Credit Evaluation Model Research Articles

The Usage of Machine Learning Algorithms in Credit Evaluation Model

Credit scoring models are important tools for evaluating the credit status of individuals or businesses and play a significant role in the financial field. This study aims to suggest a prediction framework for credit evaluation model based on machine learning (ML) algorithms and explore the application principles and steps of combining credit scoring models, then provide an practical example to show the method for applying the model.In addition, the article also analyzes the issues that credit evaluation models should pay attention to in production practice at the end.

Measuring fairness in credit ratings

Fairness is, along with explainability, a key requirement to assess the trustworthiness of Artificial Intelligence methods that are employed for credit rating. While explainability is concerned with the capability to identify the main drivers of credit ratings, fairness evaluates how similar are credit ratings assigned to different population groups. Although explainability and fairness are strictly connected, there are no research papers that consider them jointly. We aim to fill this gap.To this purpose, we propose a general post-processing methodology for credit ratings based on machine learning models, which measures explainability, by means of the Shapley–Lorenz values of the explanatory variables, and fairness, by comparing the Shapley–Lorenz values calculated in each population group, conditionally on the explanatory variables.We experiment our approach on a credit rating model applied to a panel dataset of 119,857 credit records for approximately 20,000 small and medium-sized enterprises (SMEs), in four European countries and eleven industry sectors for the period 2015 to 2020. The obtained results indicate which are the most explainable variables and show that the credit rating model is fair, across countries and industrial sectors. However, when subsamples of smaller size are considered, the model is not fair, indicating that fairness depends on the available data.

A Deep Federated Learning-Based User Credit Evaluation Model Under Financial Internet of Things Scenarios

With the rapid development of Internet of Things (IoT) technology and the digital transformation of the financial industry, the financial IoT is becoming an important trend in the future financial field. In the era of financial IoT, a large amount of data information is recorded by sensors and devices, which poses new challenges and opportunities for user credit evaluation. In this context, conventional deep learning-based user credit evaluation methods often cannot meet privacy needs. The paper combines the privacy security ability of federated learning with deep learning, and proposes a deep federated learning-based user credit evaluation model under financial IoT scenarios. First, a particle swarm optimization-based backpropagation neural network algorithm is formulated to extract user credit evaluation features, in order to obtain user behavior patterns and credit features. Then, the XGBoost algorithm is employed to output credit evaluation results. As for the training process, the thought of federated learning is integrated to distribute the model to individual participants. In such mode, the model can be updated and trained without exposing user data to the central cloud. The experiments are conducted on real-world data to assess the proposal’s performance. The results show that the proposed credit evaluation framework can achieve better accuracy, under the guarantee of user privacy.

Stronger relationships higher risk? Credit risk evaluation based on SMEs network microstructure

Relationships between firms and between firms and financial institutions influence firms' credit risk. Thus, these relationships should be crucial considerations in credit evaluation. This paper constructs a comprehensive SME network, which integrates multiple types of inter-firm associations and considers lender-borrower relationships, and then establish credit evaluation models utilizing network microstructure and machine learning. We find that complex interfirm relationships contained in network-based features can significantly enhance the credit risk evaluation of SMEs and the predictive contribution of different levels of network structural features varies. We further find that specific network microstructures containing lender-borrower relationships tend to be associated with high defaulting probabilities. It suggests that if a SME is closely linked to microlending institutions through multiple relationships, its defaulting probability will increase.

Research on personal credit scoring model based on deep learning

The increasing integration of internet technology and the financial industry has led to the gradual replacement of traditional credit evaluation models with those based on deep learning, which have demonstrated excellent accuracy. This has become a prominent area of research. Nevertheless, the credit scoring model based on a deep neural network encounters significant challenges in terms of its applicability in the field of credit scoring, largely due to the opaque nature of its learning and decision-making processes. The application of deep learning to personal credit scoring has been shown to enhance the accuracy of the resulting scores by leveraging large amounts of data. The model employs a deep neural network (DNN) architecture that integrates multiple input features, including the user's transaction history, social behaviour and other relevant data. The model is trained using supervised learning, with a large amount of labelled data used to optimise its prediction performance. Experimental results demonstrate that the deep learning-based model exhibits a notable improvement in accuracy and robustness compared to traditional credit scoring models.

Utilizing the LightGBM algorithm for operator user credit assessment research

Mobile Internet user credit assessment is an important way for communication operators to establish decisions and formulate measures, and it is also a guarantee for operators to obtain expected benefits. However, credit evaluation methods have long been monopolized by financial industries such as banks and credit. As supporters and providers of platform network technology and network resources, communication operators are also builders and maintainers of communication networks. Internet data improves the users credit evaluation strategy. This paper uses the massive data provided by communication operators to carry out research on the operators user credit evaluation model based on the fusion LightGBM algorithm. First, for the massive data related to user evaluation provided by operators, key features are extracted by data preprocessing and feature engineering methods, and a multi-dimensional feature set with statistical significance is constructed; then, linear regression, decision tree, LightGBM, etc. The machine learning algorithm builds multiple basic models to find the best basic model; finally, integrates Averaging, Voting, Blending, Stacking and other integrated algorithms to refine multiple fusion models, and finally establish the most suitable fusion model for operator user evaluation.

Optimal structure of an expected loss credit rating model

ABSTRACT According to Basel III, expected loss is regarded as a key indicator of credit risk. In this study, we introduce an innovative expected loss credit rating model (ELCRM) using expected loss as the risk indicator and construct the ELCRM using data from peer-to-peer lending platforms. Additionally, we employ the XGBoost method to build each risk component of the ELCRM, making the XGBoost approach interpretable through the use of SHapley Additive exPlanations values, and further discuss the impact of loan variables on expected losses. We also utilize Kruskal-Wallis tests and Conover’s t-tests to demonstrate that, compared to credit rating models based on the probability of default, ELCRM possesses superior capabilities in discriminating between good and bad borrowers. Finally, we show that incorporating prepayment risk into the credit rating model significantly enhances its performance in predicting actual borrower losses.

Modelling Financial Variables Using Neural Networking to Access Creditworthiness

Abstract This study examines the existing credit rating methodology proposed in the literature to explore the development of a new credit rating model based on the financial variables of the enterprise. The focus is on the period after the financial crisis of 2018. This study aims to develop a credit rating model using neural networking and tests the same for its accuracy. The goal of this study is to address the issue brought up by previous research on subjectivity in the data used to determine creditworthiness. The database for the study includes financial data up to July 2022 from December 2018. A model is created to assess an enterprise's creditworthiness using neural networking. This study first evaluated the existing credit rating models proposed in the literature. Next, based on financial data and neural networking, a model is developed. It was evident that the model developed in this study has an accuracy of 85.16% and 76.47% on train and test data respectively. There exist several models to determine the creditworthiness of borrowers but all failed to address the concern of subjectivity in the data. The model created in this study made use of cutting-edge technology such as neural networking and financial data. This paper's unique approach and model construction based on a comparison of existing models is rare in the literature and justify the originality of this paper with a practical value at the global level.

Tác động của Thông tư 200 đến mô hình xếp hạng tín dụng sử dụng phương pháp trí tuệ nhân tạo

The study investigates the impact of Circular 200 on the credit rating model for small, medium, and large enterprises in Vietnam during the period 2008-2018, using Artificial Neural Network (ANN) methodology. The research compares credit rating models before and after the implementation of Circular 200 between 2008-2014 and 2015-2018, using data from 39,162 businesses in Vietnam obtained from the Orbis database. Results indicate that NITA, ROE, liquidity, and current payment ratio are important independent variables with significant differences in credit rating models before and after Circular 200. The research method proves useful for investors in analyzing investment risks for informed investment decisions. Vietnamese financial institutions can apply the model to identify specific credit rating issues for borrowers, enabling them to formulate appropriate credit policies and set different interest rates for varying risk levels. Future research directions include (1) enhancing data and variables, (2) improving data analysis methods, and (3) enhancing performance metrics.

Credit Evaluation Model and Its Application in Healthcare Insurance Fraud Detection

Credit Evaluation Model and Its Application in Healthcare Insurance Fraud Detection

CG-PBFT: an efficient PBFT algorithm based on credit grouping

Because of its excellent properties of fault tolerance, efficiency and availability, the practical Byzantine fault tolerance (PBFT) algorithm has become the mainstream consensus algorithm in blockchain. However, current PBFT algorithms have problems such as inadequate security of primary node selection, high communication overhead and network delay in the process of consensus. To address these problems, we design a novel efficient Byzantine fault tolerance algorithm based on credit grouping, called CG-PBFT. First, we propose a new credit evaluation model to obtain nodes’ credit values and introduce an optimized three-way quick sorting algorithm to divide nodes into the master-node group, the consensus-node group and the observation-node group, which have different privileges. The nodes in the observation-node group are restricted from participating in consensus, which reduces the communication overhead and improves consensus efficiency. Second, we propose an optimized selection method for the primary node based on a voting mechanism whereby the consensus-node group and observation-node group vote to produce the primary node, which reduces the probability of malicious nodes acting as the primary node and improves the security of primary node selection. Finally, the identity conversion mechanism between node groups is designed, and the actual behavior of nodes within different groups is given credit rewards or punishment, so as to keep an incentive for nodes to participate in appropriate system behavior and improve the working enthusiasm of nodes. The experimental simulation results show that compared with existing PBFT algorithms, the CG-PBFT algorithm improves the average throughput by 51.3% and reduces the average delay by 64.5%; it greatly improves the operating efficiency of the system and can be more suitable for application in the consortium blockchain scenarios.

Blockchain-driven framework for financing credit in small and medium-sized real estate enterprises

PurposeThis study aimed to improve the financing credit evaluation for small and medium-sized real estate enterprises (SMREEs). A financing credit evaluation model was proposed, and a blockchain-driven financing credit evaluation framework was designed to improve the transparency, credibility and applicability of the financing credit evaluation process.Design/methodology/approachThe design science research methodology was adopted to identify the main steps in constructing the financing credit model and blockchain-driven framework. The fuzzy analytic hierarchy process (FAHP)–entropy weighting method (EWM)–set pair analysis (SPA) method was used to design a financing credit evaluation model. Moreover, the proposed framework was validated using data acquired from actual cases.FindingsThe results indicate that: (1) the proposed blockchain-driven financing credit evaluation framework can effectively realize a transparent evaluation process compared to the traditional financing credit evaluation system. (2) The proposed model has high effectiveness and can achieve efficient credit ranking, reflect SMREEs' credit status and help improve credit rating.Originality/valueThis study proposes a financing credit evaluation model of SMREEs based on the FAHP–EWM–SPA method. All credit rating data and evaluation process data are immediately stored in the proposed blockchain framework, and the immutable and traceable nature of blockchain enhances trust between nodes, improving the reliability of the financing credit evaluation process and results. In addition, this study partially fulfills the lack of investigations on blockchain adoption for SMREEs' financing credit.

Logistics financial risk assessment based on decision tree algorithm model

In order to solve the financial risk problem of small and medium-sized logistics enterprises, a log algorithm is used to measure the financial risk of logistics. Combined with the actual situation of logistics finance, through the analysis of randomly selected logistics finance data, quantitatively extract important financial risk indicators, build a credit rating model based on decision tree C4.5 algorithm, and conduct empirical research on the model. The empirical results show that the quantitative financial risk indicator extraction method combined with decision tree C4.5 algorithm credit rating model has high accuracy in the evaluation of logistics finance risk. Therefore, based on the existing logistics financial risk assessment methods and models, the decision tree analysis technology is applied to analyze and make decisions on the credit status of credit applicants, and select companies with good credit, so as to reduce the financial risk of logistics enterprises and improve the efficiency of financial risk management.

Research on the Application of Cloud Computing in Enterprise Credit Rating System

At present, in the context of the "Internet+" era, cloud computing has become the basic equipment in the era of digital economy, and the increasing improvement of the big data ecosystem has laid an important foundation for the development of cloud computing, and cloud computing has also catalyzed the rapid development of big data in the application field. This paper is based on the application of cloud computing to enterprise credit rating system, that is, the collection of enterprise information and behavior information through a distributed platform; The collected data is modeled and verified through the big data mining platform; Provide cloud desktops for credit rating applications through virtualization technology; Through the exploration of credit rating theory and credit rating model development. At the same time, combined with the related technology and theoretical knowledge of cloud computing, a credit rating solution model for cloud computing is found. The cloud computing application of the credit rating system was initially realized through VMware software.

The Influences of Self-Introspection and Credit Evaluation on Self-Organized Flocking

For biological groups, the behaviors of individuals will have an impact on the alignment efficiency of the collective movement. Motivated by Vicsek’s pioneering research on self-organized particles and other related works about flocking behaviors, we propose two mathematical models based on the local information of individuals to include more realistic details in the interaction mechanism between individuals and the rest of the group during the flocking process. The local information of the individual refers to the local consistency, representing the degree of alignment with its neighbors. These two models are the self-introspection model, where the process of orientation adjustment of one individual is ruled by the degree of local consistency with the neighborhood, and the credit evaluation model, where the average orientation of the neighborhoods is weighed using the local consistency of the interacting individuals. Different metrics are calculated to analyze the effects of the model parameters and flocking parameters on groups. Simulation calculations indicate that the two improved models have certain advantages in terms of alignment efficiency for the group. Finally, the optimal model parameters are determined, and the effects of random noise on groups with a single behavior and mixed behaviors are analyzed. The results confirm that individuals with mixed behaviors still possess robustness against noise. This research would contribute to the further interdisciplinary cooperation that involves biology, ethology, and multi-agent complex systems.

A novel approach to screening patents for securitization: a machine learning-based predictive analysis of high-quality basic asset

PurposeThis paper aims to provide a complete analysis framework and prediction method for the construction of the patent securitization (PS) basic asset pool.Design/methodology/approachThis paper proposes an integrated classification method based on genetic algorithm and random forest algorithm. First, comprehensively consider the patent value evaluation model and SME credit evaluation model, determine 17 indicators to measure the patent value and SME credit; Secondly, establish the classification label of high-quality basic assets; Then, genetic algorithm and random forest model are used to predict and screen high-quality basic assets; Finally, the performance of the model is evaluated.FindingsThe machine learning model proposed in this study is mainly used to solve the screening problem of high-quality patents that constitute the underlying asset pool of PS. The empirical research shows that the integrated classification method based on genetic algorithm and random forest has good performance and prediction accuracy, and is superior to the single method that constitutes it.Originality/valueThe main contributions of the article are twofold: firstly, the machine learning model proposed in this article determines the standards for high-quality basic assets; Secondly, this article addresses the screening issue of basic assets in PS.

Enriching the green economy through sustainable investments: An ESG-based credit rating model for green financing

Environmental, social, and governance (ESG) measures have grown significantly as sustainable investment has become a key driver of capital allocation. Sustainable investment is one of the main agendas for fulfilling sustainable development. Thus, financial institutions can significantly tackle socio-ecological concerns by recognising socially conscientious borrowers for long-term investments. They can invest in or lend to enterprises involved in sustainable development to construct a sustainable future. Unfortunately, financial institutions confront several obstacles in selecting such borrowers from a large pool of applicants. To accomplish the goal of sustainable investments, this study proposes an ESG-based credit rating model that considers a firm's ESG performance. The suggested model was built by applying the fuzzy Best Worst Method (BWM) and the newly developed fuzzy Technique for Order Preferences by Similarity to an Ideal Solution (TOPSIS) Sorting. The fuzzy BWM was used to determine the weight of criteria, while the fuzzy TOPSIS-Sorting was used to evaluate firms against the identified criteria. A practical case has been demonstrated to show the utility of the proposed model. This study identifies the financial pillar as the most important, accounting for 43% of the overall importance, followed by the environmental pillar (24%), the social pillar (19%), and the governance pillar (14%). The suggested credit rating model has shown an accuracy rate of 84.31% and a true positive rate of 87.5%. Regarding policy implementations, financial institutions, regulators, and other authorities may employ it to assist sustainable investments in fulfilling sustainable development goals. Banks may use the suggested method to calculate the capital required under the internal rating-based approach of Basel norms.

Pengembangan Model Fintech-Micro BMT (FIT)

This article's goal is to create a Fintech Micro BMT (FIT) financial technology innovation model for the Islamic microfinance institution Baitul Maal wa Tamwil (BMT) at the APEX/association scale. Being a successful and independent institution (financial self-uffency) as a commercial function and assisting in reducing poverty (poverty alleviation) as a social function are the two fundamental goals of BMT. The goal of fintech micro BMT is to accomplish both objectives. Through the use of descriptive analytic techniques, the research was carried out utilizing qualitative approaches. Primary data from interviews and secondary data from literature reviews make up the utilised data. The basic prototype of the application and its features were analyzed for model innovation using the Business Model Canvas framework. This was followed by a description of the BMT and MSME simple financial reporting accounting systems as well as the credit scoring model. In order to solve the issue of liquidity gaps (mismatch), this study produced a Fintech micro BMT model that maximizes the dualities of commercial BMT functions (increasing market share) and social (ZISWAF). Business management, accounting reporting, as well as a qualified credit rating model, support these two tasks. The triple bottom line purpose of BMT—economic growth, community empowerment, and sustainability—is also embodied by fintech micro BMT. The adoption of Fintech micro BMT is anticipated to assist BMTs in expanding their role in developing the sharia microfinance network, promote cooperation among BMTs in Indonesia, boost the volume of BMT financial transactions, integrate MSME actors as recipients of ZISWAF financing and donors with BMTs, promote market transparency, and lower the risk of information asymmetry in the process of providing financing.

The Use of Artificial Intelligence in Banking Industry

Industry 4.0, also known as the fourth industrial revolution, has altered society and the economy by introducing intelligent robotics, artificial intelligence (AI), cloud computing enormous data sets, the Internet of Things (IoT), and 3D printers, among other scientific advances. To maintain competitiveness and keep up with global competition, it is vital to adapt to modern technology. The financial sector is a vibrant market with intense competition for products and services, and advancements in information technology have led to the development of highly valuable new technologies. This essay addresses the possible advantages of artificial intelligence in the banking sector. The study utilized a Systematic Literature Review (SLR) to evaluate the current literature on AI in the banking industry. The results of the SLR demonstrate that AI has been utilized in the banking industry in a variety of ways, including credit rating models and bank collapse prediction. In establishing credit card eligibility, logistic regression models were shown to be effective, with an accuracy rate of 80.43 percent. With a precision rate of 75.7% and a recall rate of 75.7%, artificial neural networks (ANNs) were shown to be the most accurate method for predicting bank collapse based on financial characteristics. Overall, the study indicates that AI has the ability to dramatically improve the banking business by enhancing efficiency, precision, and decision-making procedures. The study has limitations and potential biases, including the exclusion of non-English language articles and the possibility of a selection bias. To explore the full potential of AI in the banking business, additional study is required.

A local binary social spider algorithm for feature selection in credit scoring model

Borrowers’ default is the main risk of online lending. Using credit scoring model to assess borrowers’ credit is an important means to reduce default risk. The existing related work focus on the improvement of assessment methods, and do not study the quality of credit data enough. Actually, there are usually some noisy, redundant or irrelevant features in online credit data, which increase the computational complexity and reduce the evaluation accuracy of the model. Well-performing feature selection method is the key premise to improve accuracy of the credit evaluation model. At present, the feature selection methods applied to online credit scoring generally have shortcomings such as subjectivity, time consuming, low accuracy, etc. So it is urgent to introduce new schemes. Among the feature selection schemes in many fields, heuristic algorithm is widely recognized because of its advantages of high efficiency and accuracy, and especially BinSSA is an outstanding representative. However, BinSSA has the defects that it is easy to form extreme distribution in initialization, and is inefficient because there is a high probability of falling into local optimum during iteration. So it is still not the best choice for feature selection in online lending credit scoring model. In this paper, we propose a local binary social spider algorithm (LBSA), which introduces two local optimization strategies into BinSSA: opposition-based learning (OBL) and improved local search algorithm (ILSA). These strategies can help to improve the above defects. We conduct comparative experiments based on three typical online credit data sets and different algorithms, to verify the superior performance of LBSA. The experimental results validate that LBSA greatly reduces the redundancy of returned feature subsets, improves the iterative stability, and makes the credit scoring model more accurate and effective.