Bankruptcy prediction using ensemble of autoencoders optimized by genetic algorithm

被引:1
|
作者
Kanasz, Robert [1 ]
Gnip, Peter [1 ]
Zoricak, Martin [2 ]
Drotar, Peter [1 ]
机构
[1] Tech Univ Kosice, Fac Elect Engn & Informat, Dept Comp & Informat, Kosice, Slovakia
[2] Tech Univ Kosice, Fac Econ, Dept Finance, Kosice, Slovakia
关键词
Autoencoder; Bankruptcy prediction; Imbalanced learning; Neural networks; Genetic algorithm; Financial ratios; CORPORATE FAILURE; FINANCIAL RATIOS; MODELS; PERFORMANCE;
D O I
10.7717/peerj-cs.1257
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The prediction of imminent bankruptcy for a company is important to banks, government agencies, business owners, and different business stakeholders. Bankruptcy is influenced by many global and local aspects, so it can hardly be anticipated without deeper analysis and economic modeling knowledge. To make this problem even more challenging, the available bankruptcy datasets are usually imbalanced since even in times of financial crisis, bankrupt companies constitute only a fraction of all operating businesses. In this article, we propose a novel bankruptcy prediction approach based on a shallow autoencoder ensemble that is optimized by a genetic algorithm. The goal of the autoencoders is to learn the distribution of the majority class: going concern businesses. Then, the bankrupt companies are represented by higher autoencoder reconstruction errors. The choice of the optimal threshold value for the reconstruction error, which is used to differentiate between bankrupt and nonbankrupt companies, is crucial and determines the final classification decision. In our approach, the threshold for each autoencoder is determined by a genetic algorithm. We evaluate the proposed method on four different datasets containing small and medium-sized enterprises. The results show that the autoencoder ensemble is able to identify bankrupt companies with geometric mean scores ranging from 71% to 93.7%, (depending on the industry and evaluation year).
引用
收藏
页数:23
相关论文
共 50 条
  • [41] A fuzzy autopilot optimized using a genetic algorithm
    Sutton, R
    Marsden, GD
    JOURNAL OF NAVIGATION, 1997, 50 (01): : 120 - 131
  • [42] DNA gene expression classification with ensemble classifiers optimized by speciated genetic algorithm
    Kim, KJ
    Cho, SB
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS, 2005, 3776 : 649 - 653
  • [43] Genetic Algorithm Optimized Training for Neural Network Spectrum Prediction
    Yang, Jian
    Zhao, Hangsheng
    Chen, Xi
    2016 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2016, : 2949 - 2954
  • [44] Optimized Ensemble Model with Genetic Algorithm for DDoS Attack Detection in IoT Networks
    Saiyed, Makhduma F.
    Al-Anbagi, Irfan
    2024 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS, ICC WORKSHOPS 2024, 2024, : 433 - 438
  • [45] Ensemble Recurrent Neural Network Design using a Genetic Algorithm applied in Times Series Prediction
    Pulido, Martha
    Melin, Patricia
    COMPUTACION Y SISTEMAS, 2022, 26 (02): : 683 - 700
  • [46] Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model
    Chatterjee, Snehamoy
    Bandopadhyay, Sukumar
    Machuca, David
    MATHEMATICAL GEOSCIENCES, 2010, 42 (03) : 309 - 326
  • [47] Prediction of soil moisture content using genetic algorithm-optimized backpropagation algorithm from spectral data
    Wang, Jiawei
    Zhang, Dong
    Zhang, Yulu
    Liu, Hu
    Zhou, Linkang
    Jin, Hua
    JOURNAL OF SOILS AND SEDIMENTS, 2024, 24 (09) : 3238 - 3251
  • [48] Ensemble Methods for Bankruptcy Resolution Prediction: A New Approach
    Sanchez-Medina, Agustin J.
    Blazquez-Santana, Felix
    Cervino-Cortinez, Daniel L.
    Pellejero, Monica
    COMPUTATIONAL ECONOMICS, 2025,
  • [49] Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model
    Snehamoy Chatterjee
    Sukumar Bandopadhyay
    David Machuca
    Mathematical Geosciences, 2010, 42 : 309 - 326
  • [50] A selective ensemble based on expected probabilities for bankruptcy prediction
    Hung, Chihli
    Chen, Jing-Hong
    EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (03) : 5297 - 5303