The improved AdaBoost-SVM algorithm is used to classify the safety and the risk from the Peers-to-Peers net loan platforms. Since the SVM algorithm is hard to deal with the rare samples and its training is slow, rule sampling is used to reduce the classify noise. Then, with the combinations of learning machine, P2P risks can be identified. The result shows that IAdaBoost algorithm can improve the risk platform classification accuracy. And the error of classification can be controlled in 5%.
Chew, H.-G., Crisp, D. J., Bogner, R. E. et al. (2000). Target Detection in Radar Imagery Using Support Vector Machines with Training Size Biasing. In Proceedings of the Sixth International Conference on Control, Automation, Robotics and Vision, Singapore.
Joshi, M. V., Agarwal, R. C., & Kumar, V. (2002). Predict Rare Classes: Can Boosting Make Any Weak Learner Strong? In Proceedings of the Eighth ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2002), Edmonton, Canada.