Risk Rating Model Research Articles

A novel enterprise credit risk rating model with the perspective of multiple regulatory demands

With the number of market participants rising, the issue of contradiction between heavy supervision task and insufficient supervision resource have become increasingly urgent for regulatory authorities to consider. The credit risk rating of enterprises is therefore introduced to improve the efficiency of supervision. By analyzing the purposes of enterprise credit risk rating and the multiple demands for regulatory authorities, this paper offers a multi-classification ensemble model with hybrid decomposition strategy and two-stage multi-objective feature selection. First, an adaptive resampling technique is introduced into the hybrid decomposition strategy for multi-classification, so to appropriately allocate supervision resources in each credit risk class. Then, a two-stage multi-objective feature selection method is developed to combine the various demands of regulatory authorities for feature selection. In the first stage, results of multiple Filter feature selection methods are integrated as output to improve the performance of feature information; In the second stage, the feature information from the first stage is used as input to guide the Wrapper feature selection, which is based on the Improved Multi-objective Ant Colony Optimization. Finally, a real listed enterprise credit dataset of China is used to evaluate the performance of each module and the entire model. The empirical results show that the design of hybrid decomposition strategy and multi-objective feature selection can not only deal with the class-imbalanced problem during the decomposition process, but also take into account the balance of each demand well. More importantly, a desirable framework is set in this paper to simplify the process from imbalanced multi-classification to a balanced binary one.

Retracted: Construction and Application of the Online Finance Credit Risk Rating Model Based on the Artificial Neural Network

Retracted: Construction and Application of the Online Finance Credit Risk Rating Model Based on the Artificial Neural Network

Corporate Credit Risk Rating Model Based on Financial Big Data

In recent years, leveraging financial big data and machine learning to identify corporate risks has emerged as a crucial approach for financial risk management. This paper proposes a method based on financial big data and the LightGBM model to effectively assess corporate credit risk ratings. Feature engineering is performed on corporate financial datasets, using correlation coefficients, chi-square tests, and machine learning techniques to select essential financial indicators. Subsequently, bayesian optimization is employed for hyperparameter tuning, using the classification accuracy of high risk and highest risk categories as the objective function. This process yields a multi-classification model capable of effectively identifying corporate credit risk ratings through financial data. The results demonstrate that the model exhibits strong identification capabilities for high credit risk corporates. The model achieves the best classification performance for high-risk categories, with an accuracy of 74%. The comprehensive classification accuracy and recall rate for both high-risk and highest-risk categories reach 70%. The overall classification accuracy across all categories is approximately 64%. In summary, through judicious model selection, data preprocessing, feature selection, Bayesian parameter tuning, and the establishment of appropriate objective functions, the LightGBM model demonstrates robust performance in addressing corporate credit risk rating problems.

Analysis of prognostic biomarker models and immune microenvironment in acute myeloid leukemia by integrative bioinformatics.

Acute myeloid leukemia (AML) is a hematological cancer driven on by aberrant myeloid precursor cell proliferation and differentiation. A prognostic model was created in this study to direct therapeutic care. Differentially expressed genes (DEGs) were investigated using the RNA-seq data from the TCGA-LAML and GTEx. Weighted Gene Coexpression Network Analysis (WGCNA) examines the genes involved in cancer. Find the intersection genes and construct the PPI network to discover hub genes and remove prognosis-related genes. A nomogram was produced for predicting the prognosis of AML patients using the risk prognosis model that was constructed using COX and Lasso regression analysis. GO, KEGG, and ssGSEA analysis were used to look into its biological function. TIDE score predicts immunotherapy response. Differentially expressed gene analysis revealed 1004 genes, WGCNA analysis revealed 19,575 tumor-related genes, and 941 intersection genes in total. Twelve prognostic genes were found using the PPI network and prognostic analysis. To build a risk rating model, RPS3A and PSMA2 were examined using COX and Lasso regression analysis. The risk score was used to divide the patients into two groups, and Kaplan-Meier analysis indicated that the two groups had different overall survival rates. Univariate and multivariate COX studies demonstrated that risk score is an independent prognostic factor. According to the TIDE study, the immunotherapy response was better in the low-risk group than in the high-risk group. We eventually selected out two molecules to construct prediction models that might be used as biomarkers for predicting AML immunotherapy and prognosis.

Characterization of Fatty Acid Metabolism-Related Genes Landscape for Predicting Prognosis and Aiding Immunotherapy in Glioma Patients.

Glioma is a highly malignant brain tumor with a poor survival rate. The involvement of fatty acid metabolism in glioma was examined to find viable treatment options. The information was gathered from the Cancer Genome Atlas (TCGA) and the Chinese Glioma Genome Atlas (CGGA) databases. A prognostic signature containing fatty acid metabolism-dependent genes (FAMDs) was developed to predict glioma outcome by multivariate and most minor absolute shrinkage and selection operator (LASSO) regression analyses. In the TCGA cohort, individuals with a good score had a worse prognosis than those with a poor score, validated in the CGGA cohort. According to further research by “pRRophetic” R package, higher-risk individuals were more susceptible to crizotinib. According to a complete study of the connection between the predictive risk rating model and tumor microenvironment (TME) features, high-risk individuals were eligible for activating the immune cell-associated receptor pathway. We also discovered that anti-PD-1/PD-L1 and anti-CTLA4 immunotherapy are more effective in high-risk individuals. Furthermore, we demonstrated that CCNA2 promotes glioma proliferation, migration, and invasion and regulates macrophage polarization. Therefore, examining the fatty acid metabolism pathway aids our understanding of TME invasion properties, allowing us to develop more effective immunotherapies for glioma.

An effective credit rating method for corporate entities using machine learning

In this study we introduce a new approach to designing credit risk rating models for corporate entities. This approach allows a bank to make accurate and cost-effective rating decisions by maximizing risk-adjusted returns under model uncertainty. We propose a meta-algorithm, which exploits the ordinal information embedded in the expert-assigned credit ratings in order to accurately rank customers. Then, a costsensitive rating-assignment method is used to reduce the impact of model uncertainty on the bank’s risk-adjusted return. We provide detailed discussions on specifying the cost matrix under the Basel regulatory framework. Empirical results for North American large and medium-sized companies show strong performance from the proposed approach.

Construction and Application of the Online Finance Credit Risk Rating Model Based on the Artificial Neural Network

The low-cost, highly efficient online finance credit provides underfunded individuals and small and medium enterprises (SMEs) with an indispensable credit channel. Most of the previous studies focus on the client crediting and screening of online finance. Few have studied the risk rating under a complete credit risk management system. This paper introduces the improved neural network technology to the credit risk rating of online finance. Firstly, the study period was divided into the early phase and late phase after the launch of an online finance credit product. In the early phase, there are few manually labeled samples and many unlabeled samples. Therefore, a cold start method was designed for the credit risk rating of online finance, and the similarity and abnormality of credit default were calculated. In the late phase, there are few unlabeled samples. Hence, the backpropagation neural network (BPNN) was improved for online finance credit risk rating. Our strategy was proved valid through experiments.

Research on credit risk of commercial banks based on multiple logistic model

This paper establishes a bank credit decision-making system for small and medium-sized enterprises. This paper quantifies the risk of enterprises with existing credit records and reputation ratings and establishes a risk rating model. The specific financial situation of 123 enterprises with credit records and credit rating is quantified and a model is established. In this paper, a large number of original data are processed and integrated by EXCEL and MATLAB software to get six indexes, and then three representative principal component factors are extracted by principal component analysis, which are used as independent variables for binary Logistic regression analysis, the evaluation of whether the enterprise is in breach of contract is obtained, the default screening model is established, the grade of the enterprise in breach of contract is rated as IV, and then the enterprise without default is analyzed by multivariate ordered Logistic regression analysis. Establish a risk level refinement model to further refine the non-default corporate rating, that is, I-level, II-level and III-level.

Study on Environmental Risk Assessment and Control Countermeasures of Tailings pond in a Mountainous Area of North China

The safety and environmental accidents of the tailings pond are likely to cause pollution of surrounding soil and water bodies, and endanger the safety of life and production of surrounding residents. In this study, the analytic hierarchy process (ahp) was used to score environmental sensitivity and control mechanism reliability of tailings ponds. The environmental risk rating model was used to characterize the environmental risk rating of tailings pond. The risk level characterization and evaluation results show that the four tailings ponds were general risks to downstream residents and the environment. Suggestions on environmental risk control of the upstream tailings pond were put forward.

Quantifying risk factors associated with light-induced potato tuber greening in retail stores.

Light conditions in retail stores may contribute to potato greening. In this study, we aimed to develop a potato tuber greening risk rating model for retail stores based on light quality and intensity parameters. This was achieved by firstly exposing three potato varieties (Nicola, Maranca and Kennebec) to seven specific light wavelengths (370, 420, 450, 530, 630, 660 and 735 nm) to determine the tuber greening propensity. Detailed light quality and intensity measurements from 25 retail stores were then combined with the greening propensity data to develop a tuber greening risk rating model. Our study showed that maximum greening occurred under blue light (450 nm), while 53%, 65% and 75% less occurred under green (530 nm), red (660 nm) and orange (630 nm) light, respectively. Greening risk, which varied between stores, was found to be related to light intensity level, and partially explained potato stock loss in stores. Our results from this study suggested that other in-store management practices, including lighting duration, average potato turnover, and light protection during non-retail periods, likely influence tuber greening risk.

Metabolic syndrome predicts postoperative complications after gastrectomy in gastric cancer patients: Development of an individualized usable nomogram and rating model.

BackgroundMetabolic syndrome (MetS), a public health problem, is reportedly related to an increased risk of postoperative complications after surgery. However, whether MetS have an effect on complications after gastric cancer (GC) surgery are unknown. This study aimed to investigate the effects of preoperative MetS on complications after gastrectomy.MethodsAltogether, 718 gastric cancer patients who planned to receive radical gastrectomy between June 2014 and December 2016 were enrolled, demographic and clinicopathological characteristics were analyzed. Univariate and multivariate analyses were performed to identify potential risk factors for postoperative complications. A predictive model for postoperative complications was constructed in the form of a nomogram, and its clinical usefulness was assessed.ResultsOf the 628 patients ultimately included in the study (mean age 62.92 years, 450 men and 178 women), 84 were diagnosed with MetS preoperatively. Severe postoperative complications (Clavien‐Dindo grade ≥II) were significantly more common in patients with MetS (41.7% versus 23.7%, P < .001). Predictors of postoperative complications included MetS (odds ratio [OR] = 1.800, P = .023), age (OR = 1.418, P = .050), Charlson score (OR = 1.787, P = .004 for 1‐2 points) and anastomosis type (OR = 1.746, P = .007 for Billroth II reconstruction). The high‐risk rating had a high AUC (ROC I = 0.503, ROC Ib = 0.544, ROC IIa = 0.601, ROC IIb = 0.612, ROC IIc = 0.638, ROC III = 0.735), indicating that the risk‐rating model has good discriminative capacity and clinical usefulness.ConclusionsMetS was an independent risk factor for complications after gastrectomy. The nomogram and rating model incorporating MetS, Billroth II anastomosis, age, and Charlson score was useful for individualized prediction of postoperative complications.

Applying decision trees to establish risk rating model of breast cancer incidence based on non-genetic factors among Southwest China females

Objective: To estimate incident probability and establish risk rating model of breast cancer incidence under different combinations of non-genetic factors among Southwest China females, applying the decision trees. Methods: From 2014 to 2015, a total of 783 cases, which were pathologically diagnosed as primary breast cancer, were sequentially collected from West China Hospital of Sichuan University, Sichuan Cancer Hospital and Sichuan Province People's Hospital. 3, 879(excluding 36 samples with missing data) controls were randomly selected and matched by area of residence and age. Classification and regression tree (CART) algorithm was applied to construct breast cancer risk rating model according to non-genetic factors. 5 test sets were randomly selected for model validation. Results: BI-RADS classes, menopausal status, age, history of benign breast disease, menarche age, age of first delivery and number of live births were identified as risk factors and included in the risk rating model of breast cancer incidence. Among these factors, BI-RADS classes, menopausal status and age were the most important. The risk rating model developed were vitrificated by 5 test sets, and the average sensitivity, positive predictive value, accuracy were 95.60%, 92.26%, 97.93%, respectively. Conclusions: Breast cancer risk rating model constructed by decision trees was valid and reliable. The model could be used as the basic tool of breast cancer risk assessment among Southwest China females.

RESEARCH ON RISK CLASSIFICATION METHOD OF ASSEMBLY OCCUPANCIES

Due to the densely population and mobility characteristics of the crowd, generally accidents happened in assembly occupancies will trigger a chain reaction, and then bring heavy casualties and property loss, and result disastrous consequences. In the context of safety regulation resources limited, building risk classification system of assembly occupancies is important for "scientific predicting, and hierarchical controlling” In this paper, a software with a graphical user interface is designed using MATLAB GUI to analyze and calculate risks of stampede accident caused by gathered crowds in the video. A velocity extraction method based on cross-correlation algorithm is adopted, and the risk characteristic parameters such as velocity variance is also applied. In this way, real-time analysis and early-warning for risks of stampede accident in time and space can be achieved. Also, the algorithm is applied to the surveillance video of the stampede in Shanghai and its feasibility is proved. Empirical research shows that, the assembly occupancies risk rating model built in this paper has good effectiveness, simplicity and practicability, applies to the government safety regulation and organization safety management, and can improve the safety situation of assembly occupancies effectively.

A quantified risk-scoring system and rating model for postsurgical gastroparesis syndrome in gastric cancer patients.

The study aimed to investigate the relationship between obesity and postsurgical gastroparesis syndrome (PGS), and to construct a scoring system and a risk model to identify patients at high risk. A total of 634 patients were retrospectively analyzed. Clinical characteristics were evaluated via receiver operating characteristic (ROC) curve analysis. Logistic analysis was performed to determine the independent predictive indicators of PGS. A scoring system consisting of these indicators and a risk-rating model were constructed and evaluated via ROC curve analysis. Based on the ROC curves, the visceral fat area (VFA) cutoff value for PGS was 94.00. Logistic analysis showed that visceral obesity (VFA ≥ 94.00 cm2 ), the reconstruction technique, and tumor size were independent prognostic factors for PGS. The scoring system could predict PGS reliably with a high area under the ROC curve ([AUC] = 0.769). A high-risk rating had a high AUC (AUC I = 0.56, AUC II = 0.65, and AUC III = 0.77), indicating that the risk-rating model could effectively screen patients at high risk of PGS. Visceral obesity defined by VFA effectively predicted PGS. Our scoring system may be a reliable instrument for identifying patients most at risk of PGS.

Proposal for a new Sharīʿah risk rating approach for Islamic banks

Purpose Customers of Islamic banking industry continue to be skeptical on Sharīʿah compliance of Islamic banks despite receiving fatwa from the competent authorities. The purpose of this paper is to quantify the Sharīʿah risk taken by Islamic banks, so that customers are better informed on the level of Sharīʿah compliance that will help in removing the persistent level of skepticism toward Sharīʿah compliance. Design/methodology/approach This research has used the scorecard based modeling approach to build the Sharīʿah risk rating model, which consists of 14 factors that capture Sharīʿah risk and are grouped in 5 major areas revolving around regulatory support, quality of Sharīʿah supervision, business structure, product mix and treatment of capital adequacy ratio. The score calculated by applying the model is grouped into 4 tiers reflecting the level Sharīʿah compliance at bank as non-compliant, weak compliance, satisfactory compliance and high level of Sharīʿah compliance. Three case studies were conducted by applying the model to Islamic banks from Malaysia, Pakistan and Saudi Arabia. Findings The final Sharīʿah risk scores calculated by the model clearly differentiate the 3 banks on basis of their Sharīʿah risk. The underlying scores also highlighted the areas where banks need to improve to reduce their Sharīʿah risk. Originality/value This model can be applied by customers of Islamic banks who are interested in understanding Sharīʿah-related aspects of Islamic banking industry. This model can be applied on standalone basis or as an extension to the conventional counter party risk rating models. This model can benefit management of Islamic banks toward allocation of capital against Sharīʿah risk under Basel III, and regulators can apply the model to measure industry wide risk of Sharīʿah non-compliance.

Standardized Risk Management Procedure (SRMP) for Mini Grids Case Study: Mini-Grid Sunderbans, West Bengal, India

Rural electrification by using mini-grids has been the objective of many development policies over the past years. Most mini-grid projects turned out as failures because of poor suitability to user needs, local conditions and expectations of investors and several other risks. In order to shed light on the principles and processes involved in determining a mini-grid risk rating this paper develops and elaborates a risk rating model based on a standardized risk management procedure (SRMP). Five key criteria were outlined and explained in detail using an empirical case study on a mini-grid located in India. Ultimately, this paper aims to have shown how a methodology to achieve a risk rating for a mini-grid could be structured. In this sense a mini-grid rating is a decision supporting tool to enable sound investment decisions for debtholders and shareholders in a mini-grid and to contribute for de-risking renewable energy investments. The proposed standardized risk management procedure (SRMP) for mini grids should be considered as an educated, systematic attempt at measuring current and future development of a mini-grid's capability to fulfill future payment obligations and profitability expectations.

Feasibility Study of Credit Risk Rating Systems in Banks

Credit risk rating is an important tool used by banks to quantify risk associated with lending. Accuracy of the rating mechanism is an important aspect as it affects the nature and quality of credit decisions made. A wrong rating may affect not only the sustainability and goodwill of the banks; it can even affect the overall economic harmony and balance, as banks are barometers of the economy. Recent global economic crisis of 2008, itself showcases a need for very strict and accurate credit policy. Under this back drop, present study aims to analyze the credit risk rating mechanism of banks. A comparative study of the different risk rating models adopted by public and private banks in Thiruvananthapuram district (Kerala, India) is made and study attempts to determine the lacuna in the present risk rating model, if any. The study aims to provide suggestions to improve the credit risk management of banks.

Measuring Shar??ah Risk:Proposal for A New Shar??ah Risk Rating Model for Islamic Banks and Allocation of Capital for Shar??ah Risk under Basel III

Measuring Shar??ah Risk:Proposal for A New Shar??ah Risk Rating Model for Islamic Banks and Allocation of Capital for Shar??ah Risk under Basel III

Development of jacket platform tsunami risk rating system in waters offshore North Borneo

This work details the simulation of tsunami waves generated by seaquakes in the Manila Trench and their effect on fixed oil and gas jacket platforms in waters offshore North Borneo. For this study, a four-leg living quarter jacket platform located in a water depth of 63m is modelled in SACS v5.3. Malaysia has traditionally been perceived to be safe from the hazards of earthquakes and tsunamis. Local design practices tend to neglect tsunami waves and include no such provisions. In 2004, a 9.3M w seaquake occurred off the northwest coast of Aceh, which generated tsunami waves that caused destruction in Malaysia totalling US$ 25 million and 68 deaths. This event prompted an awareness of the need to study the reliability of fixed offshore platforms scattered throughout Malaysian waters. In this paper, we present a review of research on the seismicity of the Manila Trench, which is perceived to be high risk for Southeast Asia. From the tsunami numerical model TUNA-M2, we extract computer-simulated tsunami waves at prescribed grid points in the vicinity of the platforms in the region. Using wave heights as input, we simulate the tsunami using SACS v5.3 structural analysis software of offshore platforms, which is widely accepted by the industry. We employ the nonlinear solitary wave theory in our tsunami loading calculations for the platforms, and formulate a platform-specific risk quantification system. We then perform an intensive structural sensitivity analysis and derive a corresponding platform-specific risk rating model.

Combining market and accounting-based models for credit scoring using a classification scheme based on support vector machines

Combination of option-based model with accounting data for credit risk model.Application of market model to non-listed firms.Use of a novel additive support vector machines model. Credit risk rating is an important issue for both financial institutions and companies, especially in periods of economic recession. There are many different approaches and methods which have been developed over the years. The aim of this paper is to create a credit risk rating model, using a machine learning methodology that combines accounting data with the option-based approach of Black, Scholes, and Merton. The model is built on data for companies listed in the Greek stock exchange, but it is also shown to provide accurate results for non-listed firms as well. Linear and nonlinear support vector machines are used for model building, as well as an innovative additive modeling approach, which enables the construction of comprehensible and accurate credit scoring models.