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%.
Inspired by sensor coverage density and matching & preserving strategy, this paper proposes an Improved Artificial Bee Colony (IABC) algorithm which is designed to optimize bridge sensor placement. We use dynamic random coverage coding method to initialize colony to ensure the diversity and effectiveness. In addition, we randomly select the factors with lower trust value to search and evolve after food source being matched in order that the relatively high trust point factor is retained in the exploitation of food sources, which reduces the blindness of searching and improves the efficiency of convergence and the accuracy of the algorithm. According to the analysis of the modal data of the Ha-Qi long span railway bridge, the results show that IABC algorithm has faster convergence rate and better global search ability when solving the optimal placement problem of bridge sensor. The final analysis results also indicate that the IABC’s solution accuracy is 76.45% higher than that of the ABC algorithm, and the solution stability is improved by 86.23%. The final sensor placement mostly covers the sensitive monitoring points of the bridge structure and, in this way, the IABC algorithm is suitable for solving the optimal placement problem of large bridge and other structures.
This paper combines the nonlinear dimensionality reduction method, and the Restricted Boltzmann machine (RBM algorithm), to assess the credit risk of P2P borrowers. After screening and processing many big data indicators, the most representative indicators are selected to build the P2P customer credit risk assessment model. In addition, after comparing the advantages and disadvantages of linear dimensionality reduction algorithm and nonlinear dimensionality reduction algorithm, this paper establishes a P2P enterprise customer credit risk assessment model based on RBM feature extraction combined with contrast divergence theory. It is concluded that the effect of RBM is better than that of PCA when the same model is selected. The Logistic model performs best in the three models when the same data feature extraction method is selected.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.