Electronic transaction fraud detection based on improved PSO algorithm

Aiming to the problem of how to find the cheating samples of the Electronic transaction, using method of assigning the value on every particle base on the environment, the improved particle swarm optimization (PSO) algorithm is presented to handle this problem. Though the theoretical derivation, the cheating sample is detected in optimization cost and the adaptability and correctness of the algorithm is proofed. The correctness of theoretical derivation is also verified by the experiment.