establishes multi-dimensional data mining model, and realizes the data mining function of the system. The experimental results show that the difference between the predicted value and the actual value of the system in the application of power load forecasting is small. Under the conditions of minimum support and transaction data volume, the execution time of data mining is less than 2 s and 10 s respectively, which has high execution efficiency and shows that the system is feasible.