Repayment failures of borrowers have greatly affected the sustainable development of the peer-to-peer (P2P) lending industry. The latest literature reveals that existing risk evaluation systems may ignore important signals and risk factors affecting P2P repayment. In our study, we applied four machine learning methods (random forest (RF), extreme gradient boosting tree (XGBT), gradient boosting model (GBM), and neural network (NN)) to predict important factors affecting repayment by utilizing data from Renrendai.com in China from Thursday, January 1, 2015, to Tuesday, June 30, 2015. The results showed that borrowers who have passed video, mobile phone, job, residence or education level verification are more likely to default on loan repayment, whereas those who have passed identity and asset certification are less likely to default on loans. The accuracy and kappa value of the four methods all exceed 90%, and RF is superior to the other classification models. Our findings demonstrate important techniques for borrower screening by P2P companies and risk regulation by regulatory agencies. Our methodology and findings will help regulators, banks and creditors combat current financial disasters caused by the coronavirus disease 2019 (COVID-19) pandemic by addressing various financial risks and translating credit scoring improvements.

This study aimed to investigate the influence of artificial intelligence in education (AIEd) on adolescents’ social adaptability, as well as to identify the relevant psychosocial factors that can predict adolescents’ social adaptability. A total of 1328 participants (mean_age = 13.89, SD = 2.22) completed the survey. A machine-learning algorithm was used to find out whether AIEd may influence adolescents’ social adaptability as well as the relevant psychosocial variables, such as teacher–student relations, peer relations, interparental relations, and loneliness that may be significantly related to social adaptability. Results showed that it has a positive influence of AIEd on adolescents’ social adaptability. In addition, the four most important factors in the prediction of social adaptability among AI group students are interpersonal relationships, peer relations, academic emotion, and loneliness. A high level of interpersonal relationships and peer relations can predict a high level of social adaptability among the AI group students, while a high level of academic emotion and loneliness can predict a low level of social adaptability. Overall, the findings highlight the need to focus interventions according to the relation between these psychosocial factors and social adaptability in order to increase the positive influence of AIEd and promote the development of social adaptability.

A major goal of ideological education in China is to promote loyalty to the party-state and to instill atheism among the people. How effective is this ideological education? This article examines the relationship between education and trust in government and trust in religion using data from the 2010 Chinese General Social Survey. We find that education is negatively associated with trust in government, while positively related to trust in religion. Our findings suggest that policies aimed at displacing religion in favor of the Communist ideology have largely failed to shape the public mindset; rather, the more educated, the more people tend to trust religion instead of the government.

Background and Aims: There are no accurate statistical data on the relapse rate of drug abstainers after compulsory detoxification in China. This study aimed to collect relapse data for drug abstainers through follow-up visits, verify the effectiveness of professional social worker services and explore significant factors affecting relapse.Design and Setting: The drug abstainers released from Guangzhou T Compulsory Isolated Detoxification Center were randomly divided into two groups. The difference between the experimental group and the control group is that assistance services were provided by social workers to the former.Participants: The study included 510 drug abstainers released from T Center, including 153 in the experimental group and 357 in the control group.Measurements: Demographic information, history of drug abuse, and motivation for drug rehabilitation (SOCRATES) were collected 1 month prior to drug abstainer release from compulsory detoxification. Then, the relapse situation after their release was tracked according to fixed time points.Findings: The overall relapse rate of 510 drug abstainers after their release from compulsory detoxification was 47.6%. The average survival time to relapse based on survival analysis was 220 days (N = 486), as calculated with Bayesian estimation by the MCMC method. The average survival times to relapse of the experimental group and control group were 393 and 175 days, respectively. By taking the specific survival time as the dependent variable and the group as the control variable (OR = 25.362), logistic regression analysis showed that marital status (OR = 2.666), previous compulsory detoxification experience (OR = 2.329) and location of household registration (OR = 1.557) had a significant impact on the survival time to relapse.Conclusions: The occurrence of relapse among drug patients released from compulsory detoxification can be delayed effectively through the intervention of professional social worker services. Regardless of whether patients receive aftercare after compulsory detoxification, drug-using patients who are single, have multiple detoxification experiences and whose households are registered in other provinces deserve special attention. Relevant suggestions to avoid relapse are provided.

This study aimed to explore which factors had a greater impact on substance craving in people with substance use and the direction of the impact. A total of 895 male substance users completed questionnaires regarding substance craving, psychological security, positive psychological capital, interpersonal trust, alexithymia, impulsivity, parental conflict, aggression behavior, life events, family intimacy, and deviant peers. Calculating the factor importance by gradient boosting method (GBM), found that the psychosocial factors that had a greater impact on substance craving were, in order, life events, aggression behavior, positive psychological capital, interpersonal trust, psychological security, impulsivity, alexithymia, family intimacy, parental conflict, and deviant peers. Correlation analysis showed that life events, positive psychological capital, interpersonal trust, psychological security, and family intimacy negatively predicted substance craving, while aggression behavior, impulsivity, alexithymia, parental conflict, and deviant peers positively predicted substance cravings. These findings have important implications for the prevention and intervention of substance craving behavior among substance users.