In order to solve the problem of qualitative analysis and low real-time performance of collusion identification methods in power market, this paper proposes an intelligent identification method of collusion behavior based on AdaBoost-DT algorithm, which uses AdaBoost-DT integrated classification algorithm to identify collusion behavior, and solves the problem that collusion behavior is difficult to identify quantitatively. Firstly, based on the mechanism of collusion, a set of collusion identification index system is designed. In the face of the problem of data imbalance, the oversampling method is used to expand the training data set, and the AdaBoost-DT classification algorithm is used to train the collusion behavior intelligent identification model. Finally, based on the monthly transaction data, an example is analyzed, and the receiver operating characteristic curve (ROC curve) and the area under the receiver operating characteristic curve (AUC value) are used to evaluate the recognition effect of the model. The experimental results show that the proposed method has good accuracy and real-time performance, which fully verifies the effectiveness of the algorithm.