Internet finance has permeated into myriad households, bringing about lifestyle convenience alongside potential risks. Presently, internet finance enterprises are progressively adopting machine learning and other artificial intelligence methods for risk alertness. What is the current status of the application of various machine learning models and algorithms across different institutions? Is there an optimal machine learning algorithm suited for the majority of internet finance platforms and application scenarios? Scholars have embarked on a series of studies addressing these questions; however, the focus predominantly lies in comparing different algorithms within specific platforms and contexts, lacking a comprehensive discourse and summary on the utilization of machine learning in this domain. Thus, based on the data from Web of Science and Scopus databases, this paper conducts a systematic literature review on all aspects of machine learning in internet finance risk in recent years, based on publications trends, geographical distribution, literature focus, machine learning models and algorithms, and evaluations. The research reveals that machine learning, as a nascent technology, whether through basic algorithms or intricate algorithmic combinations, has made significant strides compared to traditional credit scoring methods in predicting accuracy, time efficiency, and robustness in internet finance risk management. Nonetheless, there exist noticeable disparities among different algorithms, and factors such as model structure, sample data, and parameter settings also influence prediction accuracy, although generally, updated algorithms tend to achieve higher accuracy. Consequently, there is no one-size-fits-all approach applicable to all platforms; each platform should enhance its machine learning models and algorithms based on its unique characteristics, data, and the development of AI technology, starting from key evaluation indicators to mitigate internet finance risks.
Living in high expressed emotion (EE) environments tends to increase the relapse rate in schizophrenia (SZ). At present, the neural substrates responsible for high EE in SZ remain poorly understood. Functional near-infrared spectroscopy (fNIRS) may be of great use to quantitatively assess cortical hemodynamics and elucidate the pathophysiology of psychiatric disorders. In this study, we designed novel low- (positivity and warmth) and high-EE (criticism, negative emotion, and hostility) stimulations, in the form of audio, to investigate cortical hemodynamics. We used fNIRS to measure hemodynamic signals while participants listened to the recorded audio. Healthy controls (HCs, [Formula: see text]) showed increased hemodynamic activation in the major language centers across EE stimulations, with stronger activation in Wernicke's area during the processing of negative emotional language. Compared to HCs, people with SZ ([Formula: see text]) exhibited smaller hemodynamic activation in the major language centers across EE stimulations. In addition, people with SZ showed weaker or insignificant hemodynamic deactivation in the medial prefrontal cortex. Notably, hemodynamic activation in SZ was found to be negatively correlated with the negative syndrome scale score at high EE. Our findings suggest that the neural mechanisms in SZ are altered and disrupted, especially during negative emotional language processing. This supports the feasibility of using the designed EE stimulations to assess people who are vulnerable to high-EE environments, such as SZ. Furthermore, our findings provide preliminary evidence for future research on functional neuroimaging biomarkers for people with psychiatric disorders.