Credit Scores Research Articles

Technology and Civic Virtue

Today, a major technological trend is the increasing focus on the person: technical systems personalize, customize, and tailor to the person in both beneficial and troubling ways. This trend has moved beyond the realm of commerce and has become a matter of public governance, where systems for citizen risk scoring, predictive policing, and social credit scores proliferate. What these systems have in common is that they may target the person and her ethical and political dispositions, her virtues. Virtue ethics is the most appropriate approach for evaluating the impacts of these new systems, which has translated in a revival of talk about virtue in technology ethics. Yet, the focus on individual dispositions has rightly been criticized for lacking a concern with the political collective and institutional structures. This paper advocates a new direction of research into civic virtue, which is situated in between personal dispositions and structures of governance. First, it surveys the discourse on virtue ethics of technology, emphasizing its neglect of the political dimension of impacts of emerging technologies. Second, it presents a pluralist conception of civic virtue that enables us to scrutinize the impact of technology on civic virtue on three different levels of reciprocal reputation building, the cultivation of internal goods, and excellence in the public sphere. Third, it illustrates the benefits of this conceptions by discussing some paradigmatic examples of emerging technologies that aim to cultivate civic virtue.

Application of QUBO model in credit score card combination optimization

Credit cards are a rule by which banks rate their customers. Different credit scoring cards have different thresholds, corresponding to different pass rates and bad debt rates, which have a crucial impact on the bank's revenue. To help banks choose the best combination of credit scoring cards, so as to maximize revenue. Based on the triple credit card combination strategy of the bank, this paper establishes a mathematical programming model for solving the optimal combination. Aiming at the particularity of the binary decision variables, a constraint method is proposed to transform the quartic and quartic terms in the model into quadratic terms. Then, in order to balance the relationship between the objective function and the constraint conditions, the weighted penalty coefficient is further introduced by combining the entropy weight method. The model is transformed into QUBO(quadratic unconstrained binary optimization) model, and then combined with the bank's credit score card data, the optimal combination is solved by quantum annealing algorithm and verified by experiment. The experimental results show that this method has high precision and strong applicability in solving combinatorial optimization problems.

Does Consumer Credit Precede or Follow Changes in Cognitive Impairment Among Older Adults? An Investigation in the Advanced Cognitive Training for Independent and Vital Elderly (ACTIVE) Trial.

We assessed the relationships between pre- and post-morbid consumer credit history (credit scores, debts unpaid, or in collections) and classification of mild (or greater) cognitive impairment (MCI). Generalized Estimating Equation models assessed pre-and post-morbid credit history and MCI risk among 1740 participants aged 65+ in the Advanced Cognitive Training for Independent and Vital Elderly (ACTIVE) study, linked to TransUnion consumer credit data. Each 50-point increase in credit score was associated with up to 8% lower odds of MCI in the next 3years. In contrast, new unpaid collections over doubled the odds of having MCI in the next 3years. MCI was associated with subsequent credit score declines and a 47%-71% greater risk of having a new unpaid collection in the next 4years. Credit declines may signal risk for future MCI. MCI may lead to financial challenges that warrant credit monitoring interventions for older adults.

"If I don't have credit, I don't have anything": Perspectives on the credit scoring system among mothers with low incomes.

This mixed-methods study examines consumer perspectives on the credit scoring system drawn from in-depth interviews with 72 mothers with low incomes and national survey data from the National Financial Capability Study. Interviewees express strong awareness of credit scoring and a desire to have good credit. National survey data corroborate these findings, showing that most mothers with low incomes are knowledgeable about their credit scores. They know what behaviors improve credit standing and recognize the tradeoffs between present consumption and longer-run goals. They do not reject the credit scoring system's legitimacy and seek to work within this system to pursue their financial goals, despite obstacles to success. This evidence enriches our understanding of the perspectives and values that motivate consumer financial behaviors and highlights the systemic challenges to people's financial well-being that are embedded in a seemingly widely accepted credit scoring system.

Mathematical Modeling and Analysis of Credit Scoring Using the LIME Explainer: A Comprehensive Approach

Credit scoring models serve as pivotal instruments for lenders and financial institutions, facilitating the assessment of creditworthiness. Traditional models, while instrumental, grapple with challenges related to efficiency and subjectivity. The advent of machine learning heralds a transformative era, offering data-driven solutions that transcend these limitations. This research delves into a comprehensive analysis of various machine learning algorithms, emphasizing their mathematical underpinnings and their applicability in credit score classification. A comprehensive evaluation is conducted on a range of algorithms, including logistic regression, decision trees, support vector machines, and neural networks, using publicly available credit datasets. Within the research, a unified mathematical framework is introduced, which encompasses preprocessing techniques and critical algorithms such as Particle Swarm Optimization (PSO), the Light Gradient Boosting Model, and Extreme Gradient Boosting (XGB), among others. The focal point of the investigation is the LIME (Local Interpretable Model-agnostic Explanations) explainer. This study offers a comprehensive mathematical model using the LIME explainer, shedding light on its pivotal role in elucidating the intricacies of complex machine learning models. This study’s empirical findings offer compelling evidence of the efficacy of these methodologies in credit scoring, with notable accuracies of 88.84%, 78.30%, and 77.80% for the Australian, German, and South German datasets, respectively. In summation, this research not only amplifies the significance of machine learning in credit scoring but also accentuates the importance of mathematical modeling and the LIME explainer, providing a roadmap for practitioners to navigate the evolving landscape of credit assessment.

Explainable semi-supervised AI for green performance evaluation of airport buildings

Despite the global sustainability trend, airport buildings have received limited attention regarding their environmental impact within the built environment and aviation sectors. With less than 1% of green building certifications worldwide, there is a lack of essential green performance assessment tools, including frameworks, primary datasets, and models that require less human supervision. Previous research has addressed these issues by proposing frameworks, primary datasets, and a supervised method that leverages Classification and Regression Trees. However, these methods still rely on human effort to fix credit scores and assign category weights, necessitating significant supervision from human experts. This study presents a green performance evaluation model for airport buildings using an explainable semi-supervised AI approach to reduce human dependency during the inference of green scores. Principal Component Analysis and Hierarchical Clustering algorithms (agglomerative and divisive) are employed to construct the models. The dataset's dimensionality is reduced based on metrics such as scatter coefficient, Psi Index, variation, and permutation. The cluster numbers are determined using elbow point and silhouette coefficient values, resulting in cluster initializations between 6 and 12. Performance measures, including the rand index, mean absolute error, precision, recall, F1-measure, and accuracy, are evaluated for the models. The AHC and DHC models exhibit a maximum accuracy of 74%, albeit with different cluster numbers. Consequently, models are developed with suitable cluster numbers to derive green rules with improved predictive accuracy. Each agglomerative and divisive hierarchical clustering model yields 12 practical green rules that can assist airport operators and facility managers in enhancing the green performance of their airport buildings. These explainable green rules serve as guidelines to improve airport facilities. Additionally, a web-based green rating tool is developed to demonstrate the proof-of-concept, utilizing the green rules extracted from the agglomerative model.

Desirability of outcome ranking for obstetrical trials: illustration and application to the ARRIVE trial

In randomized trials, 1 primary outcome is typically chosen to evaluate the consequences of an intervention, whereas other important outcomes are relegated to secondary outcomes. This issue is amplified for many obstetrical trials in which an intervention may have consequences for both the pregnant person and the child. In contrast, desirability of outcome ranking, a paradigm shift for the design and analysis of clinical trials based on patient-centric evaluation, allows multiple outcomes-including from >1 individual-to be considered concurrently. This study aimed to describe desirability of outcome ranking methodology tailored to obstetrical trials and to apply the methodology to maternal-perinatal paired (dyadic) outcomes in which both individuals may be affected by an intervention but may experience discordant outcomes (eg, an obstetrical intervention may improve perinatal but worsen maternal outcomes). This secondary analysis applies the desirability of outcome ranking methodology to data from the Eunice Kennedy Shriver National Institute of Child Health and Human Development Maternal-Fetal Medicine Units Network ARRIVE trial. The original analysis found no substantial difference in the primary (perinatal composite) outcome, but a decreased risk of the secondary outcome of cesarean delivery with elective induction at 39 weeks. In the present desirability-of-outcome-ranking analysis, dyadic outcomes ranging from spontaneous vaginal delivery without severe neonatal complication (most desirable) to cesarean delivery with perinatal death (least desirable) were classified into 8 categories ranked by overall desirability by experienced investigators. Distributions of the desirability of outcome ranking were compared by estimating the probability of having a more desirable dyadic outcome with elective induction at 39 weeks of gestation than with expectant management. To account for various perspectives on these outcomes, a complementary analysis, called the partial credit strategy, was used to grade outcomes on a 100-point scale and estimate the difference in overall treatment scores between groups using a t test. All 6096 participants from the trial were included. The probability of a better dyadic outcome for a randomly selected patient who was randomized to elective induction was 53% (95% confidence interval, 51-54), implying that elective induction led to a better overall outcome for the dyad when taking multiple outcomes into account concurrently. Furthermore, the desirability-of-outcome-ranking probability of averting cesarean delivery with elective induction was 52% (95% confidence interval, 51-53), which was not at the expense of an operative vaginal delivery or a poorer outcome for the perinate (ie, survival with a severe neonatal complication or perinatal death). Randomization to elective induction was also advantageous in most of the partial credit score scenarios. Desirability-of-outcome-ranking methodology is a useful tool for obstetrical trials because it provides a concurrent view of the effect of an intervention on multiple dyadic outcomes, potentially allowing for better translation of data for decision-making and person-centered care.

Eviction and Poverty in American Cities.

More than two million U.S. households have an eviction case filed against them each year. Policy makers at the federal, state, and local levels are increasingly pursuing policies to reduce the number of evictions, citing harm to tenants and high public expenditures related to homelessness. We study the consequences of eviction for tenants using newly linked administrative data from two major urban areas: Cook County (which includes Chicago) and New York City. We document that before housing court, tenants experience declines in earnings and employment and increases in financial distress and hospital visits. These pre trends pose a challenge for disentangling correlation and causation. To address this problem, we use an instrumental variables approach based on cases randomly assigned to judges of varying leniency. We find that an eviction order increases homelessness and hospital visits and reduces earnings, durable goods consumption, and access to credit in the first two years. Effects on housing and labor market outcomes are driven by effects for female and Black tenants. In the longer run, eviction increases indebtedness and reduces credit scores.

Knowledge graph driven credit risk assessment for micro, small and medium-sized enterprises

Micro, Small, and Medium-sized Enterprises (MSMEs) are essential for the growth and development of the country's economy, as they create jobs, generate income, and foster production and innovation. In recent years, credit risk assessment (CRA) has been an essential process used by financial institutions to evaluate the creditworthiness of MSMEs and determine the likelihood of default. Traditionally, CRA has relied on credit scores and financial statements, but with the advent of machine learning (ML) algorithms, lenders have a new tool at their disposal. By and large, ML algorithms are designed to classify borrowers based on their credit history and transactional data while leveraging the entity relationship involved in credit transactions. This study introduces an innovative knowledge graph-driven credit risk assessment model (RGCN-RF) based on the Relational Graph Convolutional Network (RGCN) and Random Forest (RF) algorithm. RGCN is employed to identify topological structures and relationships, which is currently nascent in traditional credit risk assessment methods. RF categorises MSMEs based on the enterprise embedding vector generated from RGCN. Extensive experimentation is conducted to assess model performance utilising the Indian MSMEs database. The balanced accuracy of 92% obtained using the RGCN-RF model demonstrates a considerable advancement over prior techniques in identifying risk-free enterprises.

Credit rating- and credit score-based carbon emission quota trading model of city dwellers

Introduction: The reduction of electricity-related carbon emissions by city dwellers (CDs) is important for China to achieve low-carbon development and sustainable energy transformation. Due to the lack of incentives for reduction, electricity-related carbon emissions from CDs are increasing year by year. To this end, this paper proposes an electricity-related carbon emission quota trading model that integrates a credit rating and credit score system, particularly for motivating CDs to actively participate in carbon emission reduction.Methods: With the history of electricity bill payment data, the density-based spatial clustering of applications with noise (DBSCAN) algorithm is used to cluster CDs, forming different clusters of CDs with different sensitivity levels to carbon emission quota prices. Thereafter, based on the total carbon emission quota and tiered electricity prices from the power company, incentive rules according to the classification result and credit scores of CDs are formulated. Under certain conditions, a leader–follower Stackelberg game between CDs and the power company is built to determine the base price of the carbon emission quota, and thereby, referring to the credit scores of CDs, floating carbon emission quota prices are offered to them in the final settlement.Results: The simulation results for an actual community in a city in China show that the proposed method can considerably reduce the carbon emissions.Discussion: The proposed credit rating and credit score system outperforms the asymmetric Nash negotiation method in terms of promoting carbon emission reduction.

A novel credit scoring system in financial institutions using artificial intelligence technology

<p>In order to evaluate a person’s or a company’s creditworthiness, financial institutions must use credit scoring. Traditional credit scoring algorithms frequently rely on manual and rule-based methods, which can be tedious and inaccurate. Recent developments in artificial intelligence (AI) technology have opened up possibilities for creating more reliable and effective credit rating systems. The data are pre-processed, including scaling using the 0–1 normalization method and resolving missing values by imputation. Information gain (IG), gain ratio (GR), and chi-square are three feature selection methodologies covered in the study. While GR normalizes IG by dividing it by the total entropy of the feature, IG quantifies the reduction in total entropy by adding a new feature. Based on chi-squared statistics, the most vital traits are determined using chi-square. This research employs different ML models to develop a hybrid model for credit score prediction. The ML algorithms support vector machine (SVM), neural networks (NNs), decision trees (DTs), random forest (RF), and logistic regression (LR) classifiers are employed here for experiments along with IG, GR, and chi-square feature selection methodologies for credit prediction over Australian and German datasets. The study offers an understanding of the decision-making process for informative characteristics and the functionality of machine learning (ML) in credit prediction tasks. The empirical analysis shows that in the case of the German dataset, the DT with GR feature selection and hyperparameter optimization outperforms SVM and NN with an accuracy of 99.78%. For the Australian dataset, SVM with GR feature selection outperforms NN and DT with an accuracy of 99.98%.</p>

Monitoring System Application for Evaluating the Performance of Lecturers and Credit Score Assessment Team for Proposing Lecturers' Functional Positions

The purpose of this study is to analyze the use of the monitoring system application for evaluating the performance of lecturers and the role of the credit score assessment team in improving the quality of services for proposing lecturers' functional positions. This research uses quantitative research with descriptive methods. This research was conducted at the Regional XIII Higher Education Service Institute. The sample consists of lecturers who have proposed a functional promotion through simonekid. The total number of subjects is 121 people. The data collection technique used a questionnaire with a Likert scale. The data analysis used descriptive statistical analysis. The result of the research is that the use of the information system application monitoring and evaluation of lecturer performance (simonekid) gets a very satisfactory number, which is more dominant, namely 42% of the total respondents. The use of the information system application for monitoring and evaluating lecturer performance (simonekid) greatly facilitates the performance of the Credit Score Assessment Team. The conclusion is that the use of an information system application for monitoring and evaluating lecturer performance (simonekid) and the role of the credit score assessment team has helped improve the quality of service for proposing the Functional Position of Lecturer in private universities at the Higher Education Service Institution Region XIII Aceh.

Crabgrass confinement: Housing and transportation challenges of low- and moderate-income suburban residents in the San Francisco Bay Area

The relationship between housing and transportation costs has been the focus of much research, with classic urban theory positing that housing costs decrease and commuting costs increase as households move away from city centers. The growing population of low and low-moderate (LMI) households in suburbs may be taking advantage of lower housing costs, though research shows that housing cost savings in suburbs are offset by higher transportation costs. Our research explores dimensions of housing and transportation cost burden on LMI households in Contra Costa County in the San Francisco Bay Area using qualitative data from online/in-person surveys (n = 208) and interviews conducted in English and Spanish (n = 25).We found that housing burden is high, suggesting that LMI households choose to live in suburbs for diverse reasons, including rising rents and other requirements (e.g., credit score, rental history) in core cities, and desire for home ownership and a safer environment for children. Yet LMI suburban residents are still vulnerable to rising rents and housing instability in suburban areas. In addition to high housing costs, transportation costs are higher in suburbs due to longer commutes and higher reliance on personal vehicles. Car access is necessary, especially for households with young children. Reliance on cars becomes an issue as LMI households often encounter maintenance issues of used cars or inability to make car payments. When faced with lack of car ownership, households rely on social networks or public transit, and in some cases, forgo trips or relinquish their vehicles entirely. The lack of quality transportation alternatives in suburban contexts, as existing public transit services have long headways and are not well-suited to serving off-peak trips between suburban areas, leaves LMI households vulnerable.

Facts in the machine: Systems of record and the performance of sociotechnical truth

AbstractInformation systems serve as the “source of truth” for much of social reality, from credit scores to eligibility for boarding an airplane to the current time. In contexts of practical consensus, the system makes it so. I label this phenomenon system‐dependent truth. This paper advances a theory of performative truthmaking, wherein the agencies of giving as and taking as produce facts and truth as relations. I introduce the term systems of record to denote information systems that contain facts rather than propositions. I develop a suitable performative approach to the phenomenon of system‐dependent truth by synthesizing John Searle's social ontology, an account of truth, facts, and social reality, with Karen Barad's agential realism, an onto‐epistemology of human and nonhuman agency. Using several specific examples drawn from travel and migration contexts, including the US government's No Fly List, I show that system‐dependent truth arises when an agent takes information from a system as fact during the performance of sociotechnical truth. I argue that the agencies of truthmaking and factmaking are a distinct form of power, that the coordination of these agencies constitutes institutional rationalities of potentially global scale, and that systems of record are therefore critical sites for justice‐oriented information studies.

Dominant Requirements for Student Graduation in the Faculty of Informatics using the C4.5 Algorithm

Graduating on time is one of the indicators in the achievement and ranking of educational institutions. The achievement of graduating on time in educational institutions is essential to balance incoming and graduating students. The problem that occurs, the attributes for graduating on time have varying weightings, so the determinants of the attributes for passing on time need to be known so that the anticipation of achieving graduation on time can be met. The purpose of this study is to find out the dominant attributes in the prediction of graduating on time for students. The attributes used are credit scores (Semester Credit Units), GPA scores (Grade Point Average), and English scores (TOEFL). The method used is the C4.5 Algorithm which is one of the classification methods in data mining. The data used was 262 data, split randomly with a composition of training and testing data of 80:20. Data is processed using the data mining process by creating decision trees. The decision tree results using the C4.5 Algorithm show that the GPA value is the most influential attribute in predicting a student's graduation time. In addition, predictions based on the decision tree of the C4.5 Algorithm with criterion = 'gini' and max_depth = 5 showed an accuracy result of 77%.

PENGEMBANGAN PROFESI SEBAGAI UPAYA PEMENUHAN ANGKA KREDIT GURU MADRASAH IBTIDAIYAH NEGERI 4 SUKOHARJO

The form of professional development carried out by teachers at Madrasah Ibtidaiyah Negeri 4 Sukoharjo as an effort to increase the value of teacher credit scores is to conduct training and mentoring on sub-elements of professional development. The forms of these activities are Workshops and Assistance in the Implementation of Classroom Action Research (PTK), Development of Learning Media and Making Innovative Works. The empowerment strategies carried out for Sukoharjo 4 State Madrasah Ibtidaiyah teachers are: 1) Workshops on implementing Classroom Action Research, Development of Learning Media and Making Innovative Works. 2) Organize activities to assist the implementation of Classroom Action Research, Development of Learning Media and Making Innovative Works. The participation method used in Community Service is Community Based Research (CBR). The survey that was delivered to 25 teachers who took part in the training showed that 80% were civil servants, namely around 20 people. This is a consideration for the selection of assisted subjects. The results of the evaluation of the community service activities carried out are: Expertise and Readiness of the Resource Persons 64% in the good category, The usefulness of the material presented is 72% in the useful category, Conformity of the implementation with the expectations of the participants 64% in the appropriate category, Guidance given is easy to understand 64% in the easy category, The need for ongoing guidance is 76% in the necessary category.

Optimization of credit scorecard combinations based on quantum annealing algorithm

With the development of the times, the usage of loan-related business is increasing. However, most of the credit score card portfolio methods used nowadays are manually designed and supplemented with computer calculations, so the bank yields are low. Therefore, it is of great interest to study the application of quantum computers in credit score card portfolio optimization for better rating of customer credit ratings. Based on the given credit score card data, a linear programming model is developed. Firstly, the data is processed into two sets of one-dimensional data by Python and the working range of the two sets of data is found. Secondly, after deriving the objective function expressions according to the given conditions, the data were visualized by building a 3D grid matrix with the pass rate and bad debt rate as the XOY plane and the final benefit to the bank as the Z axis. Subsequently, the decision variables in the linear programming model are converted into binary variables, and the original model is transformed into a QUBO model by converting the constraints into binary variables. After analyzing the QUBO model, the quantum annealing method is chosen to solve the optimal solution of the objective function. And based on this, the case of three selected credit score card combinations and any three credit score cards are considered.

Financial toxicity of hidradenitis suppurativa: A single-center experience at an urban wound-care clinic.

Hidradenitis suppurativa (HS), is a chronic inflammatory skin disorder that confers a substantial financial burden to patients. The aim of the current study was to assess the patient-reported financial impact of HS. Patients presenting to a wound center between 2010 and 2021 were retrospectively reviewed. Demographics, comorbidities, and disease characteristics were collected. The financial impact of HS was assessed via the Comprehensive Score for Financial Toxicity - Functional Assessment of Chronic Illness Therapy (COST-FACIT) version 2 and investigator-generated surveys. Of 199 patients contacted, 27.1% (n = 54) completed the survey. The majority were women (77.8%, n = 42) and had private health insurance (n = 30; 55.6%). Most patients (66.7%, n = 36) had Hurley stage III disease. Mean follow-up was 2.3 + 2.8 years. The overall COST score was 19.7 + 12.4, indicating grade 1 financial toxicity (FT). Grade 0 FT was reported in 31.5% (n = 17) of patients, grade 1 in 37.0% (n = 20), grade 2 in 27.8% (n = 15), and grade 3 in 3.7% (n = 2). The mean self-reported 12-month out-of-pocket cost and credit scores were $2250 + 3269.24 and 674.6 + 95.3, respectively. Patients with private insurance had lower FT compared with Medicaid and Medicare (p = 0.003). Higher out-of-pocket costs were positively correlated with FT (p = 0.042), while higher credit scores were negatively correlated (p = 0.003). Patients with HS lesions in three or more anatomic regions reported the highest FT (p = 0.031). HS is a debilitating skin disorder that affects the livelihood of patients in a multifaceted manner. These patient-reported outcomes highlight the impact that HS has on an individual's financial security, calling for further attention to this vulnerable population.

A Comparative Study of Deep Learning and Machine Learning Techniques in Credit Score Classification

The field of credit score classification has experienced notable progress through the introduction of deep learning (DL) and machine learning (ML) techniques, empowering financial institutions to make well-informed decisions about assessing creditworthiness. However, existing research often focuses on just a few classifiers pertaining to either ML or DL techniques, lacking a comprehensive comparative analysis between the two. This gap calls for a thorough study that evaluates and compares a wide range of ML classifiers and DL models in the context of credit scoring. Our work aims to address this limitation by presenting an extensive comparative analysis between different ML and DL approaches. We provide novel insights into the strengths and weaknesses of each model, enabling financial institutions to select the most suitable approach for their specific needs. Through conducting extensive experiments on a credit records dataset, we evaluated the accuracy, precision, recall, and F1 score of various ML classifiers, such as logistic regression, decision trees, and random forests. Additionally, we delved into the capabilities of DL models, which included multi-layer perceptron (MLP), convolutional neural networks (CNN), recurrent neural networks (RNN), and hybrid models. Our findings revealed that Random Forest achieved the highest test accuracy of 90.27, while MLP and CNN closely followed with the second-highest accuracies at 87.08 and 87.16, respectively. These results also demonstrated the potential of both MLP and CNN in credit scoring assessment. MLP's strength lies in its capacity to handle non-linear relationships between features, providing a viable alternative to decision tree-based models. On the other hand, CNN excels in capturing spatial patterns and dependencies among features, presenting a distinct advantage in credit score classification. Overall, our study presents a broad-spectrum overview of the analysis, encompassing each model's performance and effectiveness in credit score classification. The findings empower financial institutions to leverage the benefits of DL and ML techniques, optimizing their decision-making processes and enhancing risk management strategies. By selecting the most suitable credit score classification model based on the insights gained from this comparative analysis, institutions can make informed choices and effectively evaluate creditworthiness, leading to improved risk assessment and lending decisions.

Effectiveness of debt modification system in Korea

This study aims to examine the effectiveness of the debt modification system (DMS) in Korea. We find that DMS does have a positive effect in increasing the credit scores and annual income of DMS users. We also find that a debt management plan (DMP) is more effective in raising credit scores than personal rehabilitation (PR). However, the credit scores of DMS users in the first half of 2019 (551.1–626.1 points) are at a very low level, making it difficult to access low-interest unsecured loans from banks. Therefore, DMS in Kores is still insufficient to support the return of debt-ridden consumers to normal financial life and provide opportunities for a fresh start.