scholarly journals The Use of PCA in Reduction of Credit Scoring Modeling Variables: Evidence from Greek Banking System

2018 ◽  
Author(s):  
Panagiota Giannouli ◽  
Christos E. Kountzakis
Keyword(s):  
Logistic Regression ◽  
Principal Components ◽  
Credit Scoring ◽  
Banking System ◽  
Real Data ◽  
Categorical Variables

In this paper, we use the Principal Components Logistic Regression as a technique to reduce the variables being used in Credit Scoring Modeling. Specifically, we construct two models in which greek enterprises are classified, through their credit behavior and we evaluate them, relying on real data. In general, we propose a general way to use PC Regression, in case that we have high correlations and categorical variables in the sample.

scholarly journals Methodology for the validation of the credit scoring model of the retail portfolio

2021 ◽  
Vol 73 (7) ◽  
pp. 41-44
Author(s):  
Y.S. Zhieru
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Final Stage ◽  
Logistic Regression Model ◽  
Credit Scoring ◽  
Real Data ◽  
Scoring Model ◽  
Credit Scoring Model

The final stage of constructing a logistic regression model is checking its validity and testing it on real data. The degree of validity of a logistic regression model is evidenced by its ability to correctly classify borrowers, the model's ability to distinguish "good" borrowers from "bad" borrowers.

scholarly journals Geographically Weighted Logistic Regression Applied to Credit Scoring Models

2017 ◽  
Vol 28 (73) ◽  
pp. 93-112 ◽  
Author(s):  
Pedro Henrique Melo Albuquerque ◽  
◽  
Fabio Augusto Scalet Medina ◽  
Alan Ricardo da Silva ◽  
Keyword(s):  
Logistic Regression ◽  
Credit Risk ◽  
Predictive Power ◽  
Financial Institution ◽  
Credit Scoring ◽  
Real Data ◽  
Monetary Value ◽  
Weighted Logistic Regression ◽  
Geographically Weighted Logistic Regression ◽  
Financial Losses

Abstract This study used real data from a Brazilian financial institution on transactions involving Consumer Direct Credit (CDC), granted to clients residing in the Distrito Federal (DF), to construct credit scoring models via Logistic Regression and Geographically Weighted Logistic Regression (GWLR) techniques. The aims were: to verify whether the factors that influence credit risk differ according to the borrower’s geographic location; to compare the set of models estimated via GWLR with the global model estimated via Logistic Regression, in terms of predictive power and financial losses for the institution; and to verify the viability of using the GWLR technique to develop credit scoring models. The metrics used to compare the models developed via the two techniques were the AICc informational criterion, the accuracy of the models, the percentage of false positives, the sum of the value of false positive debt, and the expected monetary value of portfolio default compared with the monetary value of defaults observed. The models estimated for each region in the DF were distinct in their variables and coefficients (parameters), with it being concluded that credit risk was influenced differently in each region in the study. The Logistic Regression and GWLR methodologies presented very close results, in terms of predictive power and financial losses for the institution, and the study demonstrated viability in using the GWLR technique to develop credit scoring models for the target population in the study.

Regression model of assessment of customer solvency and banking risks in the process of lending

2019 ◽  
pp. 69-73
Author(s):  
Zoryna Yurynets ◽  
Rostyslav Yurynets ◽  
Nataliya Kunanets ◽  
Ivanna Myshchyshyn
Keyword(s):  
Logistic Regression ◽  
Discriminant Analysis ◽  
Regression Model ◽  
Likelihood Ratio ◽  
Credit Scoring ◽  
Bank Loans ◽  
Management Decisions ◽  
Computer Data ◽  
Proposed Model ◽  
Loan Risk

In the current conditions of economic development, it is important to pay attention to the study of the main types of risks, effective methods of evaluation, monitoring, analysis of banking risks. One of the main approaches to quantitatively assessing the creditworthiness of borrowers is credit scoring. The objective of credit scoring is to optimize management decisions regarding the possibility of providing bank loans. In the article, the scientific and methodological provisions concerning the formation of a regression model for assessing bank risks in the process of granting loans to borrowers has been proposed. The proposed model is based on the use of logistic regression tools, discriminant analysis with the use of expert evaluation. During the formation of a regression model, the relationship between risk factors and probable magnitude of loan risk has been established. In the course of calculations, the coefficient of the individual's solvency has been calculated. Direct computer data preparation, including the calculation of the indicators selected in the process of discriminant analysis, has been carried out in the Excel package environment, followed by their import into the STATISTICA package for analysis in the “Logistic regression” sub-module of the “Nonlinear evaluation” module. The adequacy of the constructed model has been determined using the Macfaden's likelihood ratio index. The calculated value of the Macfaden's likelihood ratio index indicates the adequacy of the constructed model. The ability to issue loans to new clients has been evaluated using a regression model. The conducted calculations show the possibility of granting a loan exclusively to the second and third clients. The offered method allows to conduct assessment of client's solvency and risk prevention at different stages of lending, facilitates the possibility to independently make informed decisions on credit servicing of clients and management of a loan portfolio, optimization of management decisions in banks. In order for a loan-based model to continue to perform its functions, it must be periodically adjusted.

scholarly journals Assessment of nasopharyngeal Streptococcus pneumoniae colonization does not permit discrimination between Canadian children with viral and bacterial respiratory infection: a matched-cohort cross-sectional study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jeffrey M. Pernica ◽  
Kristin Inch ◽  
Haifa Alfaraidi ◽  
Ania Van Meer ◽  
Redjana Carciumaru ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Bacterial Infection ◽  
Viral Infection ◽  
Respiratory Illness ◽  
Categorical Variables ◽  
Healthy Children ◽  
Disease Category ◽  
Pneumococcal Carriage ◽  
Colonization Patterns ◽  
Pneumococcal Colonization

Abstract Background Readily-available diagnostics do not reliably discriminate between viral and bacterial pediatric uncomplicated pneumonia, both of which are common. Some have suggested that assessment of pneumococcal carriage could be used to identify those children with bacterial pneumonia. The objective of this study was to determine if nasopharyngeal pneumococcal colonization patterns differed between children with definite viral disease, definite bacterial disease, and respiratory disease of indeterminate etiology. Methods Three groups of subjects were recruited: children with critical respiratory illness, previously healthy children with respiratory illness admitted to the ward, and previously healthy children diagnosed in the emergency department with non-severe pneumonia. Subjects were categorized as follows: a) viral infection syndrome (eg. bronchiolitis), b) bacterial infection syndrome (ie. pneumonia complicated by effusion/empyema), or c) ‘indeterminate’ pneumonia. Subjects’ nasopharyngeal swabs underwent quantitative PCR testing for S. pneumoniae. Associations between categorical variables were determined with Fisher’s exact, chi-square, or logistic regression, as appropriate. Associations between quantitative genomic load and categorical variables was determined by linear regression. Results There were 206 children in Group 1, 122 children in Group 2, and 179 children in Group 3. Only a minority (227/507, 45%) had detectable pneumococcal carriage; in those subjects, there was no association of quantitative genomic load with age, recruitment group, or disease category. In multivariate logistic regression, pneumococcal colonization > 3 log copies/mL was associated with younger age and recruitment group, but not with disease category. Conclusions The nasopharyngeal S. pneumoniae colonization patterns of subjects with definite viral infection were very similar to colonization patterns of those with definite bacterial infection or indeterminate pneumonia. Assessment and quantification of nasopharyngeal pneumococcal colonization does not therefore appear useful to discriminate between acute viral and bacterial respiratory disease; consequently, this diagnostic testing is unlikely to reliably determine which children with indeterminate pneumonia have a bacterial etiology and/or require antibiotic treatment.

P007 CROHN’S DISEASE: PREDICTORS OF HOSPITAL DISPOSITION AND COSTS USING DEMOGRAPHIC, CLINICAL, AND TREATMENT DATA

2020 ◽  
Vol 26 (Supplement_1) ◽  
pp. S48-S48
Author(s):  
Hartman Brunt ◽  
Mason Adams ◽  
Michael Barker ◽  
Diana Hamer ◽  
J C Chapman
Keyword(s):  
Logistic Regression ◽  
Crohn’S Disease ◽  
Abdominal Pain ◽  
Crohn's Disease ◽  
Hospital Admission ◽  
Categorical Variables ◽  
History Of ◽  
The Difference ◽  
The Impact ◽  
Total Charges

Abstract Purpose Crohn’s disease (CD) is an inflammatory bowel disease (IBD) caused by an abnormal immune response to intestinal microbes in a genetically susceptible host. The objective of this cohort analysis is to compare demographic characteristics, cost difference, and treatment modalities between patients who were discharged from the Emergency Department (ED) and those who were admitted to the hospital. Methods This study is a retrospective chart review of adult patients diagnosed with CD who were discharged from the ED and those who were admitted to the hospital between January 1, 2014 and January 1, 2017. We compared demographic and clinical characteristics as well as total charges incurred by these patients. A chi square test of independence and a Mann Whitney U-Test were used to compare categorical variables. Linear and logistic regression analyses were utilized to identify predictors of hospitalization and total charges. Results Of a total 195 patients, 97 were discharged from the ED and 98 were admitted to the hospital (Table 1). Patients who presented with fever, nausea/vomiting, or abdominal pain or who had a history of a fistula or stenosis were more likely to be hospitalized, as were patients who presented on steroids, 5-ASA compounds, or narcotics (Table 2). A logistic regression adjusted for these factors showed patients presenting with abdominal pain (OR=0.239, 95% CI 0.07 – 0.77) are less likely, while patients presenting with fever (OR=7.0, 95% CI 1.9 – 24.5) and history of stenosis (OR=17.8, 95% CI 5.7 – 55.9) are more likely to have a hospital admission. An increase in age and white blood cell count was associated with an increase in likelihood of admission (OR=1.04, 95% CI 1.01 – 1.07 and OR=1.2, 95% CI 1.1 – 1.4), while an increase in HGB was associated with a decrease in likelihood of admission (OR=0.682, 95% CI 0.55 – 0.83). Patients on 5-ASA compounds had the strongest association with hospital admission (OR=4.5, 95% CI 1.03 – 20.4). A linear regression analysis predicting total charges of hospitalization identified an increase of $37,500 (95% CI 6,600 – 68,489) for obese patients and of $29,000 (95% CI 20 – 57,000) for patients on narcotics prior to hospitalization. Notably, blacks were on average 6 years younger than whites (μ=36.2, st.d.=13.2 v μ=42.7, st.d.=18.2, p=0.031, respectively). No other differences in presentation or outcomes of CD were identified between these races. Conclusion This study describes the difference between CD patients who were admitted to the hospital compared to those who were discharged from the ED. The impact that 5-ASA compound, steroid, and narcotic use prior to presentation has on hospital admission and charges highlights the need for consistent outpatient care to manage the symptoms and disease progression in patients with CD in Baton Rouge. The difference in age at presentation between blacks and whites should also be considered in future research.

Abstract 395: State-Level CPR Education Legislation Associated With Higher Survival After Out-Of-Hospital Cardiac Arrest in Older Adults

Circulation ◽  
2019 ◽  
Vol 140 (Suppl_2) ◽  
Author(s):  
David G Buckler ◽  
Megan Barnes ◽  
Tyler D Alexander ◽  
Marissa Lang ◽  
Alexis M Zebrowski ◽  
...  
Keyword(s):  
Older Adults ◽  
Logistic Regression ◽  
Cardiac Arrest ◽  
State Level ◽  
Categorical Variables ◽  
Multiple Logistic Regression ◽  
Education Legislation ◽  
Chi Squared ◽  
Patient State ◽  
Hospital Cardiac Arrest

Introduction: State-level legislation requiring CPR education prior to high school graduation (CPR Legislation) is associated with an increased likelihood of community-level CPR training. CPR Legislation has also been shown to be associated with increased bystander CPR. We hypothesized that states with recent CPR Legislation would be associated with higher survival in older adults following out-of-hospital cardiac arrest (OHCA). Methods: Utilizing 2014 Medicare Claims data for emergency department (ED) visits and inpatient stays, we identified OHCA via ICD-9-CM code. CPR Legislation data was collected through online statute review. Exposure to CPR Legislation was assessed using the patient state of residence reported on the first claim. Patient dispositions were coded as home, SNF, death/hospice, rehab or other. All categories were considered survival to discharge except for death/hospice. Associations between categorical variables were assessed by chi-squared test. Multiple logistic regression was used to calculate the odds ratio associated with OHCA survival and CPR Legislation, controlling for patient age and sex. Results: In 2014, 256,277 OHCAs were identified. Mean age was 79 ±8 y, 48% were female, 23% were non-white, and survival to discharge was 22%. Prior to 2013, 4 states had passed CPR Legislation and 6 others passed legislation in 2013. These states account for 12% of OCHA for the study year. States that passed CPR Legislation in 2013 had the highest survival compared to states with earlier passage or no CPR Legislation (22.2% vs 20.6% vs. 21.8%, respectively, p < 0.001). Among those who survived to discharge, more patients were discharged home from states with 2013 CPR Legislation, than earlier or no legislation (50.8% vs. 41.3% vs. 42.8%, p <0.001). Results of the multiple logistic regression showed CPR Legislation passed in 2013 was associated with a 12% increase in the odds of survival to discharge compared to states with CPR Legislation prior to 2013 (OR: 1.12, p <0.001). Conclusion: States with CPR Legislation passed in 2013 were associated with higher survival to discharge and discharge to home, compared to earlier adopters and states with no legislation. Further work is needed to assess the mechanisms underlying this relationship.

scholarly journals Credit concession through credit scoring: Analysis and application proposal

2017 ◽  
Vol 13 (1) ◽  
pp. 51 ◽  
Author(s):  
Oriol Amat ◽  
Raffaele Manini ◽  
Marcos Antón Renart
Keyword(s):  
Financial Institutions ◽  
Design Methodology ◽  
Credit Scoring ◽  
Real Data ◽  
Statistical Techniques ◽  
Probability Of Default ◽  
Relative Importance ◽  
Linear Discriminant ◽  
Scoring Model ◽  
Credit Scoring Model

Purpose: The study herein develops and tests a credit scoring model which can help financial institutions in assessing credit requests. Design/methodology/approach: The empirical study has the objective of answering two questions: (1) Which ratios better discriminate the companies based on their being solvent or insolvent? and (2) What is the relative importance of these ratios? To do this, several statistical techniques with a multifactorial focus have been used (Multivariate Analysis of Variance, Linear Discriminant Analysis, Logit and Probit Models). Several samples of companies have been used in order to obtain and to test the model. Findings: Through the application of several statistical techniques, the credit scoring model has been proved to be effective in discriminating between good and bad creditors. Research limitations:  This study focuses on manufacturing, commercial and services companies of all sizes in Spain; Therefore, the conclusions may differ for other geographical locations.Practical implications:  Because credit is one of the main drivers of growth, a solid credit scoring model can help financial institutions assessing to whom to grant credit and to whom not to grant credit.Social implications: Because of the growing importance of credit for our society and the fear of granting it due to the latest financial turmoil, a solid credit scoring model can strengthen the trust toward the financial institutions assessment’s. Originality/value: There is already a stream of literature related to credit scoring. However, this paper focuses on Spanish firms and proves the results of our model based on real data. The application of the model to detect the probability of default in loans is original.

Physiological Exophoria Did Not Increase The Incidence of Myopia in Rural School Children in Taiwan

2021 ◽  
Author(s):  
Jui-Hung Hsu ◽  
Li-Ju Lai ◽  
Tao-Hsin Tung ◽  
Wei-Hsiu Hsu
Keyword(s):  
Elementary School ◽  
Logistic Regression ◽  
Elementary School Students ◽  
Multinomial Logistic Regression ◽  
Significant Risk ◽  
Epidemiological Data ◽  
Significant Risk Factor ◽  
Categorical Variables ◽  
School Students

Abstract Purpose:This study evaluated the incidence rate and risk factors for developing myopia in elementary school students in Chiayi, Taiwan.Methods:This prospective cohort study comprised 1816 students without myopia (grades 1 to 5 in Chiayi County). The students underwent a noncycloplegic ocular alignment examinations using an autorefractometer and completed a questionnaires at baseline and at a 1-year follow-up. A univariate logistic regression was used to assess the effects of the categorical variables on new cases of myopia. A multinomial logistic regression was then conducted. A chi-squared test was used to compare new cases of myopia in terms of ocular alignment. A Cox hazard ratio model was then used to validate factors associated with changes in ocular alignment. A P value of <.05 was considered significant.Results: In 370 participants with new cases of myopia out of 1816 participants, a spherical error of −1.51 ± 0.6 diopters was noted at follow-up. The baseline ocular alignment was not a significant risk factor for developing myopia (exophoria vs orthophoria: OR 1.26, 95% CI 0.97-1.62; other vs. orthophoria: OR 1.15, 95% CI 0.73-1.82). However, new cases of myopia (HR 1.36, 95% CI 1.14-1.61), and baseline ocular alignment (exophoria vs orthophoria: HR 3.76, 95% CI 3.20-4.42; other vs orthophoria: HR 3.02, 95% CI 2.05-4.45) were associated with exophoria at follow-up.Conclusions: This study provided epidemiological data on the incidence of myopia in elementary school students in Chiayi, Taiwan. It also demonstrated that physiological exophoria does not predispose patients to developing myopia.

Sign in / Sign up

Export Citation Format

Share Document