scholarly journals An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression

Risks ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 200
Author(s):  
Youssef Zizi ◽  
Amine Jamali-Alaoui ◽  
Badreddine El Goumi ◽  
Mohamed Oudgou ◽  
Abdeslam El Moudden
Keyword(s):  
Neural Networks ◽  
Logistic Regression ◽  
Financial Distress ◽  
Prediction Models ◽  
Type I ◽  
Return On Assets ◽  
Logistic Regression Models ◽  
The Face ◽  
One Year ◽  
Type Ii Errors

In the face of rising defaults and limited studies on the prediction of financial distress in Morocco, this article aims to determine the most relevant predictors of financial distress and identify its optimal prediction models in a normal Moroccan economic context over two years. To achieve these objectives, logistic regression and neural networks are used based on financial ratios selected by lasso and stepwise techniques. Our empirical results highlight the significant role of predictors, namely interest to sales and return on assets in predicting financial distress. The results show that logistic regression models obtained by stepwise selection outperform the other models with an overall accuracy of 93.33% two years before financial distress and 95.00% one year prior to financial distress. Results also show that our models classify distressed SMEs better than healthy SMEs with type I errors lower than type II errors.

scholarly journals Neural Networks Versus Logit Regression Model For Predicting Financial Distress Response Variables

2011 ◽  
Vol 15 (1) ◽  
pp. 21 ◽  
Author(s):  
Jozef M. Zurada ◽  
Benjamin P. Foster ◽  
Terry J. Ward ◽  
Robert M. Barker
Keyword(s):  
Neural Networks ◽  
Logistic Regression ◽  
Financial Distress ◽  
Response Variable ◽  
Logistic Regression Models ◽  
State Response ◽  
Distressed Firms ◽  
Complex Relationships ◽  
Logit Regression Model ◽  
Better Than

<span>Neural networks are designed to detect complex relationships among variables better than traditional statistical methods. Our study examined whether the complexity of the response measure impacts whether logistic regression or a neural network produces the highest classification accuracy for financially distressed firms. We compared results obtained from the two methods for a four state response variable and a dichotomous response variable. Our results suggest that neural networks are not superior to logistic regression models for the traditional dichotomous response variable, but are superior for the more complex financial distress response variable.</span>

scholarly journals OP0034 DOES THE RISK OF VENOUS THROMBOEMBOLISM VARY WITH DISEASE ACTIVITY IN RHEUMATOID ARTHRITIS?

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 23.2-24
Author(s):  
V. Molander ◽  
H. Bower ◽  
J. Askling
Keyword(s):  
Rheumatoid Arthritis ◽  
Logistic Regression ◽  
Venous Thromboembolism ◽  
Disease Activity ◽  
Das28 Score ◽  
Logistic Regression Models ◽  
Highly Active ◽  
Increased Risk ◽  
Das28 Remission ◽  
One Year

Background:Patients with rheumatoid arthritis (RA) are at increased risk for venous thromboembolism (VTE), including deep vein thrombosis (DVT) and pulmonary embolism (PE) (1). Several established risk factors of VTE, such as age, immobilization and comorbid conditions, occur more often patients with RA (2). In addition, inflammation may in itself also increase VTE risk by upregulating procoagolatory factors and causing endothelial damage (3). Recent reports indicate an increased risk of VTE in RA patients treated with JAK-inhibitors (4), pointing to the need to better understand how inflammation measured as clinical RA disease activity influences VTE risk.Objectives:To investigate the relationship between clinical RA disease activity and incidence of VTE.Methods:Patients with RA were identified from the Swedish Rheumatology Quality Register (SRQ) between July 1st2006 and December 31st2017. Clinical rheumatology data for these patients were obtained from the visits recorded in SRQ, and linked to national registers capturing data on VTE events and comorbid conditions. For each such rheumatologist visit, we defined a one-year period after the visit and determined whether a VTE event had occurred within this period or not. A visit followed by a VTE event was categorized as a case, all other visits were used as controls. Each patient could contribute to several visits. The DAS28 score registered at the visit was stratified into remission (0-2.5) vs. low (2.6-3.1), moderate (3.2-5.1) and high (>5.1) disease activity. Logistic regression with robust cluster standard errors was used to estimate the association between the DAS28 score and VTE.Results:We identified 46,311 patients with RA who contributed data from 320,094 visits. Among these, 2,257 visits (0.7% of all visits) in 1345 unique individuals were followed by a VTE within the one-year window. Of these, 1391 were DVT events and 866 were PE events. Figure 1 displays the absolute probabilities of a VTE in this one-year window, and odds ratios for VTE by each DAS28 category, using DAS28 remission as reference. The one-year risk of a VTE increased from 0.5% in patients in DAS28 remission, to 1.1% in patients with DAS28 high disease activity (DAS28 above 5.1). The age- and sex-adjusted odds ratio for a VTE event in highly active RA compared to RA in remission was 2.12 (95% CI 1.80-2.47). A different analysis, in which each patient could only contribute to one visit, yielded similar results.Figure 1.Odds ratios (OR) comparing the odds of VTE for DAS28 activity categories versus remission. Grey estimates are from unadjusted logistic regression models, black estimates are from logistic regression models adjusted for age and sex. Absolute one-year risk of VTE are estimated from unadjusted models.Conclusion:This study demonstrates a strong association between clinical RA inflammatory activity as measured through DAS28 and risk of VTE. Among patients with high disease activity one in a hundred will develop a VTE within the coming year. These findings highlight the need for proper VTE risk assessment in patients with active RA, and confirm that patients with highly active RA, such as those recruited to trials for treatment with new drugs, are already at particularly elevated risk of VTE.References:[1]Holmqvist et al. Risk of venous thromboembolism in patients with rheumatoid arthritis and association with disease duration and hospitalization. JAMA. 2012;308(13):1350-6.[2]Cushman M. Epidemiology and risk factors for venous thrombosis. Semin Hematol. 2007;44(2):62-9.[3]Xu J et al. Inflammation, innate immunity and blood coagulation. Hamostaseologie. 2010;30(1):5-6, 8-9.[4]FDA. Safety trial finds risk of blood clots in the lungs and death with higher dose of tofacitinib (Xeljanz, Xeljanz XR) in rheumatoid arthritis patients; FDA to investigate. 2019.Acknowledgments:Many thanks to all patients and rheumatologists persistently filling out the SRQ.Disclosure of Interests:Viktor Molander: None declared, Hannah Bower: None declared, Johan Askling Grant/research support from: JA acts or has acted as PI for agreements between Karolinska Institutet and the following entities, mainly in the context of the ARTIS national safety monitoring programme of immunomodulators in rheumatology: Abbvie, BMS, Eli Lilly, Merck, MSD, Pfizer, Roche, Samsung Bioepis, Sanofi, and UCB Pharma

scholarly journals Financial Information Asymmetry: Using Deep Learning Algorithms to Predict Financial Distress

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 443
Author(s):  
Chyan-long Jan
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Information Asymmetry ◽  
Error Rate ◽  
Financial Distress ◽  
Prediction Models ◽  
High Accuracy ◽  
Financial Information ◽  
Financial Distress Prediction ◽  
Distress Prediction

Because of the financial information asymmetry, the stakeholders usually do not know a company’s real financial condition until financial distress occurs. Financial distress not only influences a company’s operational sustainability and damages the rights and interests of its stakeholders, it may also harm the national economy and society; hence, it is very important to build high-accuracy financial distress prediction models. The purpose of this study is to build high-accuracy and effective financial distress prediction models by two representative deep learning algorithms: Deep neural networks (DNN) and convolutional neural networks (CNN). In addition, important variables are selected by the chi-squared automatic interaction detector (CHAID). In this study, the data of Taiwan’s listed and OTC sample companies are taken from the Taiwan Economic Journal (TEJ) database during the period from 2000 to 2019, including 86 companies in financial distress and 258 not in financial distress, for a total of 344 companies. According to the empirical results, with the important variables selected by CHAID and modeling by CNN, the CHAID-CNN model has the highest financial distress prediction accuracy rate of 94.23%, and the lowest type I error rate and type II error rate, which are 0.96% and 4.81%, respectively.

45 Application of Machine Learning Models to Thermal Burn Patient Outcome Predictions in the Aftermath of a Nuclear Event

2021 ◽  
Vol 42 (Supplement_1) ◽  
pp. S33-S34
Author(s):  
Morgan A Taylor ◽  
Randy D Kearns ◽  
Jeffrey E Carter ◽  
Mark H Ebell ◽  
Curt A Harris
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Length Of Stay ◽  
Regression Models ◽  
Large Scale ◽  
Prediction Models ◽  
Burn Patients ◽  
Thermal Burn ◽  
Logistic Regression Models ◽  
Burn Patient

Abstract Introduction A nuclear disaster would generate an unprecedented volume of thermal burn patients from the explosion and subsequent mass fires (Figure 1). Prediction models characterizing outcomes for these patients may better equip healthcare providers and other responders to manage large scale nuclear events. Logistic regression models have traditionally been employed to develop prediction scores for mortality of all burn patients. However, other healthcare disciplines have increasingly transitioned to machine learning (ML) models, which are automatically generated and continually improved, potentially increasing predictive accuracy. Preliminary research suggests ML models can predict burn patient mortality more accurately than commonly used prediction scores. The purpose of this study is to examine the efficacy of various ML methods in assessing thermal burn patient mortality and length of stay in burn centers. Methods This retrospective study identified patients with fire/flame burn etiologies in the National Burn Repository between the years 2009 – 2018. Patients were randomly partitioned into a 67%/33% split for training and validation. A random forest model (RF) and an artificial neural network (ANN) were then constructed for each outcome, mortality and length of stay. These models were then compared to logistic regression models and previously developed prediction tools with similar outcomes using a combination of classification and regression metrics. Results During the study period, 82,404 burn patients with a thermal etiology were identified in the analysis. The ANN models will likely tend to overfit the data, which can be resolved by ending the model training early or adding additional regularization parameters. Further exploration of the advantages and limitations of these models is forthcoming as metric analyses become available. Conclusions In this proof-of-concept study, we anticipate that at least one ML model will predict the targeted outcomes of thermal burn patient mortality and length of stay as judged by the fidelity with which it matches the logistic regression analysis. These advancements can then help disaster preparedness programs consider resource limitations during catastrophic incidents resulting in burn injuries.

scholarly journals An Empirical Test Of The View Of Inventory As A Liability IN Explaining Financial Distress

2011 ◽  
Vol 14 (2) ◽  
pp. 83 ◽  
Author(s):  
Benjamin P. Foster ◽  
M. Cathy Sullivan ◽  
Terry J. Ward
Keyword(s):  
Logistic Regression ◽  
Financial Distress ◽  
Regression Models ◽  
Empirical Test ◽  
Explanatory Power ◽  
Manufacturing Firms ◽  
Logistic Regression Models ◽  
Financially Distressed ◽  
Accounting Ratios ◽  
Extreme View

<span>This study reports a first attempt in a financial distress context to test the extreme JIT and TOC view that inventory is a liability. We compared inventory levels and the change in inventory for healthy and financially distressed manufacturing firms. We also compared the explanatory power of logistic regression models including traditional accounting ratios to that of models including accounting ratios created by viewing inventory as a liability. We found some support for the extreme view of some JIT and TOC proponents that traditional inventory should be considered a liability.</span>

scholarly journals Determinants and Predictors of SMEs’ Financial Failure: A Logistic Regression Approach

Risks ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 107
Author(s):  
Youssef Zizi ◽  
Mohamed Oudgou ◽  
Abdeslam El Moudden
Keyword(s):  
Logistic Regression ◽  
Return On Assets ◽  
Classification Rate ◽  
Accounts Receivable ◽  
Financial Failure ◽  
Stepwise Method ◽  
Regression Approach ◽  
Asset Turnover ◽  
Duration Of Trade ◽  
One Year

This paper aims to identify the determinants and predictors of Small and Medium-sized Enterprises (SMEs)’ financial failure. Within this framework, we have opted for a quantitative method based on a sample of healthy and failing SMEs of a Moroccan bank. The main results of the different optimal models are obtained by the stepwise method of estimating logistic regression. These results show, in a normal economic context, that the variables that discriminate between healthy and failing SMEs are the main predictors of financial failure. Autonomy ratio, interest to sales, asset turnover, days in accounts receivable, and duration of trade payables are the variables that increase the probability of financial failure, while repayment capacity and return on assets reduce the probability of failure. These variables present an overall classification rate of healthy and failing SMEs of 91.11% three years before failure and of 84.44% two years and one year before failure.

scholarly journals Ambient air pollution exposure and risk and progression of interstitial lung abnormalities: the Framingham Heart Study

Thorax ◽  
2019 ◽  
Vol 74 (11) ◽  
pp. 1063-1069 ◽  
Author(s):  
Mary B Rice ◽  
Wenyuan Li ◽  
Joel Schwartz ◽  
Qian Di ◽  
Itai Kloog ◽  
...  
Keyword(s):  
Air Pollution ◽  
Logistic Regression ◽  
Regression Models ◽  
Cardiac Ct ◽  
Prediction Models ◽  
Ambient Air ◽  
Chest Ct ◽  
Ambient Air Pollution ◽  
Logistic Regression Models ◽  
Lung Abnormalities

BackgroundAmbient air pollution accelerates lung function decline among adults, however, there are limited data about its role in the development and progression of early stages of interstitial lung disease.AimsTo evaluate associations of long-term exposure to traffic and ambient pollutants with odds of interstitial lung abnormalities (ILA) and progression of ILA on repeated imaging.MethodsWe ascertained ILA on chest CT obtained from 2618 Framingham participants from 2008 to 2011. Among 1846 participants who also completed a cardiac CT from 2002 to 2005, we determined interval ILA progression. We assigned distance from home address to major roadway, and the 5-year average of fine particulate matter (PM2.5), elemental carbon (EC, a traffic-related PM2.5 constituent) and ozone using spatio-temporal prediction models. Logistic regression models were adjusted for age, sex, body mass index, smoking status, packyears of smoking, household tobacco exposure, neighbourhood household value, primary occupation, cohort and date.ResultsAmong 2618 participants with a chest CT, 176 (6.7%) had ILA, 1361 (52.0%) had no ILA, and the remainder were indeterminate. Among 1846 with a preceding cardiac CT, 118 (6.4%) had ILA with interval progression. In adjusted logistic regression models, an IQR difference in 5-year EC exposure of 0.14 µg/m3 was associated with a 1.27 (95% CI 1.04 to 1.55) times greater odds of ILA, and a 1.33 (95% CI 1.00 to 1.76) times greater odds of ILA progression. PM2.5 and O3 were not associated with ILA or ILA progression.ConclusionsExposure to EC may increase risk of progressive ILA, however, associations with other measures of ambient pollution were inconclusive.

scholarly journals Pengaruh Rasio Keuangan Terhadap Financial Distress Pada Perusahaan Manufaktur Yang Terdaftar Di Bursa Efek Indonesia Periode 2009-2013

2018 ◽  
Vol 21 (1) ◽  
pp. 43
Author(s):  
Steven Sean, Viriany
Keyword(s):  
Logistic Regression ◽  
Data Analysis ◽  
Financial Distress ◽  
Sampling Method ◽  
Financial Ratios ◽  
Manufacturing Companies ◽  
Analysis Techniques ◽  
Independent Variables ◽  
One Year ◽  
Manufacture Company

The purpose of this study is to determine the financial ratios partial effect on financial distress in manufacturing companies prior to the period of financial distress (t-n). Financial distress is defined as a late stage of corporate decline that precedes more cataclysmic events such as bankruptcy or liquidation.  Analysis of  financial ratios  is performed to  determine  the ratio that affect the probability of  financial distress. The method used is the  purposive  sampling  method.  Data analysis techniques logistic regression.  Hypothesis  testing  is  done  in  three  periods,  that  is  the period of  one  year  before the  financial distress  (t-1),  a  two-year period  before  the  financial  distress  (t-2) and a  three-year period  before the financial distress (t-3). Results indicate that  the independent variables  have a partial effect on manufacture company. The period  t-1, ratio TL/TA and  NI/TA  affect  financial  distress.  The  period  t-2,  ratio  NI/EQ affect financial  distress.  The period  t-3, ratio TL/TA and NI/TA affect financial distress.

scholarly journals THE EFFECTS OF FINANCIAL RATIO, LOCAL SIZE AND LOCAL STATUS ON FINANCIAL DISTRESS

2019 ◽  
Vol 3 (01) ◽  
pp. 38
Author(s):  
Novica Indriaty ◽  
Doddy Setiawan ◽  
Yuwita Ariessa Pravasanti
Keyword(s):  
Logistic Regression ◽  
Local Government ◽  
Financial Distress ◽  
Local Governments ◽  
Sampling Method ◽  
Return On Assets ◽  
Return On Equity ◽  
Financial Ratio ◽  
The Status ◽  
Equity Ratio

This study is aimed to examine the effects of financial ratio empirically, local size and local status on financial distress. The status of financial distress is the condition of the inability of the local government to repay the loan principal and the loan interest. The population of this study include local governments in Indonesia that publish Report on Local Government Finances in 2008-2014. Samples were selected based on purposive sampling method and obtained 641 as research observation. With logistic regression, this study found that financial ratio included current ratio (CR), debt to equity ratio (D/E), operating revenues to total revenues ratio (OR/TR), return on assets ratio (ROA), return on equity ratio (ROE), and macro-economic variables were local size and local status have a significant effect on financial distress. Keywords : Financial Distress, Financial Ratio, Local Size, Local Status, Logistic Regression, Report on Local Government Finances

Sign in / Sign up

Export Citation Format

Share Document