Risk Control Model Research Articles

Load forecasting based on multi-core learning Support Vector Machine (SVM)

Abstract The development of smart grids requires enhanced data integration, robust risk assessment, and dynamic response optimization. In this paper, a multi-core learning Support Vector Machine (SVM) model is presented to improve the accuracy and efficiency of load and photovoltaic output forecasting. The model leverages kernel function optimization and parallel computing frameworks to handle large-scale data efficiently. Additionally, a comprehensive risk assessment system is developed to quantify risks such as overvoltage, undervoltage, line overload, and load loss in distribution networks. An adaptive genetic algorithm-based risk control model is also proposed, optimized in two stages—day-ahead and intra-day—to achieve minimal comprehensive risk through real-time adjustments in distributed power output and electric vehicle charging strategies. Furthermore, an integrated virtual synchronous control online verification method for source-network-load-storage is introduced, enhancing system response speed and control accuracy. These innovations collectively provide a solid theoretical foundation and technical support for the efficient and safe operation of smart grids, addressing the increasing demands of modern energy systems.

Technology Empowers Finance: Boundaries and Risks

BigTech credit has enhanced financial inclusion, but it also poses concerns with its boundaries. This article uses theoretical frameworks and numerical simulations to examine the risks and inclusiveness of technology-empowered credit services for “long-tail” clients. This research discovered that the discrepancy between the commercial boundaries of BigTech credit and the technical limitations of risk management poses a risk in BigTech credit. The expanding boundaries of BigTech’s credit business may mitigate the representativeness of the data, resulting in a systematic deviation of unclear characteristics from the training sample data, which reduces the risk-control model’s ability to identify long-tail customers and raises the risk of credit defaults. Further computer simulations validate these results and demonstrate that competition among various companies would expedite the market’s transition over the boundary in case of a capital shortage. Finally, this article proposes setting up a joint-stock social unified credit technology company with data assets as an investment to facilitate the healthy and orderly development of financial technology institutions.

Research on risk detection and management based on machine learning

With the rapid advancement in financial risk management, machine learning techniques are playing an increasingly crucial role in credit assessment and risk detection. They provide financial institutions with more scientific and precise platforms and methodologies for risk management. This paper explores various traditional machine learning methods in risk assessment, introduces the XGBoost ensemble learning method, and integrates traditional machine learning with Long Short-Term Memory (LSTM) neural networks to enhance the generalization capability of risk control and credit assessment models. This approach offers new perspectives and improvement directions for risk assessment standards and practices in the financial industry, affirming the potential application of machine learning technologies in future risk management.The results show that the random forest and decision tree have excellent accuracy and recall rates for distinguishing fraudulent transactions. After the introduction of LSTM neural networks, the accuracy and recall rates of fraudulent transaction recognition models reach around 99%, indicating that these models have good adaptability for fraud risk recognition.

Financial risk control model based on multi-swarm multi-objective root system growth algorithms

Financial risk control model based on multi-swarm multi-objective root system growth algorithms

Research on the Implementation of Financial Risk Control Models and Algorithms Based on Machine Learning

Nowadays, machine learning has been rapidly applied to the financial services industry. With the applications of machine learning, it will bring challenges to the stable development of the financial industry. This paper studies the user behavior analysis algorithm based on operator big data, and provides financial risk control mechanism for financial enterprises. Taking finance as the data collection object, in the user behavior prediction algorithm, the experiment uses the spectral clustering algorithm to cluster the non-convex data samples, and converts the samples to the Laplacian feature space. It not only reduces the dimension, but also clusters the data, and obtains the global optimal solution. The proposed algorithm is analyzed experimentally, and the tool prototype is realized. The developed gadgets have also been applied in enterprises. The research provides a method for the construction of a risk control model in the financial industry, thereby helping financial enterprises to better control the risk of lending. This paper also provides reference for the performance improvement of the model.

An analysis of risk control in the financial sector using big data technology

The rapid development of information technology has ushered in a new era of big data in the financial industry, which has provided financial institutions with a plethora of novel tools for risk management, while also playing a pivotal role in the industry's risk control landscape. This paper analyzes the public data of existing financial institutions, combines relevant literature, and employs big data technology to assess and identify risks, which aims to explore how big data technology can improve the risk management ability of the financial industry. In addition, the paper examines the challenges and problems faced by big data technology in the application of financial risk control, including data privacy and security, technology costs, and the demand for specialized talents. The research demonstrates that big data technology improves the speed and accuracy of risk identification, but also points out the challenges of data privacy and security management. Future risk control models need to better integrate big data analytics with traditional risk management methods, thus promoting the further development and application of big data technology in the field of risk control.

The Sustainability Journey of Chinese Ready-Meal Companies Going Global: Configurational Analysis Using the Technology-Organization-Environment Framework.

In the new wave of globalization, China's pre-cooked meal industry has rapidly emerged as a significant player in the food supply chain domain, owing to its convenience and diverse choices. Amidst intensifying market competition, crafting a sustainable supply chain for overseas expansion has become an indispensable core element for driving corporate internationalization. This study focuses on the sustainability generation mechanism of the overseas supply chain of Chinese pre-cooked meal A-share listed companies, employing the technology-organization-environment (TOE) framework and fuzzy-set qualitative comparative analysis (fsQCA) method. Herein, an in-depth analysis of 388 data points from 17 listed companies has been conducted. The study systematically reveals the key factors affecting the sustainability of overseas supply chains and identifies three critical sustainability generation paths: the technology-driven and norm compliance model (path 1), the market sensitivity and product innovation model (path 2), and the robust operation and risk control model (path 3). The present study not only introduces a novel perspective on the application of a TOE framework within the realms of sustainable supply chain management and environmental, social, and governance (ESG) criteria but also offers clear directions for companies to enhance sustainability in their overseas expansion process. This includes strengthening technological research and development, compliance construction, market adaptability, product diversity, infrastructure construction, and risk management. Moreover, the research findings provide valuable insights for policymakers in promoting the internationalization of the pre-cooked meal industry and enhancing industry competitiveness.

Research on Financial Risk Control Model Based on Deep Neural Network

Research on Financial Risk Control Model Based on Deep Neural Network

Credit Risk Game Analysis and Control Model of Rural Small and Micro Enterprises——Based on the perspective of green credit

RMSEs (rural micro and small enterprises) absorb the rural surplus labor force for employment and entrepreneurship, which is an important economic growth point in rural areas in the future. However, RMSEs have narrow financing channels and difficult financing problems, which hinder the development of the rural economy. If RMSEs want to develop sustainably, they need to find effective financing channels. RMSEs no longer use traditional means of financing through commercial bank loans but are looking for newer financing modes, such as online loan platforms, investors, and so on. This paper takes RMSEs as the main body, RMSEs target rural commercial banks, online loans, and investors as funding instruments, and through building a benchmark model of the evolution game between funding instruments and RMSEs, banks, based on the perspective of green credit other investors industry competition and market regulatory mechanisms and to build a control model of credit risk of RMSEs to reduce the credit risk of RMSEs.

Effects of banditry security risk on livelihood of cattle herders in Katsina State, Nigeria

Livestock enterprise is an important source of livelihood to many people in Nigeria. Vulnerability of livestock business to insecurity risk is a major threat to the livelihood of stakeholders in the livestock value chain (cattle herders and marketers). Insecurity risk among livestock herders has a ripple effect in the economy of Nigeria. Empirical information is scanty for the clarification and development in security risk control model especially with the emergence of banditry in Nigeria. This study broadly examines the effect of insecurity risk on the livelihood of livestock herders in Katsina State, Nigeria. Primary data obtained with the use of structured questionnaire from randomly selected 200 respondents were analyzed by descriptive and inferential statistical tools (mean, frequency distribution table, probability and multiple regression). The result shows that the probability of banditry attack was 20%. The major benefit derivable from livestock business by herders is income generation. The major cause of banditry insecurity was unresolved conflict between farmers and herdsmen (100%), unemployment/deliberate negative tendency of bandits to climb wealth ladder (93.5%) and corruption among government officials (93%). Test of hypothesis indicates that all the insecurity indicators (cattle rustling, theft, kidnapping and tax imposition) negatively and significantly (P < 0.05) affected livelihood capital (asset) (income savings and herd size). There are sufficient evidence to conclude that livelihood capital of cattle herders is worst hit by banditry insecurity risk in Katsina State, Nigeria. It was recommended that government should adopt amnesty policy of disarmament, reintegration and rehabilitation of repentant bandits. This study has expanded the frontier of literature of the ripple effects of banditry insecurity on cattle value chain and implications for policy options.

The Application of Big Data and AI in Risk Control Models: Safeguarding User Security

The Application of Big Data and AI in Risk Control Models: Safeguarding User Security

Risk hierarchical management and control model based on AHP-DEMATEL-cloud model

Risk hierarchical management and control model based on AHP-DEMATEL-cloud model

Assessing the Bankruptcy Risks of China's Emerging Port Industries: Modeling and Early Warning

Vigorously developing emerging marine industries are an important way for China to implement the strategy of “Sea Power Nation”, and improving the ability of port enterprises to prevent financial and tax risks is a key link in accelerating the high-quality development of the marine economy. The research objective of this paper is to construct a reasonable early warning financial model for emerging port industries in Guangdong, Hong Kong, and Macao Greater Bay Area. The research hypothesis is that the original Z-SCORE model and F-SCORE model are not able to accurately predict the financial risk of emerging marine industries. The data of typical port enterprises are utilized to compare the financial risk; after that risk assessment and early warning are carried out. This paper adopts the Delphi method to assign weights to different indicators and utilizes the Analytic Hierarchy Process method to derive a financial and tax early warning model applicable to Guangdong, Hong Kong, and Macao Greater Bay Area. The results of the study found that the traditional “Z-score model” and “F-score model” are less applicable to the emerging industries in the ports of Guangdong, Hong Kong, and Macao Greater Bay Area. This paper will construct a financial and tax risk control model corresponding to the development of port emerging industries and provide early warning when exceeding a certain threshold to help enterprises develop better. In addition, this paper also puts forward policy suggestions for risk management of emerging port industries from the aspects of system improvement and government-enterprise linkage.

How Green Credit Policy Affects Commercial Banks' Credit Risk?

The green credit policy has significantly influenced the growth of green industries in China. This study evaluates its impact on reducing bank credit risk using data from 26 Chinese banks from 2015 to 2021. The authors discovered that the policy's primary effect is linked to banks' financial leverage. Notably, green credit's influence on insolvency risk is most evident in leverage risk. However, despite governmental support for green credit collaboration, prevalent information gaps between banks and green enterprises lead to misjudgments and subsequent credit losses. To address the balance between credit risk mitigation and privacy, the authors investigated vertical joint learning for a precise risk control model grounded in commercial banks' practices. Experiments revealed that this joint model outperforms the sole “bank internal model” in presenting green credit data, underscoring the potential of machine learning to refine green credit systems and bolster banks' credit risk management.

Application of Financial Big Data Analysis Method Based on Collaborative Filtering Algorithm in Supply Chain Enterprises

At present, the financial situation of China’s supply chain finance is still relatively unstable, and there are still some problems between supply chain enterprises and banks such as asymmetric information, insufficient model innovation and high operational risks. Based on this, this paper proposes and constructs a risk control model of financial big data analysis based on collaborative filtering algorithm. The purpose of this study is to realize the resource integration of supply chain enterprises and optimize the logistics chain, financial chain and information chain through the analysis of financial big data based on collaborative filtering algorithm, provide quality services for supply chain enterprises and good support for solving the financing problems of small and medium-sized enterprises. In order to verify the feasibility of the model, an experimental analysis is carried out. The experimental results show that this model has good scalability and operability, and the algorithm itself also has good scalability. The results of empirical analysis further verify that the design method in this paper has a good recommendation effect in terms of matching degree and user satisfaction. Compared with other risk control models, it is more practical and feasible. This research has certain practical significance for the financial management of supply chain enterprises.

Retracted: Invested Costs and Risk Control Model of Social Governance Based on Fuzzy Algorithm

Retracted: Invested Costs and Risk Control Model of Social Governance Based on Fuzzy Algorithm

RETRACTED ARTICLE: Research on Financial Risk Evaluation and Control of Tourism Enterprises Based on Improved GA Algorithm

With the change and complexity of the tourism market environment, the financial risks faced by tourism enterprises are increasingly diversified. Effectively evaluating and controlling these financial risks has become the key to the development of tourism enterprises. Therefore, this study builds an accurate and real-time enterprise financial risk assessment and control model with the help of genetic algorithm. The results show that compared with other models, the maximum error value of the research model is only 0.12, and the maximum mean square error is only 0.09. The high reliability of the model is verified by simulating the data of selected tourism enterprises. After increasing the number of samples, the accuracy of the model continues to improve, and the predicted financial indicators are more in line with the actual situation. The model achieves the best results in average fitness, and the required error value is reached within 10 iterations. In the goodness of fit comparison, the goodness of fit of the training set, the test set and the verification set of the model are all over 0.7. In the empirical analysis, the ACC of the research model reached 97.4%, the accuracy rate reached 97.1%, the F1 index of the research reached 98.6%, and the other three research models were all lower than 98%. The above shows that the research model has significant advantages and can effectively evaluate and control the financial risk of tourism enterprises.

A Bibliometrics-Based Systematic Review of Safety Risk Assessment for IBS Hoisting Construction

Construction faces many safety accidents with urbanization, particularly in hoisting. However, there is a lack of systematic review studies in this area. This paper explored the factors and methods of risk assessment in hoisting for industrial building system (IBS) construction. Firstly, bibliometric analysis revealed that future research will focus on “ergonomics”, “machine learning”, “computer simulation”, and “wearable sensors”. Secondly, the previous 80 factors contributing to hoisting risks were summarized from a “human–equipment–management–material–environment” perspective, which can serve as a reference point for managers. Finally, we discussed, in-depth, the application of artificial neural networks (ANNs) and digital twins (DT). ANNs have improved the efficiency and accuracy of risk assessment. Still, they require high-quality and significant data, which traditional methods do not provide, resulting in the low accuracy of risk simulation results. DT data are emerging as an alternative, enabling stakeholders to visualize and analyze the construction process. However, DT’s interactivity, high cost, and information security need further improvement. Based on the discussion and analysis, the risk control model created in this paper guides the direction for future research.

Entrepreneurial borrowing overdue prediction based on stacking model transfer learning

PurposeBy introducing Stacking algorithm to solve the underfitting problem caused by insufficient data in traditional machine learning, this paper provides a new solution to the cold start problem of entrepreneurial borrowing risk control.Design/methodology/approachThe authors introduce semi-supervised learning and integrated learning into the field of migration learning, and innovatively propose the Stacking model migration learning, which can independently train models on entrepreneurial borrowing credit data, and then use the migration strategy itself as the learning object, and use the Stacking algorithm to combine the prediction results of the source domain model and the target domain model.FindingsThe effectiveness of the two migration learning models is evaluated with real data from an entrepreneurial borrowing. The algorithmic performance of the Stacking-based model migration learning is further improved compared to the benchmark model without migration learning techniques, with the model area under curve value rising to 0.8. Comparing the two migration learning models reveals that the model-based migration learning approach performs better. The reason for this is that the sample-based migration learning approach only eliminates the noisy samples that are relatively less similar to the entrepreneurial borrowing data. However, the calculation of similarity and the weighing of similarity are subjective, and there is no unified judgment standard and operation method, so there is no guarantee that the retained traditional credit samples have the same sample distribution and feature structure as the entrepreneurial borrowing data.Practical implicationsFrom a practical standpoint, on the one hand, it provides a new solution to the cold start problem of entrepreneurial borrowing risk control. The small number of labeled high-quality samples cannot support the learning and deployment of big data risk control models, which is the cold start problem of the entrepreneurial borrowing risk control system. By extending the training sample set with auxiliary domain data through suitable migration learning methods, the prediction performance of the model can be improved to a certain extent and more generalized laws can be learned.Originality/valueThis paper introduces the thought method of migration learning to the entrepreneurial borrowing scenario, provides a new solution to the cold start problem of the entrepreneurial borrowing risk control system and verifies the feasibility and effectiveness of the migration learning method applied in the risk control field through empirical data.

Risk and UCON-based access control model for healthcare big data

The rapid development of healthcare big data has brought certain convenience to medical research and health management, but privacy protection of healthcare big data is an issue that must be considered in the process of data application. Access control is one of the methods for privacy protection, but traditional access control models cannot adapt to the dynamic, continuous, and real-time characteristics of healthcare big data scenarios. In this paper, we propose an access control model based on risk quantification and usage control (RQ-UCON). The model adds a risk quantification module to the traditional UCON model to achieve privacy protection of medical data. This module classifies risks into direct and indirect risks and quantifies them based on the physician's visit history. The model stores the quantified risk values as subject attributes. The RQ-UCON model uses an improved Exponentially Weighted Moving Average (EWMA) and penalty factors to predict risk value and to update the risk values of the subject attributes in real-time. The RQ-UCON model uses agglomerative hierarchical clustering to cluster the risk values of physicians within the department, resulting in risk intervals for each physician's operational behavior. Each risk interval is stored as a condition in the RQ-UCON model. Finally, according to the model whether the subject attributes meet the model conditions to determine whether the subject has the corresponding access rights, and according to the risk interval to grant the subject the corresponding access rights. Through the final experiment, it can be seen that the access control model proposed in this paper has a certain control on the excessive access behavior of doctors and has a certain limitation on the privacy leakage of healthcare big data.