The evaluation of bankruptcy prediction models based on socio-economic costs

被引:12
作者
Radovanovic, Jelena [1 ,2 ]
Haas, Christian [1 ]
机构
[1] Vienna Univ Econ & Business, Vienna, Austria
[2] Vienna Univ Econ & Business D5, Dept Strategy & Innovat, Welthandelspl 1, A-1020 Vienna, Austria
关键词
Machine-learning; Bankruptcy prediction; Evaluation metrics; FINANCIAL RATIOS; NEURAL-NETWORKS; RANDOM FORESTS; PERFORMANCE; SPILLOVER; DISTRESS; COLLAPSE; FIRMS; RISK;
D O I
10.1016/j.eswa.2023.120275
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Corporate bankruptcies often have severe consequences on all stakeholders, from financial stakeholders losing their investment to employees losing their jobs. Yet traditional bankruptcy prediction models typically focus solely on predicting the event of bankruptcy itself, and do not consider the socio-economic consequences of their prediction. Therefore, this study aims to integrate these perspectives into the machine-learning (ML) modeling process to consider different costs caused by bankruptcy. We improve upon existing bankruptcy prediction models by actively taking the social and financial impacts of bankruptcy into account. Specifically, we consider two alternative evaluation metrics: the financial costs of bankruptcy, and the social impact measured using number of lost jobs as proxy. We compare a variety of machine-learning models as well as multivariate discriminant analysis and logistic regression, the latter serving as a benchmark to show the improvements that can be achieved using ML models. We apply the models on a large real-world data set from the Compustat database, containing listed companies in North America for the period from 1985 to 2020, with over 190,000 company-year observations. Our results show that small differences in statistical performance can translate into large differences regarding socio-economic costs, and that the selection of the 'best' performing model crucially depends on the evaluation metric considered.
引用
收藏
页数:18
相关论文
共 58 条
  • [1] Comparing the performance of market-based and accounting-based bankruptcy prediction models
    Agarwal, Vineet
    Taffler, Richard
    [J]. JOURNAL OF BANKING & FINANCE, 2008, 32 (08) : 1541 - 1551
  • [2] Quantifying StockTwits semantic terms' trading behavior in financial markets: An effective application of decision tree algorithms
    Al Nasseri, Alya
    Tucker, Allan
    de Cesare, Sergio
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (23) : 9192 - 9210
  • [3] Systematic review of bankruptcy prediction models: Towards a framework for tool selection
    Alaka, Hafiz A.
    Oyedele, Lukumon O.
    Owolabi, Hakeem A.
    Kumar, Vikas
    Ajayi, Saheed O.
    Akinade, Olugbenga O.
    Bilal, Muhammad
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2018, 94 : 164 - 184
  • [4] Bankruptcy forecasting:: An empirical comparison of AdaBoost and neural networks
    Alfaro, Esteban
    Garcia, Noelia
    Gamez, Matias
    Elizondo, David
    [J]. DECISION SUPPORT SYSTEMS, 2008, 45 (01) : 110 - 122
  • [5] Altman E. I., 1977, Journal of Banking & Finance, V1, P29, DOI DOI 10.1016/0378-4266(77)90017-6
  • [6] A Race for Long Horizon Bankruptcy Prediction
    Altman, Edward I.
    Iwanicz-Drozdowska, Malgorzata
    Laitinen, Erkki K.
    Suvas, Arto
    [J]. APPLIED ECONOMICS, 2020, 52 (37) : 4092 - 4111
  • [7] FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND PREDICTION OF CORPORATE BANKRUPTCY
    ALTMAN, EI
    [J]. JOURNAL OF FINANCE, 1968, 23 (04) : 589 - 609
  • [8] Balcaen S., 2006, BRIT ACCOUNT REV, V38, P63, DOI [DOI 10.1016/J.BAR.2005.09.001, 10.1016/j.bar.2005.09.001]
  • [9] Machine learning models and bankruptcy prediction
    Barboza, Flavio
    Kimura, Herbert
    Altman, Edward
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2017, 83 : 405 - 417
  • [10] FINANCIAL RATIOS AS PREDICTORS OF FAILURE
    BEAVER, WH
    [J]. JOURNAL OF ACCOUNTING RESEARCH, 1966, 4 : 71 - 111