Risk Forecast Model Research Articles

Developing and validating clinical models to identify candidates for allergic rhinitis pre-exposure prophylaxis

Purpose Few risk-forecasting models of allergic rhinitis (AR) exist that may aid AR pre-exposure prophylaxis (PrEP) in clinical practice. Therefore, this study aimed to develop and validate an effective clinical model for identifying candidates for AR PrEP using a routine medical questionnaire. Methods This study was conducted in 10 Chinese provinces with 13 medical centers (n = 877) between 2019 and 2021. Clinical characteristics and exposure history were collected via face-to-face interviews. Well-trained physicians diagnosed patients with AR based on skin prick test results and clinical performance. The least absolute shrinkage and selection operator model was used to identify potential risk factors for AR, and the logistic regression model was used to construct the risk-forecasting model. Predictive power and model reliability were assessed using area under the receiver operating characteristic curve and calibration curves, respectively. Results This study diagnosed 625 patients with AR who had positive responses to at least one indoor or outdoor allergen and 460 to at least one outdoor pollen allergen. Two nomograms were established to identify two types of AR with various sensitization patterns. Both models had an area under curve of approximately 0.7 in the development and internal validation datasets. Additionally, our findings found good agreement for the calibration curves of both models. Conclusion Early identification of candidates for AR PrEP using routine medical information may improve the deployment of limited resources and effective health management. Our models showed good performance in predicting AR; therefore, they can serve as potential automatic screening tools to identify AR PrEP candidates.

Good risk measures, bad statistical assumptions, ugly risk forecasts

AbstractThis paper proposes the time‐heterogeneous Student's t autoregressive model as an alternative to the various volatility forecast models documented in the literature. The empirical results indicate that: (i) the proposed model has better forecasting performance than other commonly used models, and (ii) the problem of reliable risk measurement arises primarily from the model risk associated with risk forecast models rather than the particular risk measure for computing risk. Based on the results, the paper makes recommendations to regulators and practitioners.

Framework for Detecting Breast Cancer Risk Presence Using Deep Learning

Cancer is a complicated global health concern with a significant fatality rate. Breast cancer is among the leading causes of mortality each year. Advancements in prognoses have been progressively based primarily on the expression of genes, offering insight into robust and appropriate healthcare decisions, owing to the fast growth of advanced throughput sequencing techniques and the use of various deep learning approaches that have arisen in the past few years. Diagnostic-imaging disease indicators such as breast density and tissue texture are widely used by physicians and automated technology. The effective and specific identification of cancer risk presence can be used to inform tailored screening and preventive decisions. For several classifications and prediction applications, such as breast imaging, deep learning has increasingly emerged as an effective method. We present a deep learning model approach for predicting breast cancer risk primarily on this foundation. The proposed methodology is based on transfer learning using the InceptionResNetV2 deep learning model. Our experimental work on a breast cancer dataset demonstrates high model performance, with 91% accuracy. The proposed model includes risk markers that are used to improve breast cancer risk assessment scores and presents promising results compared to existing approaches. Deep learning models include risk markers that are used to improve accuracy scores. This article depicts breast cancer risk indicators, defines the proper usage, features, and limits of each risk forecasting model, and examines the increasing role of deep learning (DL) in risk detection. The proposed model could potentially be used to automate various types of medical imaging techniques.

Blockchain-Based Secure Communication of Intelligent Transportation Digital Twins System

The present work aims to improve the communication security of Internet of Vehicles (IoV) nodes in intelligent transportation through studying the safety of IoV in smart transportation based on Blockchain (BC). An IoV DTs model is built by combining big data with Digital Twins (DTs). Then, regarding the current IoV communication security issues, a secure communication architecture for the IoV system is proposed based on the immutable and trackable BC data. Besides, Wasserstein Distance Based Generative Adversarial Network (WaGAN) model constructs the IoV node risk forecast model. Because the WaGAN model calculates the loss function through Wasserstein distance, the learning rate of the model accelerates remarkably. After ten iterations, the loss rate of the WaGAN model is close to zero. Massive in-vehicle devices in IoV are connected simultaneously to the base station, causing network channel congestion. Therefore, a Group Authentication and Privacy-preserving (GAP) scheme is put forward. As users increase during authentication, the GAP scheme performs better than other authentication access schemes. In summary, the Intelligent Transportation System driven by DTs can promote intelligent transportation management. Besides, introducing BC into IoV can improve access control’s accuracy and response efficiency. The research reported here has significant value for improving the security of the information sharing of the IoV.

Research on Risk Assessment and Prediction of RMB Internationalization Based on the PCA-SA-BPNN Model.

This paper combines principal component analysis, a BP neural network, and a simulated annealing algorithm, to construct a PCA-SA-BPNN risk forecast model to evaluate and predict the RMB internationalization risk status of China. First, we analyze the risk of RMB internationalization and its transmission mechanism from the perspective of the economic characteristics of neighboring countries and trading partner countries. Second, we use the FASP index system construction method for reference to construct a forecast index system for macro- and microrisks brought about by RMB internationalization. Then, the weight of each index is determined through index common degree analysis and principal component analysis, and the risk of RMB internationalization is divided. On this basis, the risks of RMB internationalization in China from 2000 to 2019 are divided into four categories. Based on the BP neural network algorithm optimized by the simulated degradation algorithm, the PCA-SA-BPNN model of RMB internationalization risk forecast is constructed. Finally, the validity of the model is verified by experimental verification, and the risk status of RMB internationalization in 2020 is simulated and predicted. The research results show that the risk status of RMB internationalization in 2020 is basically safe, and the risks of RMB internationalization mainly come from macroeconomic growth risks and systemic risks of the financial system.

Research on Financial Risk Forecast Model of Listed Companies Based on Convolutional Neural Network

With the continuous improvement of China’s market economy, many listed companies enjoy the unlimited development opportunities brought by the market economy environment but are also threatened by various potential risks. They may be labeled “ST” at any time due to financial risks. The label may even end up in danger of delisting. Most companies encountered serious financial crises or even bankruptcies in the later period because they did not pay enough attention to the financial problems that occurred in the early stage and did not take effective measures to deal with the crisis in a timely manner. This is extremely detrimental to the subsequent development of the company. Therefore, more and more attention has been paid to the research on the financial risk status of enterprises. Therefore, on the basis of analyzing the financial information of listed companies, this article extracts the characteristics of listed companies and images them and uses convolutional neural networks to construct a financial risk prediction model to improve the accuracy of risk prediction. Specifically, this article also compares and analyzes the financial risk prediction models of different types of listed companies, optimizes the index system, and uses the convolutional neural network method to construct a targeted financial risk prediction model with data characteristics. The actual operation data and actual risk data of the listed companies are verified, proving that it has strong adaptive ability to face different types of data, strong operability, and high prediction accuracy.

Sovereign Default Forecasting in the Era of the COVID-19 Crisis

The COVID-19 crisis has revealed the economic vulnerability of various countries and, thus, has instigated the systematic exploration and forecasting of sovereign default risks. Multivariate statistical and stochastic process-based sovereign default risk forecasting has a 50-year developmental history. This article describes a continuous, non-homogeneous Markov chain method as the basis for a COVID-19-related sovereign default risk forecast model. It demonstrates the estimation of sovereign probabilities of default (PDs) over a five-year horizon period with the developed model reflecting the impact of the COVID-19 crisis. The COVID-19-adopted Markov model estimates PDs for most countries, including those that are advanced with AAA and AA ratings, to suggest that no sovereign nation’s economy is secure from the financial impact of the COVID-19 pandemic. The dynamics of the estimated PDs are indicative of contemporary evidence as experienced in the recent financial crisis. The empirical results of this article have policy implications for foreign investors, sovereign lenders, export finance institutions, foreign trade experts, risk management professionals, and policymakers in the field of finance. The developed model can be used to timely recognize potential problems with sovereign entities in the current COVID-19 crisis and to take appropriate mitigating actions.

An application of Regular Vine copula in portfolio risk forecasting: evidence from Istanbul stock exchange

<abstract> In times of financial turbulence, it is a well-documented fact that the co-movement of financial returns tends to increase leading to unexpected portfolio losses. The magnitude of the losses can severely be underestimated when the characteristics of univariate return series and the dependence structure between the returns are not represented well by a risk forecasting model. From a growing literature on the available multivariate modelling tools, this paper aims to investigate daily portfolio Value at Risk and Expected Shortfall forecasting performance of elliptical as well as Regular Vine copulas. For this purpose, return series of twelve stocks that are listed in Istanbul Stock Exchange are obtained for the period of June 2010 to December 2018. The series are modelled with univariate Generalized Auto-Regressive Conditional Heteroskedasticity models with Normal and Student's t innovations. Equally weighted portfolio returns are forecasted depending on the univariate GARCH marginals and their multivariate dependence structure. Estimated daily portfolio Value at Risk and Expected Shortfall values with varying levels are compared with the traditional Variance-Covariance and Dynamic Conditional Correlation Multivariate GARCH model estimates. While the models performed well at the Value at Risk backtests, according to the applied ES backtests R-vine copula GARCH found better at yielding more accurate Expected Shortfall forecasts. </abstract>

Assessment of Trajectories of Non-bankrupt and Bankrupt Enterprises

The aim of this study is to show how long-term trajectories of enterprises can be used to increase the forecasting horizon of bankruptcy prediction models. The author used seven popular forecasting models (two from Europe, two from Asia, two from North America and one from Latin America). These models (five multivariate discriminant analysis models and two logit models) were used to develop 17-year trajectories separately for non-bankrupt enterprises and those at risk of financial failure. Based on a sample of 200 enterprises, the author evaluated the differences between non-bankrupt and bankrupt firms in development during 17 years of activity. The long-term usability of the models was demonstrated. To date, these models have been used only to forecast bankruptcy risk in the short term (1–3 years’ prediction horizon). This paper demonstrates that these models can also serve to evaluate long-term growth and to identify the first symptoms of future bankruptcy risk many years before it actually occurs. It was proven and specified that long-term developmental differences exist between non-threatened and future insolvent companies. These studies proved that the process of going bankrupt is very long, perhaps even longer than the literature has previously demonstrated. This study is one of the first attempts in the literature globally to assess such long-term enterprise trajectories. Additionally by implementing a dynamic approach to the financial ratios in the risk-forecasting model let visualize the changes occurring in the company.

Estimating offshore exposure to oil spill impacts based on a statistical forecast model

A statistical oil spill risk forecast model in support of emergency response and environmental risk assessment is presented by combing the deterministic model, probabilistic strategy and frequency estimation. When applied to evaluate various potential spill sources (oil port, fairway, anchorage and pipeline) in the Zhoushan offshore area, the model provides the probability of slick spatial position, oil slick thickness, and exposure duration of floating slick. An oil spill risk map is generated after integrating multiple spill sources, which is a powerful tool for identifying high-risk areas and developing contingency plan. Impact scope and damage degree vary among different sources because of special local topographical, hydrological, and meteorological conditions, where generally exists high pollution intensity of point-source and wide range of line-source. Huge Changjiang River runoff prevents coastal sea in the north from being contaminated by spilled oil from the southern Zhoushan offshore area.

Криптоэкономика: пилотный анализ инвестиций в ICO-стартапы с использованием нейронных сетей

In the field of cryptoeconomics the Ethereum (Ethereum Foundation) project gave opportunity to create “own” cryptocurrency – new token based on its smart-contract platform to everyone without lowlevel programming skills. Then it became obvious that tokens could be used for crowdfunding as the Ethereum did in 2014. Unregulated and easy to access such scheme became popular among related to the blockchain tech startups. It was named Initial Coin Offering (ICO/or ITO). Despite its name, which is similar to IPO, this scheme is usually used for venture funding of a new project instead of expanding already well-established working business. The authors use machine-learning algorithms to classify ICOs and estimate ROI based on public digital data and web-sources. The goal of the research is to develop sustainable and efficient model, which will predict target profit ROI (profit trends) of ICO startup. Data collection and analysis period: Feb-Mar 2018. The prediction model and the application (service) of ICO startups’ selection are developed as the result of the study. Results. There were over 3000 samples of ICO-startups in the research dataset. After cleaning and elimination of outliers, it contained only 518. The number of samples with positive ROI (which means that these ICOs were profitable) was 234. Cross validation metric was confirmed to be accurate. The model achieved 79 % accuracy (average value). To prove this score separated prediction was executed the metrics: for test dataset AUC is 0.78; for profitable samples Precision: 0.76; Recall: 0.9 for profitable; F1-score: 0.82. Discussions. In order to achieve the objectives of this study, various IT components of the service architecture (applications) were developed to monitor, analyze and predict the risks of ICO startups. An artificial neural network was developed to solve the problem of ROI classification and prediction. The average ROI among profitable ICOS was 47 %. Taking into consideration that the crypto market is highly volatile and that there is a possibility that such investments will not bring any profit, this model of monitoring, analysis and prediction can be very valuable for the purposes of critical selection (exclusion) of a number of ICO projects from potential investment. Conclusion. The developed components can be used as a basis of monitoring service of ICO startups. The risk-forecasting model can be improved, foremost, by using the most complete (and wider) set of data. In this case, individual data collection and processing tasks can be performed manually, which will require additional resources. It should be noted that other types of neural networks can be developed for both text analysis and trading data analysis. This may lead to the logic of using a combination of models, which will potentially help to provide the most accurate predictions.

Crude oil risk forecasting: New evidence from multiscale analysis approach

Fluctuations in the crude oil price allied to risk have increased significantly over the last decade frequently varying at different risk levels. Although existing models partially predict such variations, so far, they have been unable to predict oil prices accurately in this highly volatile market. The development of an effective, predictive model has therefore become a prime objective of research in this field. Our approach, albeit based in part on previous research, develops an original methodology, in that we have created a risk forecasting model with the ability to predict oil price fluctuations caused by changes in both fundamental and transient risk factors. We achieve this by disintegrating the multi-scale risk-structure of the crude oil market using Variational Mode Decomposition. Normal and transient risk factors are then extracted from the crude oil price using Variational Mode Decomposition and modelled separately using the Quantile Regression Neural Network (QRNN) model. Both risk factors are integrated and ensembled to produce the risk estimates. We then apply our proposed risk forecasting model to predicting future downside risk level in three major crude oil markets, namely the West Taxes Intermediate (WTI), the Brent Market, and the OPEC market. The results demonstrate that our model has the ability to capture downside risk estimates with significantly improved precision, thus reducing estimation errors and increasing forecasting reliability.

Model risk of risk models

This paper evaluates the model risk of models used for forecasting systemic and market risk. Model risk, which is the potential for different models to provide inconsistent outcomes, is shown to be increasing with market uncertainty. During calm periods, the underlying risk forecast models produce similar risk readings; hence, model risk is typically negligible. However, the disagreement between the various candidate models increases significantly during market distress, further frustrating the reliability of risk readings. Finally, particular conclusions on the underlying reasons for the high model risk and the implications for practitioners and policy makers are discussed.

Model Risk of Risk Models

This paper evaluates the model risk of models used for forecasting systemic and market risk. Model risk, which is the potential for different models to provide inconsistent outcomes, is shown to be increasing with market uncertainty. During calm periods, the underlying risk forecast models produce similar risk readings; hence, model risk is typically negligible. However, the disagreement between the various candidate models increases significantly during market distress, further frustrating the reliability of risk readings. Finally, particular conclusions on the underlying reasons for the high model risk and the implications for practitioners and policy makers are discussed.

The System Architecture of Smart Water Grid for Water Security

Architecture of smart water grid based on Internet of Things was proposed, mainly including hierarchy framework, technical system and function framework. The hierarchy framework is consists of real-time active sensing layer, interconnecting layer of water information interconnection layer, and smart decision layer. The technical system mainly contains the techniques,e.g.,the multi-carrier network composing and real-time transporting, intelligent storage of mass data and the seamless docking of multi-modules of the system, the coupled simulation of multi-dimensional water model, the evaluation and diagnosis of water security risk,the fast and dynamic forecasting model building of water pollution incidents, the multi-objective optimization and control technology of water quality and quantity of cascade reservoirs, the dynamic early warning technology in the unexpected water pollution incidents, the emergency disposal technology of the multi-scale, multi-type and multi-objective unexpected water pollution incidents. The functions framework includes the modules, e.g., intelligent sensing, intelligent simulation, intelligent diagnosis, intelligent early warning, and intelligent regulation, intelligent disposal, and intelligent control, et.al.

Model Risk of Risk Models

This paper evaluates the model risk of models used for forecasting systemic and market risk. Model risk, which is the potential for different models to provide inconsistent outcomes, is shown to be increasing with and caused by market uncertainty. During calm periods, the underlying risk forecast models produce similar risk readings, hence, model risk is typically negligible. However, the disagreement between the various candidate models increases significantly during market distress, with a no obvious way to identify which method is the best. Finally, we discuss the main problems in risk forecasting for macro prudential purposes and propose an evaluation criteria for such models.

Establishment and Application of Risk Forecast Model of Construction Project Based upon BP Neural Network

Risk management is a kind of activity by economic unit to obtain the maximal safety guarantee at the minimal cost through the identification and measuring of risk, in which reasonable economic and technical means are defined to cope with the risk, and it is also a process of estimating, evaluating and preventing the risk. Based upon the collection and normalization of sample data, determination and training of network structure, by identifying the relationship between input and output, BP neural network establishes risk forecast model of project, then the sample is tested and risk forecast model is validated.

Model Risk of Risk Models

This paper evaluates the model risk of models used for forecasting systemic and market risk. Model risk, which is the potential for different models to provide inconsistent outcomes, is shown to be increasing with and caused by market uncertainty. During calm periods, the underlying risk forecast models produce similar risk readings hence, model risk is typically negligible. However, the disagreement between the various candidate models increases significantly during market distress, with a no obvious way to identify which method is the best. Finally, we discuss the main problems in risk forecasting for macro prudential purposes and propose an evaluation criteria for such models.

Thermal Power Financial Environment Risk Forecast Model by Combined Stock Multi-indicators Basis on RBF Neural Network

It has an important significance for thermal power industry to take analysis and forecasting financial environment risk. With the scope of this paper, a RBF neural network model focus on risk analysis was constructed, and a series of input indicator combinations designed to get more accurate predictions

A systematic approach to construct credit risk forecast models

Due to the recent growth in the consumer credit market and the consequent increase in default indices, companies are seeking to improve their credit analysis by incorporating objective procedures. Multivariate techniques have been used as an alternative to construct quantitative models for credit forecast. These techniques are based on consumer profile data and allow the identification of standards concerning default behavior. This paper presents a methodology for forecasting credit risk by using three multivariate techniques: discriminant analysis, logistic regression and neural networks. The proposed method (deemed the CRF Model) consists of six steps and is illustrated by means of a real application. An important contribution of this paper is the organization of the methodological procedures and the discussion of the decisions that should be made during the application of the model. The feasibility of the approach proposed was tested in a program for granting credit offered by a network of pharmacies. The use of the models for forecasting credit risk greatly reduces the subjectivity of the analysis, by establishing a standardized procedure that speeds up and qualifies credit analysis