The improved AdaBoost-SVM algorithm is used to classify the safety and the\nrisk from the Peers-to-Peers net loan platforms. Since the SVM algorithm is\nhard to deal with the rare samples and its training is slow, rule sampling is\nused to reduce the classify noise. Then, with the combinations of learning\nmachine, P2P risks can be identified. The result shows that IAdaBoost algorithm\ncan improve the risk platform classification accuracy. And the error of\nclassification can be controlled in 5%.
Loading....