P2P Lending Default Prediction Based on AI and Statistical Models.

Peer-to-peer lending (P2P lending) has proliferated in recent years thanks to Fintech and big data advancements. However, P2P lending platforms are not tightly governed by relevant laws yet, as their development speed has far exceeded that of regulations. Therefore, P2P lending operations are still subject to risks. This paper proposes prediction models to mitigate the risks of default and asymmetric information on P2P lending platforms. Specifically, we designed sophisticated procedures to pre-process mass data extracted from Lending Club in 2018 Q3-2019 Q2. After that, three statistical models, namely, Logistic Regression, Bayesian Classifier, and Linear Discriminant Analysis (LDA), and five AI models, namely, Decision Tree, Random Forest, LightGBM, Artificial Neural Network (ANN), and Convolutional Neural Network (CNN), were utilized for data analysis. The loan statuses of Lending Club's customers were rationally classified. To evaluate the models, we adopted the confusion matrix series of metrics, AUC-ROC curve, Kolmogorov-Smirnov chart (KS), and Student's t-test. Empirical studies show that LightGBM produces the best performance and is 2.91% more accurate than the other models, resulting in a revenue improvement of nearly USD 24 million for Lending Club. Student's t-test proves that the differences between models are statistically significant.

An evaluation of immunization coverage of the first dose of measles containing vaccine using incidence rate / 预防医学

Objective To evaluate the immunization coverage of the first dose of measles containing vaccine (MCV1 )by using the incidence of measles in Wenzhou City.Methods Descriptive epidemiological methods were used to analyze measles cases that reported in Wenzhou city from 2007 to 2012 and evaluate the immunization coverage of the first dose of measles containing vaccine.Results The average annual incidence rate was 10.46/100 000 from 2007 to 2012,and the annual incidence rate was 43.44/100 000 for children aged from 8 months to 83 months (42.59%).Based on the proportion of immunized measles cases vaccine effectiveness (VE)of MCV,the evaluated coverage rate of MCV1 was 73.80% (VE=90%)or 84.92% (VE=95%)in children aged from 13 to 83 months.The evaluated coverage rate of MCV1 was 83.25%(VE=90%)or 90.86%(VE=95%)in local children and 69.5 1%(VE=90%)or 82.02%(VE=95%)in migrating children.The timely immunization rate of MCV1 was 59.48% (VE =90%)or 74.59% (VE =95%).Conclusion The coverage rate and timely coverage rate of MCV1 are still low.It is important to strengthen the management of migrating population and enhance propaganda to ensure a high level vaccination rate to accelerate the elimination of measles.