Crisis Warning Research Articles

Optimization of Enterprise Financial Risk Management and Crisis Early Warning System Supported by AI

The stability of the financial market plays a key role in the overall health of the economic system, and optimizing corporate financial risk management and crisis warning systems is of great significance. Traditional financial risk management methods often face challenges when processing large-scale, resulting in a decrease in the accuracy of risk assessment. This study combining gated recurrent units (GRU), temporal convolutional networks (TCN) and attention mechanisms. Leverage diverse data sets to improve the accuracy of financial risk assessments and the effectiveness of crisis warnings. Experimental results show that the algorithm outperforms the baseline model in terms of risk prediction accuracy, efficiency and stability. For example, on the LendingClub loan dataset, FLOPs are reduced by more than 46.8%, inference time is improved by more than 48.5%. This method provides new perspectives and solutions for optimizing corporate financial risk management and crisis warning systems. This will have a positive impact on the stable operation of enterprises and other aspects.

Research on Financial Crisis Warning Based on Vulnerability Index

After the global financial crisis in 2008, the early warning of financial crisis has become a necessary and urgent issue. It is of great significance to analyze the factors affecting financial crisis and clarify the relationship between credit growth, housing price fluctuation, current account deficit and financial risk in order to objectively and accurately predict the degree of influence of financial risk. This paper takes 41 global economies, including developed economies and emerging economies, from 1980 to 2019 as research objects, and analyzes the early warning ability of financial vulnerability indicators such as credit growth, housing price and current account deficit in a unified framework through panel Logit model. It is found that credit is not the only important indicator to predict crisis: when housing price, current account deficit and credit are under the same research framework, housing price and current account deficit have a lot of leading information, which can predict the occurrence of financial crisis; However, as house prices and current account deficits are added to the model, the early-warning power of credit is significantly lower than that of house prices. Paying attention to house price fluctuations and current account deficits has some implications for future policy making. In view of this, we should do a good job of cross-cycle policy adjustment, persist in curbing real estate financialization and bubbles, pay close attention to the direction and extent of current account adjustment, and prudently manage related financial risks.

초점사건 이후의 정책변동에 관한 연구

This study analyzes policy changes in response to COVID-19. Following the discovery of the first domestic case on January 20, 2020, the infectious disease crisis alert was raised from “watch” to “caution” to “warning”. This study classifies COVID-19 as a focal event and uses Birkland's ERPL model to analyze the process of policy agendization and policy change after the event. The results of the analysis show that, first, the focal event significantly increased the number of media reports at each stage of the epidemic crisis warning. Second, collective mobilization took place through the formation of the National Assembly Special Committee on COVID-19, the Health and Welfare Committee, and government expert group meetings. Third, the Special Committee as well as the standing committee discussed some proposals. Finally, some amendments were passed by the National Assembly. In conclusion, this study found that media coverage of the focal event of COVID-19 had a significant impact on policy changes.

Development and usability of a Mobile Interactive Application (VCPW) for Vascular Crisis Prewarning after Skin Flap Transplantation

In microsurgical tissue transfer, skin flap transplantation is frequently used to heal the surface of a wound. Effective microcirculation surveillance of the skin flap is crucial. However, with traditional monitoring methods-that is, clinical observation-vascular crisis can still occur, thereby impairing postoperative recovery. A smartphone application is required to assist health care professionals in the standardized collection of flap perfusion parameters for flap management. The Vascular Crisis Prewarning Application was created using a design science research methodology that prioritizes users and problems. The system usability scale was used to assess the application's usability among medical practitioners. The application was used at the clinic from December 2020 to September 2022. The unplanned return to the operating room, time to diagnose vascular crisis, and flap survival rate were compared with and without the application. The application consisted of 5 modules: patient addition and basic information entry, flap labeling, flap observation, crisis warning, and case archiving. The average rating for the application's usability among medical practitioners was 97.95 score (SD 2.36). With the application, the time to detect vascular crisis reduced from 26.71 to 16.26 h (P < 0.001), the unplanned return to the operation room increased from 8.18% to 10.24% (P=0.587), and the flap survival rate went from 94.55% to 99.21% (P=0.083). An easy-to-use flap perfusion monitoring and prewarning application for medical practitioners was produced using a user-centered development method. The application provided a more standardized and accurate platform for data collection in flap management and reduced the time to detect vascular crisis. Larger cohort studies are required in the future to better assess the full potential of the application.

Construction and Optimization of a Financial Early Warning System Based on Big Data and Deep Learning Technology

New technologies such as big data, artificial intelligence, mobile internet, cloud computing, Internet of Things, and blockchain have brought about significant changes and development in the financial industry. Predicting the financial situation of enterprises, reducing the probability of uncertainty risks, and reducing the likelihood of financial crises have become important issues in enterprise financial crisis warning. In view of the issues in enterprise financial early warning systems such as lag, low accuracy, and high warning costs in data analysis, a financial early warning system based on big data and deep learning technology has been established, taking into account the different situations of listed and non-listed companies. This carries significance in improving the accuracy of enterprise financial early warning and promoting timely and effective decision-making.

Research on forecasting model of corporate financial crisis based on pattern recognition and artificial intelligence

Abstract In today’s rapid development of the economic environment, the company’s financial crisis can significantly reflect the enterprise crisis, and it has a significant impact on the development of the enterprise. Therefore, the prediction of the company’s financial crisis and the establishment of an early warning system have important practical significance. Based on the method of pattern recognition and artificial intelligence, this paper establishes a new forecasting model of corporate financial crisis, predicts its financial index data and realises the dynamic financial crisis warning. The model developed in this paper employs pattern recognition and artificial intelligence, and is thus endowed with high classification accuracy, good anti-noise ability and the ability to be sorted according to the importance of its index features.

Research on College Network Early Warning Based on LSTM

With the development of information technology and the continuous optimization of China’s education system, college students have gradually become the main group in the Internet, and college network public opinion events have received increasing attention. By analyzing the constituent elements of university network public opinion, building an early warning indicator system from three dimensions: subject, carrier, and object, and combining life cycle theory, dynamic comprehensive evaluation method, and short-term memory network, constructing a university network public opinion model. Through empirical analysis of 20 university network public opinion events, the experimental results show that the proposed public opinion model has certain feasibility. Corresponding response strategies have also been proposed for different levels of crisis warning, providing a decision-making basis for relevant departments to guide and manage online public opinion in universities.

Characteristics of High Suicide Risk Messages From Users of a Social Network-Sina Weibo "Tree Hole".

BackgroundPeople with suicidal ideation post suicide-related information on social media, and some may choose collective suicide. Sina Weibo is one of the most popular social media platforms in China, and “Zoufan” is one of the largest depression “Tree Holes.” To collect suicide warning information and prevent suicide behaviors, researchers conducted real-time network monitoring of messages in the “Zoufan” tree hole via artificial intelligence robots.ObjectiveTo explore characteristics of time, content and suicidal behaviors by analyzing high suicide risk comments in the “Zoufan” tree hole.MethodsKnowledge graph technology was used to screen high suicide risk comments in the “Zoufan” tree hole. Users' level of activity was analyzed by calculating the number of messages per hour. Words in messages were segmented by a Jieba tool. Keywords and a keywords co-occurrence matrix were extracted using a TF-IDF algorithm. Gephi software was used to conduct keywords co-occurrence network analysis.ResultsAmong 5,766 high suicide risk comments, 73.27% were level 7 (suicide method was determined but not the suicide date). Females and users from economically developed cities are more likely to express suicide ideation on social media. High suicide risk users were more active during nighttime, and they expressed strong negative emotions and willingness to end their life. Jumping off buildings, wrist slashing, burning charcoal, hanging and sleeping pills were the most frequently mentioned suicide methods. About 17.55% of comments included suicide invitations. Negative cognition and emotions are the most common suicide reason.ConclusionUsers sending high risk suicide messages on social media expressed strong suicidal ideation. Females and users from economically developed cities were more likely to leave high suicide risk comments on social media. Nighttime was the most active period for users. Characteristics of high suicide risk messages help to improve the automatic suicide monitoring system. More advanced technologies are needed to perform critical analysis to obtain accurate characteristics of the users and messages on social media. It is necessary to improve the 24-h crisis warning and intervention system for social media and create a good online social environment.

Prediction of College Students' Psychological Crisis with a Neural Network Optimized by Harmony Search Algorithm

Despite the growing concern with students’ mental health education, there are neither extensive research on stressors of psychological crisis, nor targeted research on the psychological crisis warning of college students with different levels of psychological crisis. To solve the problem, this paper aims to explore the psychological crisis warning and physical education (PE) intervention of college students based on artificial neural network (ANN). Firstly, the important evaluation indexes were determined for psychological crisis warning of college students; according to the adverse reactions and performance of college students in physiology, cognition, emotion, and behavior, the index data were processed by partial least squares (PLS) method. Next, a psychological crisis warning model was developed based on the optimized ANN: the harmony search (HS) algorithm was improved based on the differential evolutionary (DE) algorithm, and then used to optimize the backpropagation neural network (BPNN). The proposed model was proved feasible and effective through experiments.

Rating the Crisis of Online Public Opinion Using a Multi-Level Index System

Online public opinion usually spreads rapidly and widely, thus a small incident probably evolves into a large social crisis in a very short time, and results in a heavy loss in credit or economic aspects. We propose a method to rate the crisis of online public opinion based on a multi-level index system to evaluate the impact of events objectively. Firstly, the dissemination mechanism of online public opinion is explained from the perspective of information ecology. According to the mechanism, some evaluation indexes are selected through correlation analysis and principal component analysis. Then, a classification model of text emotion is created via the training by deep learning to achieve the accurate quantification of the emotional indexes in the index system. Finally, based on the multi-level evaluation index system and grey correlation analysis, we propose a method to rate the crisis of online public opinion. The experiment with the real-time incident show that this method can objectively evaluate the emotional tendency of Internet users and rate the crisis in different dissemination stages of online public opinion. It is helpful to realizing the crisis warning of online public opinion and timely blocking the further spread of the crisis.

Research on the Early Warning and Intervention of Learning Crisis Based on Smart Classroom

Under the normal state of online and offline integrated learning of open courses, the low participation of learners and low learning results are hot issues that scholars in the industry pay more attention to. Accurate learning crisis warning and personalized teaching intervention are important measures to solve the above problems and improve teaching quality. Based on the analysis of the shortcomings of the existing learning early warning and teaching intervention, this study constructs a research framework of online open course learning early warning and intervention under the intelligent classroom learning environment. The framework diagnoses and warns learners' learning state from three aspects: knowledge mastery, learning behavior and learning mood. According to the diagnosis and warning report of learners, the corresponding intervention strategies are carefully designed, and learning analysis and data mining are applied to accurately match the implementation of intervention strategies to ensure the intervention effect and finally achieve the purpose of improving the learning effect.

Intelligent Early Warning Method Based on Drone Inspection

Commonly used UAV emergency inspection methods are executed by the instructions of the ground command center. The response rate depends on the stability of the communication network and the rapid response ability of the commander. The critical time window is fleeting, which is likely to cause unnecessary loss. Crisis rapid response capability has become the key to measuring system capabilities. In order to improve the system’s rapid response capability, a method of deploying decision-making agents on airborne computers and ground early warning systems is proposed. This early warning method uses key technologies such as multi-network integration, situation assessment, neural network architecture, deep learning, reinforcement learning, and intelligent cognitive reasoning to effectively ensure the effectiveness of crisis warning. The early warning method of the early warning system is as follows: the mission computer uniformly collects the flight control status parameters, the load status parameters and the load real-time data form a composite information flow. The task computer adopts the methods of protocol conversion, data classification, and danger recognition to the compound information flow to identify the crisis information and make a preliminary analysis and judgment of the crisis state. If it is determined that it is necessary to track the target in real time, the initial task assignment and parameter adjustment of the load are carried out, and the continuous tracking of the task target is carried out to realize the rapid response to the crisis on the edge side. At the same time, the composite data are downloaded to the command center. The command center performs the secondary crisis analysis and risk level determination and outputs the crisis plan deduced by the agent to realize the strategy assistance. The accuser refers to the plan strategy and issues instructions to the task computer, and the task computer receives it. Instruction and secondary adjustment and optimization of the load parameters. If there is a flight route adjustment instruction, the adjustment route will be sent to the flight controller, which greatly improves the flexibility and efficiency of handling the crisis in the UAV inspection process. By adopting this set of early warning methods, it can provide users with an updated, faster and more efficient way to realize the early warning requirements in drone inspections, which is a new breakthrough in the field of drone command methods.

An interpretable prediction method for university student academic crisis warning

Data-driven techniques improve the quality of talent training comprehensively for university by discovering potential academic problems and proposing solutions. We propose an interpretable prediction method for university student academic crisis warning, which consists of K-prototype-based student portrait construction and Catboost–SHAP-based academic achievement prediction. The academic crisis warning experiment is carried out on desensitization multi-source student data of a university. The experimental results show that the proposed method has significant advantages over common machine learning algorithms. In terms of achievement prediction, mean square error (MSE) reaches 24.976, mean absolute error (MAE) reaches 3.551, coefficient of determination (R^{2}) reaches 80.3%. The student portrait and Catboost–SHAP method are used for visual analysis of the academic achievement factors, which provide intuitive decision support and guidance assistance for education administrators.

Effects of Emergency Care-related Health Policies during the COVID-19 Pandemic in Korea: a Quasi-Experimental Study.

BackgroundThe purpose of this study was to review the nationwide emergency care-related health policies during the coronavirus disease 2019 (COVID-19) pandemic disaster in Korea and to analyze the effects of the policies on the safety of patients who visit emergency departments (EDs) during this period.MethodsThis study is a quasi-experiment study. The study population was patients who visited all 402 EDs in Korea between December 31, 2019 and May 13, 2020, using the National Emergency Department Information System (NEDIS) database. The study period was classified into 5 phases according to the level of national crisis warning of infectious disease and the implementation of emergency care-related health policies, and all study phases were 27 days. The primary outcome was in-hospital mortality, and the secondary outcome was length of stay (LOS) in the ED during the COVID-19 outbreak.ResultsThe number of ED visits during the study period was 2,636,341, and the in-hospital mortality rate was 1.4%. The number of ED visits decreased from 803,160 in phase 1 to 496,619 in phase 5 during the study period. For in-hospital mortality, the adjusted odds ratio (OR) (95% confidence interval) was 0.77 (0.74–0.79) in phase 5 compared to phase 3. Additionally, by subgroup, the ORs were 0.69 (0.57–0.83) for the patients with acute myocardial infarction and 0.76 (0.67–0.87) for severe trauma in phase 5 compared to phase 3. The ED LOS increased while the number of ED visits decreased as the COVID-19 pandemic progressed, and the ED LOS declined after policy implementation (beta coefficient: −5.3 [−6.5 to −4.2] minutes in phase 5 compared to phase 3).ConclusionImplementing appropriate emergency care policies in the COVID-19 pandemic would have contributed to improving the safety of all emergency patients and reducing in-hospital mortality by preventing excessive deaths.

Financial Crisis Warning of Financial Robot Based on Artificial Intelligence

Robotic process automation (RPA) financial robot provides a modern and intelligent tool for financial management, and financial business processing. Currently, more than 32% of financial applications are implemented by RPA financial robot. As an alternative of human in operation and judgment, the financial robot faces some inevitable risks in actual application. So far, there is a severe lack of theoretical or practical research into the risks or operational guarantees of RPA financial robot. To bridge the gap, this paper proposes a financial crisis warning model for financial robot based on artificial neural network (ANN), drawing on the merits of artificial intelligence (AI) like self-learning, self-adaptation, and self-adjustment. Specifically, a hierarchical evaluation index system (EIS) and the corresponding warning strategy were prepared for the financial crisis of RPA financial robot. Next, the financial crisis of RPA financial robot was evaluated both statically and dynamically. Then, antecedent and subsequent networks were merged into a fuzzy neural network (FNN) for predicting financial crisis of RPA financial robot. The proposed model was proved effective and accurate through experiments.

Application of Data Mining Technology in Financial Risk Analysis

Facing the cruel market competition environment, the enterprise’s demand for risk management is increasing day by day. How to objectively evaluate the financial risks existing in the process of enterprise management and how to timely warn them is the goal that the enterprise management always pursues. Enterprise financial risk analysis and early warning research is influenced by various factors inside and outside the enterprise. The results show that the uncertainty of the technology is very high, and the excellent performance of data mining technology in the study of uncertainty theory links the two closely. In addition, it also proves that the three improved algorithms of association rules greatly improve the efficiency of data mining. Meanwhile, the concept hierarchy tree model of enterprise financial risk and the financial crisis early-warning model of dynamic maintenance of time series are put forward. In conclusion, these algorithms are suitable for the research of enterprise financial risk analysis and crisis warning.

Panic, slash, or crash—Do black swans flap in stock markets?

Stock transaction data typically present a time series that exhibits a somewhat confusing trend, making it difficult to issue any form of crisis warning. This study employs Fourier spectrum analysis to clearly show manic and irrational investors chasing prices. When clustering generates an enormous amount of unstable power, the result is a stock market collapsing into a danger area that can be taken as a warning signal. We thus take the Dow Jones Index as a typical stock market and employ daily data from 1994–2015. This study finds the investors’ purchasing power through certain thresholds, analyses the performance characteristics of the spectrum, and denotes when a stock market is in a most serious crisis stage and in a second most serious correction stage. The result of our study indicates that the warning signal accurately measures a stock market crash that can be applicable to the Dow Jones Index, Nasdaq Index, and Germany ADX Index and to the emerging markets of Bovespa Index (Brazil) and Shanghai Index (China). Furthermore, this study provides a quantitative reference concerning the depth of market crashes.

顶岗实习期大学生思想危机的归因分析和对策研究

顶岗实习是高职院校深化教学改革和创新人才培养方式的一项重要工作，期间学生的思想危机困扰着一线的管理者，而危机的应对和处理是否得当事关顶岗实习工作的成败。文章认为大学生的思想危机与个体、学校和企业等方面存在的问题直接相关，而有针对性的教育、组建专门的服务团队、建立相关的制度和危机预警和干预机制、采取科学的干预方法等是化解危机，保证顶岗实习顺利进行的关键。 Internship is an important task of Higher Vocational Colleges to deepen teaching reformation and innovation modes of talent cultivation. During the internship, the ideological crises of college students bother these managers who are in the frontline. Whether we can response and handle crisis properly is related to the success or failure of our internship work. According to the article, the ideological crises of students impact individuals, colleges and enterprises directly. Therefore, it would be the key of solving crises to aim at problems in education, setting up dedicated service teams, establishing the relevant system, crisis warning and intervention mechanism and adopting scientific methods for crises. All of them also make the college students healthy both in psychology and physiology and internship going smoothly.

Time varying moments, regime switch, and crisis warning: The birth–death process with changing transition probability

The sub-prime crisis in the U.S. reveals the limitation of diversification strategy based on mean–variance analysis. A regime switch and a turning point can be observed using a high moment representation and time-dependent transition probability. Up–down price movements are induced by interactions among agents, which can be described by the birth–death (BD) process. Financial instability is visible by dramatically increasing 3rd to 5th moments one-quarter before and during the crisis. The sudden rising high moments provide effective warning signals of a regime-switch or a coming crisis. The critical condition of a market breakdown can be identified from nonlinear stochastic dynamics. The master equation approach of population dynamics provides a unified theory of a calm and turbulent market.

Financial Crisis Warning Analysis for Companies Based on BP Neural Network

This paper chose 11 financial criteria based on the principle for criteria selection. Due to the relevance of criteria, this paper collected 5 common factors with the method of principal component analysis of factor. The comprehensive score of every sample is got from the score of every common factor. Considering whether enterprises are special treated as auxiliary reference, 3 ranges of score are divided into 3 financial status accordingly: health, focus, crisis, disregarding the division criteria of special treatment or otherwise.Finally, the network got trained and tested by regarding 5 common factor as input and the financial status as output. It is found that BP neural network has a good prediction ability, high accuracy and application value, which will give a great assistance to the development of capital market in our country.BP: financial crisis warning, empirical analysis, factor analysis, BP neural network.