scholarly journals A Comparison on Leading Methodologies for Bankruptcy Prediction: The Case of the Construction Sector in Lithuania

Economies ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 82
Author(s):  
Gintare Giriūniene ◽  
Lukas Giriūnas ◽  
Mangirdas Morkunas ◽  
Laura Brucaite
Keyword(s):  
Statistical Data ◽  
Prediction Models ◽  
Scientific Literature ◽  
Data Representation ◽  
Bankruptcy Prediction ◽  
Construction Sector ◽  
Macroeconomic Variables ◽  
Graphic Data ◽  
Macroeconomic Indicators ◽  
Business Conditions

Different economic environments differ in their characteristics; this prevents the usage of the same bankruptcy prediction models under different conditions. Objectively, the abundance of bankruptcy prediction models gives rise to the idea that these models are not in compliance with the changing business conditions in the market and do not meet the increasing complexity of business tasks. The purpose of this study is to assess the suitability of existing bankruptcy prediction models and the possibilities to increase the effectiveness of their application. In order to analyze theoretical aspects of the application of bankruptcy forecasting models and frame the research methodology, a systemic comparative and logical analysis of the scientific literature and statistical data, graphic data representation, induction, deduction and abstraction are employed. Results of the analysis confirm research hypotheses that bankruptcy prediction models based on macroeconomic variables are effective in identifying the number of corporate bankruptcies in a country and that the application of the model created on the grounds of macroeconomic indicators together with the traditional bankruptcy prediction model can improve the reliability of bankruptcy prediction. However, it was identified that models which are not specially adapted to companies in the construction sector are also suitable for forecasting their bankruptcies.

Identifying impact of variables in deep learning models on bankruptcy prediction of construction contractors

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Youjin Jang ◽  
Inbae Jeong ◽  
Yong K. Cho
Keyword(s):  
Deep Learning ◽  
Prediction Model ◽  
Shapley Value ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Bankruptcy Prediction ◽  
Content Type ◽  
Macroeconomic Variables ◽  
Input Variables ◽  
The Impact

PurposeThe study seeks to identify the impact of variables in a deep learning-based bankruptcy prediction model, which has achieved superior performance to other prediction models but cannot easily interpret hidden processes.Design/methodology/approachThis study developed three LSTM-RNN–based models that predicted the probability of bankruptcy before 1, 2 and 3 years using financial, the construction market and macroeconomic variables as input variables. Then, the impacts of the input variables that affected prediction accuracy in each model were identified by using Shapley value and compared among the three models. This study also investigated the prediction accuracy using variants of input variables grouped sequentially by high-impact ranking.FindingsThe results showed that the prediction accuracies were largely impacted by “housing starts” in all models. As the prediction period increased, the effects of macroeconomic variables on prediction accuracy increased, whereas the impact of “return on assets” on prediction accuracy decreased. It also found that the “current ratio” and “debt ratio” significantly influenced the prediction accuracies in all models. Also, the results revealed that similar prediction accuracies could be achieved using only 8, 10, and 10 variables out of a total of 18 variables for the 1-, 2-, and 3-year prediction models, respectively.Originality/valueThis study provides a Shapley value-based approach to identify how each input variable in a deep-learning bankruptcy prediction model. The findings of this study can not only assist in obtaining better insights into the underlying concept of bankruptcy but also use to select variables by removing those identified as less significant.

scholarly journals The Evaluation of the Impact of Macroeconomic Indicators on the Performance of Listed Real Estate Companies and Reits

Ekonomika ◽  
2020 ◽  
Vol 99 (1) ◽  
pp. 79-92
Author(s):  
Viktorija Cohen ◽  
Arūnas Burinskas
Keyword(s):  
Monetary Policy ◽  
Real Estate ◽  
Real Estate Market ◽  
Supply Side ◽  
Construction Sector ◽  
Monetary Policy Shocks ◽  
Macroeconomic Variables ◽  
Macroeconomic Indicators ◽  
Policy Shocks ◽  
The Impact

Using quarterly data from 2006:Q1 to 2019:Q3 (55 observations), this paper examines 18 Eurozone macroeconomic variables that represent monetary policy, external and construction sectors’ performance, economic growth, investment, households’ earnings, inflation and assesses their impact on the performance of the European listed real estate companies and REITs. Empirical results demonstrate that the European listed real estate market is strongly influenced by the supply side: the construction sector and the inflation of producers’ prices; while the demand side is strongly affected by the expansionary monetary policy of ECB. Furthermore, some primary findings propose that US expansionary monetary policy shocks have an effect on the European listed real estate market. This conclusion demands further thorough research.

Bankruptcy Prediction Models: A Bet on Artificial Neural Networks

2012 ◽  
Vol 3 (2) ◽  
pp. 48-50
Author(s):  
Ana Isabel Velasco Fernández ◽  
◽  
Ricardo José Rejas Muslera ◽  
Juan Padilla Fernández-Vega ◽  
María Isabel Cepeda González
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Models ◽  
Bankruptcy Prediction ◽  
Artificial Neural

scholarly journals Do the Determinants of Non-Performing Loans Have a Different Effect over Time? A Conditional Correlation Approach

2021 ◽  
Vol 14 (1) ◽  
pp. 21
Author(s):  
Mariagrazia Fallanca ◽  
Antonio Fabio Forgione ◽  
Edoardo Otranto
Keyword(s):  
Correlation Coefficients ◽  
Bank Loan ◽  
Time Varying ◽  
Conditional Correlation ◽  
Subprime Mortgage ◽  
Macroeconomic Variables ◽  
Correlation Models ◽  
Mortgage Crisis ◽  
The Us ◽  
Macroeconomic Indicators

Several studies have explored the linkage between non-performing loans and major macroeconomic indicators, using a wide variety of methodologies, sometimes with different results. This occurs, we argue, because these relationships are generally derived in terms of correlation coefficients evaluated in certain time spans, which represent a sort of average level of correlations. However, such correlations are necessarily time-varying, because the relationships between bank loan indicators and macroeconomic variables could be stronger during particular periods or in correspondence with important economic events. We propose an empirical exercise using dynamic conditional correlation models, with constant and time-varying parameters. Applying these models to quarterly delinquency rates and an array of macroeconomic variables for the US, for the period 1985–2019, we find that the correlation is often negligible in this period except during periods of economic crises, in particular the early 1990 crisis and the subprime mortgage crisis.

scholarly journals Modelling bankruptcy prediction models in Slovak companies

2017 ◽  
Vol 39 ◽  
pp. 01013 ◽  
Author(s):  
Maria Kovacova ◽  
Jana Kliestikova
Keyword(s):  
Prediction Models ◽  
Bankruptcy Prediction

Exploring the relationship between macroeconomic indicators and sovereign credit default swap in Pakistan

2017 ◽  
Vol 18 (4) ◽  
pp. 368-380
Author(s):  
Abdul Rashid ◽  
Farooq Ahmad ◽  
Ammara Yasmin
Keyword(s):  
Exchange Rate ◽  
Credit Default Swap ◽  
Content Type ◽  
Macroeconomic Variables ◽  
Long Run ◽  
Credit Default ◽  
Macroeconomic Indicators ◽  
Short Run ◽  
The Exchange Rate ◽  
The Interest Rate

Purpose This paper aims to empirically examine the long- and short-run relationship between macroeconomic indicators (exchange rates, interest rates, exports, imports, foreign reserves and the rate of inflation) and sovereign credit default swap (SCDS) spreads for Pakistan. Design/methodology/approach The authors apply the autoregressive distributed lag (ARDL) model to explore the level relationship between the macroeconomic variables and SCDS spreads. The error correction model is estimated to examine the short-run effects of the underlying macroeconomic variables on SCDS spreads. Finally, the long-run estimates are obtained in the ARDL framework. The study uses monthly data covering the period January 2001-February 2015. Findings The results indicate that there is a significant long-run relationship between the macroeconomic indicators and SCDS spreads. The estimated long-run coefficients reveal that both the interest rate and foreign exchange reserves are significantly and negatively, whereas imports and the rate of inflation are positively related to SCDS spreads. Yet, the results suggest that the exchange rate and exports do not have any significant long-run impact on SCDS spreads. The findings regarding the short-run relationship indicate that the exchange rate, imports and the rate of inflation are positively, whereas the interest rate and exports are negatively related to SCDS spreads. Practical implications The results suggest that State Bank of Pakistan should design monetary and foreign exchange rate polices to minimize unwanted variations in the exchange rate to reduce SCDS spreads. The results also suggest that it is incumbent to Pakistan Government to improve the balance of payments to reduce SCDS spreads. The findings also suggest that the inflation targeting policy can also help in reducing SCDS spreads. Originality/value This is the first study to examine the empirical determinants of SCDS spreads for Pakistan. Second, it estimates the short- and long-run effects in the ARDL framework. Third, it considers both internal and external empirical determinants of SCDS spreads.

Sign in / Sign up

Export Citation Format

Share Document