Using multi-state markov models to identify credit card risk

Régis, Daniel Evangelista; Artes, Rinaldo

doi:10.1590/0103-6513.160814

Cited by 7 publications

(3 citation statements)

References 23 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, the most significant risk of asset pools lies in the uncertainty of their respective returns. Drawing on the relevant design of risk and cash flow in Régis and Artes (2016), construct a cash flow model for ecological compensation projects based on a multi‐state Markov model.…”

Section: Theoretical Modelsmentioning

confidence: 99%

The way to induce asset‐backed securities participation in eco‐compensation

Zhang,

2023

Manage Decis Econ

View full text Add to dashboard Cite

By establishing an ecology compensation asset securitization project, market mechanisms can be used to regulate the interests of stakeholders in ecological conservation. Previous studies have shown that combining asset securitization with environmental protection can effectively promote the sustainable development of both economy and environment. However, there is still a lack of research on the stable mechanisms and impact of integrating ecology compensation and asset securitization. In this study, we propose a comprehensive operating model for ecology compensation asset securitization and a specific valuation framework supported by a multi‐period, multi‐state Markov model for ecology compensation asset securitization. If the project's net present value is positive, it can effectively reduce the risks of ecology compensation projects and increase the return rate of ecology compensation asset securitization projects. By employing the case study of ZhongHang ShouGang Green Energy (SZ:180801) and implementing the asset pool valuation using the multi‐state Markov model, the deviation error is 0.89%, validating the effectiveness of the model. Additionally, sensitivity analysis from simulation results indicates that changes in interest rates and default probabilities are the main factors influencing the valuation of the asset pool. After summarizing the research conclusions, relevant policy recommendations and future prospects are presented. This research aims to provide reference for the development and application of ecology compensation asset securitization.

show abstract

Section: Theoretical Modelsmentioning

confidence: 99%

The way to induce asset‐backed securities participation in eco‐compensation

Zhang,

2023

Manage Decis Econ

View full text Add to dashboard Cite

show abstract

“…where p kl (∆t) = P kl (Y (t + ∆t) = l |Y (t) = k, Z(t)) , is the probability of transition from state k → l during time period ∆t with time dependent covariate vector Z(t) (Andersen and Keiding, 2002;Jackson et al, 2003;Régis and Artes, 2015). Transition intensities will be modeled as a function of age, gender, and antiviral treatments (favipiravir, azitro||azax, plaquenil, hydroxychloroquine||chloroquine and other) as previously stated.…”

Section: Categoriesmentioning

confidence: 99%

The effect of antiviral treatment on SARS-CoV-2 infectious disease progression: A comparison of the multi-state models

Potas

2021

KJS publishes peer-review articles in Mathematics, Computer Sci

View full text Add to dashboard Cite

Combating SARS-CoV-2 is the first concern and goal of the whole world faced with the global health crisis. Since 2019, the SARS-CoV-2 infection (COVID-19) and even mutated infection cases have been increasing rapidly. From 2019 through 27 August 2021, a total of 214,468,601 individuals were confirmed cases of SARS-CoV-2, including 4,470,969 death toll. Some of these individuals were able to access treatment and some could not, but for a while there was complete uncertainty. It was not known whether those who accessed treatment were lucky, but treatment was based on trial and error because of this uncertainty around the world until data was collected. Therefore, the aim of this study was to model SARS-CoV-2 infectious disease progression from the date of polymerase chain reaction (PCR) test to the date of negative outcome via Bayesian multi-state model approaches considering risk factors such as gender, age, and antiviral treatment. Data from 746 inpatients were collected from August 1st until the December 1st, 2020. For the multi-state model, five various discrete states were selected according to the Republic of Turkey Ministery of Health treatment algorithm. The results showed that Bayesian multi-state models with the Weibull distributed baseline hazard function were more appropriate models in the presence of risk factors and antiviral treatment.

show abstract

“…In the early days, the main traditional credit card scoring mainly used statistical analysis methods such as Logistic Regression [5][6][7], Linear Discriminant Analysis [8], and Markov model [9]. After the continuous development of machine learning and artificial intelligence technology, many methods of machine learning and artificial intelligence have been applied to credit scoring [10][11].…”

Section: Introductionmentioning

confidence: 99%

A Credit Scoring Model Based on Integrated Mixed Sampling and Ensemble Feature Selection: RBR_XGB

Lin¹,

Lin²,

Wu³

et al. 2022

Journal of Internet Technology

View full text Add to dashboard Cite

<p>With the rapid development of the economy, financial institutions pay more and more attention to the importance of financial credit risk. The XGBoost algorithm is often used in credit scoring. However, it should be noted that XGBoost has three disadvantages when dealing with small samples of high-dimensional imbalance: (1) the model classification results are more biased towards the majority class when the XGBoost algorithm is used in training imbalanced data, this results in reduced model accuracy. (2) XGBoost algorithm is prone to overfitting in high-dimensional data because the higher the data dimension, the sparser the samples. (3) In small datasets, it is prone to form data fragmentation, resulting in reduced model accuracy. A Credit Scoring Model Based On Integrated Mixed Sampling And Ensemble Feature Selection (RBR_XGB) is proposed on the following issues in this paper. The model first aims at the model failure and overfitting problems of XGBoost in the face of highly imbalanced small samples, and uses the improved hybrid sampling algorithm combining RUS and BSMOTE1 to balance and expand the data set. For feature redundancy problems, the RFECV_XGB algorithm is used to filter features for reducing interference features. Then, considering the strength of the distinguishing ability of different models, the validation set is used to assign weights to different models, and the weighted ensemble is used to further improve the performance of the model. The experimental results show that the classification performance of the RBR_XGB algorithm for high-dimensional imbalanced small data is higher than that of the traditional XGBoost algorithm, and it can be used for commercial use. </p> <p> </p>

show abstract

Using multi-state markov models to identify credit card risk

Cited by 7 publications

References 23 publications

The way to induce asset‐backed securities participation in eco‐compensation

The way to induce asset‐backed securities participation in eco‐compensation

The effect of antiviral treatment on SARS-CoV-2 infectious disease progression: A comparison of the multi-state models

A Credit Scoring Model Based on Integrated Mixed Sampling and Ensemble Feature Selection: RBR_XGB

Contact Info

Product

Resources

About