Corporate internet reporting (CIR) has such advantages as the strong timeliness, large amount, and wide coverage of financial information. However, the CIR, like any other online information, faces various risks. With the aid of the increasingly sophisticated artificial intelligence (AI) technology, this paper proposes an improved deep learning algorithm for the prediction of CIR risks, aiming to improve the accuracy of CIR risk prediction. After building a reasonable evaluation index system (EIS) for CIR risks, the data involved in risk rating and the prediction of risk transmission effect (RTE) were subject to structured feature extraction and time series construction. Next, a combinatory CIR risk prediction model was established by combining the autoregressive moving average (ARMA) model with long short-term memory (LSTM). The former is good at depicting linear series, and the latter excels in describing nonlinear series. Experimental results demonstrate the effectiveness of the ARMA-LSTM model. The research findings provide a good reference for applying AI technology in risk prediction of other areas.
With the rapid advances of Internet technology, some listed companies choose to disclose their financial information in the form of corporate internet reporting (CIR). However, there is little report on the risk factors and formation mechanism of CIR risks. To better prewarn, prevent and regulate CIR risks, this paper designs an CIR risk propagation model based on fuzzy neural network (FNN). Firstly, an evaluation index system (EIS) was established for CIR safety, and subject to fuzzy comprehensive evaluation (FCE), after reliability analysis and weighting of the indices. Based on the evaluation results, the hypotheses and risk propagation mode were summarized, and used to set up a risk propagation model. Finally, a neural network (NN) algorithm was created to predict the CIR risk propagation path. The proposed model and algorithm were proved effective through experiments. The research findings provide a novel tool to dig deep into the propagation mechanism of CIR risks.
Corporate decision makers will weigh and balance before making any decisions at different points in time. Different time and process of decision-making will lead to different degrees of risk to the financial status of the company. According to different inter-temporal decision-making financial risks, corporate decision makers will show different behavioral responses and neural changes. Based on the brain evoked potential testing technology, this study tests the behavioral performance and brain mechanism responses of the subjects under the frameworks of financial risk and zero financial risk, and explores the brain evoked potential and brain network mechanism of inter-temporal decision-making on financial risks. The experimental results show that subjects are more willing to choose the options that are nearer in time and smaller in number under the framework of risk conditions. Under the two frame conditions, the decision type has significant main effect, while the electrode has no main effect, and there is no interaction effect between the decision type and the electrode. The degree distribution, clustering coefficient and shortest path length under the two frame conditions are different, that is, the function and efficiency of brain network are different. Analysis of the key nodes by degree distribution also shows that the brain mechanism is different under the two conditions.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.