Crisis Prediction Research Articles

Large Language Models Versus Expert Clinicians in Crisis Prediction Among Telemental Health Patients: Comparative Study.

Due to recent advances in artificial intelligence, large language models (LLMs) have emerged as a powerful tool for a variety of language-related tasks, including sentiment analysis, and summarization of provider-patient interactions. However, there is limited research on these models in the area of crisis prediction. This study aimed to evaluate the performance of LLMs, specifically OpenAI's generative pretrained transformer 4 (GPT-4), in predicting current and future mental health crisis episodes using patient-provided information at intake among users of a national telemental health platform. Deidentified patient-provided data were pulled from specific intake questions of the Brightside telehealth platform, including the chief complaint, for 140 patients who indicated suicidal ideation (SI), and another 120 patients who later indicated SI with a plan during the course of treatment. Similar data were pulled for 200 randomly selected patients, treated during the same time period, who never endorsed SI. In total, 6 senior Brightside clinicians (3 psychologists and 3 psychiatrists) were shown patients' self-reported chief complaint and self-reported suicide attempt history but were blinded to the future course of treatment and other reported symptoms, including SI. They were asked a simple yes or no question regarding their prediction of endorsement of SI with plan, along with their confidence level about the prediction. GPT-4 was provided with similar information and asked to answer the same questions, enabling us to directly compare the performance of artificial intelligence and clinicians. Overall, the clinicians' average precision (0.7) was higher than that of GPT-4 (0.6) in identifying the SI with plan at intake (n=140) versus no SI (n=200) when using the chief complaint alone, while sensitivity was higher for the GPT-4 (0.62) than the clinicians' average (0.53). The addition of suicide attempt history increased the clinicians' average sensitivity (0.59) and precision (0.77) while increasing the GPT-4 sensitivity (0.59) but decreasing the GPT-4 precision (0.54). Performance decreased comparatively when predicting future SI with plan (n=120) versus no SI (n=200) with a chief complaint only for the clinicians (average sensitivity=0.4; average precision=0.59) and the GPT-4 (sensitivity=0.46; precision=0.48). The addition of suicide attempt history increased performance comparatively for the clinicians (average sensitivity=0.46; average precision=0.69) and the GPT-4 (sensitivity=0.74; precision=0.48). GPT-4, with a simple prompt design, produced results on some metrics that approached those of a trained clinician. Additional work must be done before such a model can be piloted in a clinical setting. The model should undergo safety checks for bias, given evidence that LLMs can perpetuate the biases of the underlying data on which they are trained. We believe that LLMs hold promise for augmenting the identification of higher-risk patients at intake and potentially delivering more timely care to patients.

Advancing financial crisis prediction: Big data, AI, and economic theories

This paper explores the theoretical foundations of financial crisis early warning systems, focusing on the integration of big data, ensemble learning, and various financial crisis theories. It begins with defining key concepts such as big data, financial crisis, and ensemble learning, highlighting the evolution and significance of these terms in the context of financial crisis management. The literature review covers extensive research on financial crisis early warning indicators and models, tracing the development from traditional statistical methods to advanced artificial intelligence approaches, including neural networks, decision trees, and machine learning algorithms. The paper critically assesses the current methodologies and emphasizes the necessity of incorporating big data and machine learning for more accurate and comprehensive early warning systems. Theoretical foundations related to financial crises, such as information asymmetry, behavioral economics, economic cycle theory, and contingency theory, are discussed to understand their impact on financial crisis prediction and management. The conclusion synthesizes the findings and suggests future research directions, emphasizing the integration of diverse methodologies and interdisciplinary approaches to enhance the early warning capabilities of enterprises.

CRISIS MANAGEMENT IN THE DIGITAL AGE

This study explores the impact of digital technologies on crisis management through a qualitative analysis of secondary data, including literature, reports, and case studies. Findings reveal that social media facilitates rapid information dissemination and real-time engagement, while data analytics enable proactive monitoring and crisis prediction. The study also highlights the role of transparency in fostering public trust and the challenges posed by misinformation. The analysis includes insights from Uzbekistan's digital transformation, emphasizing the need for continuous adaptation in crisis management practices.

Crisis Management and Sustainability in Tourism Industry: Obstacles and Recovery Strategies after the COVID-19 Crisis in Antalya, Türkiye

This study aims to examine how tourism enterprises can ensure their sustainability and elude the negative effects of the COVID-19 crisis via recovery strategies through semi-structured in-depth interviews, focusing on the tourism industry in Antalya, the first and most important destination in Türkiye, in terms of arrivals and nights spent. According to the findings, travel bans and quarantine measures due to the COVID-19 pandemic had devastating effects on Antalya’s tourism sector. In fact, the COVID-19 pandemic caused a shortage of personnel in tourism industry, a persisting problem. In managing this crisis, businesses and the state have attempted various recovery strategies. Despite a recovery period since 2021, vulnerabilities in the national economy and increasing inflation rates since COVID-19 have triggered input and living costs. Furthermore, the Ukraine War has adversely affected the sustainability of tourism activities in Antalya. Moreover, due to new regulations regarding retirement in 2023, some middle-level managers in tourism sector have retired, leading to predictions of a potential crisis in upper-level management in the future. According to the study results, cooperation in tourism sector, public–private–university collaboration, and government support play significant roles in achieving full recovery from the crisis and ensuring sustainability in tourism sector activities. The study may contribute to the literature and help industry representatives and policymakers in terms of sustainability in tourism and crisis management recovery strategies.

Simulation application of sensors based on Kalman filter algorithm in student psychological crisis prediction model

The mental health and psychological crisis of some Chinese college students today are extremely abnormal, which has attracted the attention of many relevant personnel. Due to various external reasons, the psychological construction of Chinese college students is very pessimistic. Kalman filter is a regression calculation method for processing data. The standard calculation of this filter has the smallest data error, so that relevant data can be recursive. Within the relevant time domain, this calculation method can select suitable filters to accurately calculate high-dimensional and low-dimensional system data. This paper mainly solves some problems encountered, thus proving the effectiveness of Kalman filter calculation method. Finally, we can get the advantages and disadvantages of these filter systems, so as to improve these disadvantages, and finally improve the Rate of convergence of this calculation method. Through the corresponding experimental results, we can see that these calculation methods are correct. By analyzing these data, the analysis results show that this calculation method can effectively predict students' mental health problems, and the designed system can reduce the occurrence of psychological crisis events among college students.

Hypercalcemic Crisis Due to Parathyroid Adenoma Improved by Continuous Hemodialysis with a Common Calcium Concentration Dialysate: Discussion of Therapeutic Management.

A hypercalcemic crisis due to primary hyperparathyroidism is a life-threatening condition. We herein report a 71-years-old man with hypercalcemic crisis due to primary hyperparathyroidism with parathyroid adenoma. Generally, hemodialysis or continuous hemodiafiltration using calcium-free or low-calcium dialysate is performed early for hypercalcemic crisis. In this case, continuous hemodialysis with a common calcium concentration dialysate improved the hypercalcemic crisis, and parathyroidectomy was performed. The patient recovered sufficiently. Prediction of hypercalcemia crisis, appropriate introduction and methods of blood purification therapy, and timing decisions for parathyroidectomy are required for therapeutic management of hypercalcemic crisis with parathyroid adenoma.

Game Analysis of Financial Regulation in International Financial Crisis using Multi-view Graph Convolutional Network

The concept of "game analysis" generally refers to the study and assessment of video games, frequently from the viewpoints of player experience, story, mechanics, design, and other relevant variables. It can be used for a variety of games, such as sports, board, card, and video games. A sudden drop in the value of assets or financial institutions is referred to as a financial crisis. It frequently causes the regular operation of financial markets to be interrupted and may have negative impacts on the economy as a whole. In this manuscript, Game Analysis of Financial Regulation in International Financial Crisis using Multi-view Graph Convolutional Network (GA-FR-IFC-MGCN). The proposed method comprises of four phases: dataset, pre-processing, feature selection, classification. Initially, the data is taken from Analcat dataset. Then, Federated Neural Collaborative Filtering (FNCF) method is used to enhancing the networks data. For feature selection phase, the ideal features are chosen by Siberian Tiger Optimization (STO). After, the Multi-view graph convolutional network (MGCN) method is used to classifying international financial crisis as bankruptcy and Non-bankruptcy. In general, MGCN does not express some adaption of optimization strategies for determining optimal parameters to promise exact classification of International Financial Crisis. Therefore, Harbor Seal Whiskers Optimization Algorithm is proposed to enhance weight parameter of MGCN classifier, which precisely predicts the International Financial Crisis. The proposed technique is executed and efficiency of GA-FR-IFC-MGCN depend classification framework is assessed by support of numerous performances evaluating metrics likes accuracy, recall, precision, FI-score, specificity. Finally the performance of proposed GA-FR-IFC-MGCN methods provides 25.32%, 29.30% and 27.32% higher accuracy, 22.41%, 29.30% and 24.31% higher specificity and 25.71%, 27.12% and 25.31% higher precision though analyzed with existing method likes game analysis of financial supervision in international financial crisis(GA-FS-IFC), performance evaluation of clustering techniques for financial crisis prediction(PE-CT-FC) and modified grey wolf optimizer with sparse auto-encoder for financial crisis prediction in small marginal firms (MGWO-SA-FCP) respectively.

Financial Crisis Prediction and Stock Market Analysis: A Systematic Review

Abstract: It is common known that attempting to foresee the movements of the stock market is a huge task that calls for a great lot of focus and concentration. Because of this, precisely predicting stock prices might potentially result in attractive rewards if the necessary decisions are made. This is the reason why this is the case. The non-stationary, noisy, and chaotic data that is accessible makes it difficult to generate correct forecasts about the stock market. This is because accurate predictions are difficult to produce. Because of this, it is difficult for investors to generate accurate forecasts in order to invest their money and earn a return from their investments. Various strategies are developed within the framework of the existing methodologies in order to forecast stock market movements. An overview of research articles arguing for different approaches is the goal of this study. In addition to being great academic publications, these research articles provide calculation methodologies, machine learning algorithms, performance factors, and other information. To address this recognized need, this study attempts to provide a comprehensive and current evaluation of the stock market forecasting approaches now in use. This research will include the categorization, analysis, and comparison of various approaches. In the end, the process of training and testing the model is evaluated using machine learning models. Based on the data, it is abundantly evident that logistic regression is better than any other approach that is presently being used.

Assessing Machine Learning Techniques for Predicting Banking Crises in India

The historical prevalence of banking crises and their profound impact on global economies underscores the imperative for policy makers to refine their crisis forecasting frameworks. Against this backdrop, the present study endeavors to predict potential banking crises in India by leveraging a spectrum of artificial intelligence and machine learning techniques (AI-ML). These techniques encompass logistic regression, random forest, naïve Bayes, gradient boosting, support vector machine, neural networks, K-nearest neighbors, and decision trees. Initially, a banking fragility index was constructed utilizing monthly banking data spanning 2002 to 2023, demarcating the periods of crisis and stability. Subsequently, an extensive array of early warning indicators (EWIs) encompassing asset prices, macroeconomic factors, external influences, and credit-related variables were employed to forecast crisis periods. Our findings reveal that AI-ML models exhibit reasonable accuracy in predicting banking crises. Moreover, advanced model performance metrics highlight neural networks and random forest models as particularly effective in crisis prediction, surpassing other methodologies. Notably, among the EWIs, variables related to credit, interest rates, and liquidity emerge as possessing relatively higher information value in discerning fragilities within the Indian banking system. Importantly, the methodological framework presented herein can be extrapolated for banking crisis prediction in other economies.

Exploration and Practice of the Selection, Training and Management of College Psychological Friends—Take the School of Transportation, Hunan University of Technology as an Example

College students crisis occurs frequently year by year, the reason, college students themselves, weak frustration ability, lack of mental health knowledge, weak crisis identification ability, weak self-help awareness, etc. In college level, mental health, insufficient number of psychological consultants, mental health committee, peer team selection system, inadequate training, inadequate management; the above is leading to college psychological crisis prediction. At present, our school in the basis of peer members, established the peer team, the combination of two teams greatly improved the coverage of mental health work in colleges and universities, for now the construction of the team to solve the psychological problems of college students universal results, this paper in Hunan university of technology institute of transportation, for example, analysis of peer members and peer team selection, training, optimization of management ideas.

Deep learning: an study on financial crisis forewarning in small and medium-sized listed enterprises

Early warning of financial crisis will greatly promote the stable development of small and medium-sized listed enterprises (listed SMEs). In this article, 13 warning indicators were selected for financial crisis prediction from five aspects: profit level, debt service level, business level, cash level, and development level. Then, the parameters of the long short-term memory (LSTM) neural network model were optimised by the whale optimisation algorithm (WOA), resulting in the WOA-LSTM model. The WOA-LSTM model achieved an accuracy of 0.975 in predicting financial crises for listed SMEs. The performance of the WOA-LSTM model was significantly enhanced when using the filtered 13 indicators as inputs, compared to using the original 24 indicators. The findings prove the dependability of the WOA-LSTM model in warning financial crises of listed SMEs and the feasibility of its application in practice.

Mapping the knowledge structure of artificial neural network research in the stock market: a bibliometric analysis and future research pathways

PurposeIn past decades, artificial neural network (ANN) models have revolutionised various stock market operations due to their superior ability to deal with nonlinear data and garnered considerable attention from researchers worldwide. The present study aims to synthesize the research field concerning ANN applications in the stock market to a) systematically map the research trends, key contributors, scientific collaborations, and knowledge structure, and b) uncover the challenges and future research areas in the field.Design/methodology/approachTo provide a comprehensive appraisal of the extant literature, the study adopted the mixed approach of quantitative (bibliometric analysis) and qualitative (intensive review of influential articles) assessment to analyse 1,483 articles published in the Scopus and Web of Science indexed journals during 1992–2022. The bibliographic data was processed and analysed using VOSviewer and R software.FindingsThe results revealed the proliferation of articles since 2018, with China as the dominant country, Wang J as the most prolific author, “Expert Systems with Applications” as the leading journal, “computer science” as the dominant subject area, and “stock price forecasting” as the predominantly explored research theme in the field. Furthermore, “portfolio optimization”, “sentiment analysis”, “algorithmic trading”, and “crisis prediction” are found as recently emerged research areas.Originality/valueTo the best of the authors’ knowledge, the current study is a novel attempt that holistically assesses the existing literature on ANN applications throughout the entire domain of stock market. The main contribution of the current study lies in discussing the challenges along with the viable methodological solutions and providing application area-wise knowledge gaps for future studies.

Application of artificial intelligence based on sensor networks in student mental health support system and crisis prediction

The psychological health problems of students are directly related to the stability and development of society. With the development of society and the fierce competition in education, students are facing increasing psychological pressure, leading to increasingly prominent mental health problems. This not only seriously affects students' lives and studies, but also has a negative impact on the entire society. This article develops a student mental health support system based on artificial intelligence and big data analysis, through research and analysis of artificial intelligence and big data analysis. Then, based on the needs of students' mental health support and crisis prediction, corresponding algorithms and models are designed to apply artificial intelligence and big data analysis to the students' mental health support system, and relevant experiments and tests are conducted. The research results indicate that through this system, students can receive personalized mental health support and guidance, and can predict the possibility of student mental health crises. This system has achieved significant results in providing students with mental health support and predicting crises.

A Hybrid CNN and LSTM based Model for Financial Crisis Prediction

A Hybrid CNN and LSTM based Model for Financial Crisis Prediction

Early warning system for currency crises using long short‐term memory and gated recurrent unit neural networks

AbstractCurrency crises, recurrent events in the economic history of developing, emerging, and developed countries, have disastrous economic consequences. This paper proposes an early warning system for currency crises using sophisticated recurrent neural networks, such as long short‐term memory (LSTM) and gated recurrent unit (GRU). These models were initially used in language processing, where they performed well. Such models are increasingly being used in forecasting financial asset prices, including exchange rates, but they have not yet been applied to the prediction of currency crises. As for all recurrent neural networks, they allow for taking into account nonlinear interactions between variables and the influence of past data in a dynamic form. For a set of 68 countries including developed, emerging, and developing economies over the period of 1995–2020, LSTM and GRU outperformed our benchmark models. LSTM and GRU correctly sent continuous signals within a 2‐year warning window to alert for 91% of the crises. For the LSTM, false signals represent only 14% of the emitted signals compared with 23% for logistic regression, making it an efficient early warning system for policymakers.

Modeling of extended osprey optimization algorithm with Bayesian neural network: An application on Fintech to predict financial crisis

<abstract> <p>Accurately predicting and anticipating financial crises becomes of paramount importance in the rapidly evolving landscape of financial technology (Fintech). There is an increasing reliance on predictive modeling and advanced analytics techniques to predict possible crises and alleviate the effects of Fintech innovations reshaping traditional financial paradigms. Financial experts and academics are focusing more on financial risk prevention and control tools based on state-of-the-art technology such as machine learning (ML), big data, and neural networks (NN). Researchers aim to prioritize and identify the most informative variables for accurate prediction models by leveraging the abilities of deep learning and feature selection (FS) techniques. This combination of techniques allows the extraction of relationships and nuanced patterns from complex financial datasets, empowering predictive models to discern subtle signals indicative of potential crises. This study developed an extended osprey optimization algorithm with a Bayesian NN to predict financial crisis (EOOABNN-PFC) technique. The EOOABNN-PFC technique uses metaheuristics and the Bayesian model to predict the presence of a financial crisis. In preprocessing, the EOOABNN-PFC technique uses a min-max scalar to scale the input data into a valid format. Besides, the EOOABNN-PFC technique applies the EOOA-based feature subset selection approach to elect the optimal feature subset, and the prediction of the financial crisis is performed using the BNN classifier. Lastly, the optimal parameter selection of the BNN model is carried out using a multi-verse optimizer (MVO). The simulation process identified that the EOOABNN-PFC technique reaches superior accuracy outcomes of 95.00% and 95.87% compared with other existing approaches under the German Credit and Australian Credit datasets.</p> </abstract>

Jellyfish Search Algorithm Based Feature Selection with Optimal Deep Learning for Predicting Financial Crises in the Economy and Society

The financial crises has emphasized the part of financial relationship as a potential source of macroeconomic variability and systemic risk worldwide. Predicting financial crises using deep learning (DL) infers leveraging neural network (NN) to identify patterns indicative of future financial crisis and analyse complicated financial data. DL approaches such as recurrent neural network (RNN) or long short-term memory (LSTM) that process a massive quantity of past financial data such as geopolitical events, economic indicators, and market prices. These models target to identify refined connections and signals that can lead to an economic recession by learning from earlier crisis and their precursors. The problem resides in the complex and dynamic nature of financial market, demanding continuous training and modification of methods to retain significance in the aspect of developing financial condition. Although DL shows the potential to increase prediction capabilities, it's vital to accept the inherent ambiguity in financial market and the requirement for cutting-edge development of models to enhance their accuracy and reliability. This study proposes a jellyfish search algorithm based feature selection with optimum deep learning algorithm (JSAFS-ODL) for financial crisis prediction (FCP). The objective of JSAFS-ODL technique is classified the presence of financial crises or non-financial crises. To accomplish this, the JSAFS-ODL technique applies JSA based feature selection (JSA-FS) to choose an optimum set of features. Besides, RNN-GRU model can be used for the FCP. For enhancing the detection results of the RNN-GRU approach, chimp optimization algorithm (COA) can be utilized for the optimal tuning of the hyperparameters correlated to the RNN-GRU model. To guarantee the better performance of the JSAFS-ODL procedure, a series of tests were involved. The obtained values highlighted that the JSAFS-ODL technique reaches significant performance of the JSAFS-ODL technique.

Fuzzy Parameterized Single-Valued Neutrosophic Subset based Artificial Intelligence for Sustainable Financial Crisis Prediction and Green Finance

Predicting sustainable financial crises and promoting green finance are paramount in fast developing economic landscape. Leveraging advanced AI-driven technologies, such as Neutrosophic logic, enables a nuanced understanding of complex sustainability factors influencing financial markets. By incorporating these advanced technologies, organizations can proactively mitigate and identify risks related to unsustainable practices while fostering investment aligned with environmental, social, and governance (ESG) principles. This proactive stance improves financial resilience and contributes to the transition towards a resilient and more sustainable financial ecosystem. We can navigate future challenges with foresight and responsibility through the synergy of sustainable financial crisis prediction and green finance initiatives, which ensures a prosperous and environmentally conscious financial future for the generation to come. This study develops a new optimal Fuzzy Parameterized Single-Valued Neutrosophic Subset for financial crisis prediction and green finance (OFPSVNS-FCPGF) technique. The OFPSVNS-FCPGF technique intends to recognize the presence of the financial disaster in the sustainable and green finance sector. In the OFPSVNS-FCPGF technique, Z-score normalization is primarily used to measure the economic data into a beneficial layout. For the procedure of prediction, the OFPSVNS-FCPGF approach designs the FPSVNS approach which detects the occurrence of financial crises or not. Furthermore, the parameter tuning of the FPSVNS technique takes place utilizing the grasshopper optimization algorithm (GOA). To illustrate the improved FCP outcomes of the OFPSVNS-FCPGF model, a series of simulations were involved. An wide comparison study specified that the OFPSVNS-FCPGF method gains significant outcomes in the green finance sector.

Constructing the Public Opinion Crisis Prediction Model Using CNN and LSTM Techniques Based on Social Network Mining

Constructing the Public Opinion Crisis Prediction Model Using CNN and LSTM Techniques Based on Social Network Mining

Arithmetic Optimization Algorithm with Adaptive Neuro-Fuzzy Interference System for Predicting Financial Crisis

Financial technology (Fintech) is paramount in driving advanced technologies, economies, society, and several other sectors. Smart Fintech is the new-generation Fintech, primarily stimulated and endowed by compuational technology. Smart Fintech syndicates DSAI and renovates economies and finance for dynamic, smart, customized, automated services and systems, economies and financial companies, and the industry. The strength and development of the country’s economies are assessed by the correct forecasting. Financial crisis prediction (FCP) has the substantial consequence on the economies. Previous studies mainly emphasise statistical, DL, and ML methodologies for predicting the financial well-being of the business. Therefore, this article develops a new Arithmetic Optimization Algorithm with Adaptive Neuro-Fuzzy Interference System (AOA-ANFIS) technique for Predicting Financial Crisis. The presented AOA-ANFIS technique aims to predict the presence of financial crises or not. The model incorporates three major elements: Arithmetic Optimization Algorithm (AOA) for feature selection, Adaptive Neuro-Fuzzy Inference System (ANFIS) as the classification algorithm, and Bat Optimization Algorithm (BOA) for parameter tuning. The AOA feature selection model effectively detects the important attributes from a large proportion of financial indicators, augmenting the model's prediction capability while decreasing computational difficulty. Subsequently, the ANFIS classifier exploits the features selected for capturing the intricate non-linear relations intrinsic in financial data, permitting accurate crisis calculation. Additionally, the BOA parameter tuning model augments the ANFIS model's parameters, ensuring robustness and optimum performance. Experimental outcomes on varied financial databases validate the higher efficiency of the AOA-ANFIS technique over underlying processes, demonstrating its effectiveness in forecasting financial crises with great reliability and precision.