Cost-sensitive ensemble methods for bankruptcy prediction in a highly imbalanced data distribution: a real case from the
- PDF / 897,489 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 26 Downloads / 196 Views
REGULAR PAPER
Cost-sensitive ensemble methods for bankruptcy prediction in a highly imbalanced data distribution: a real case from the Spanish market Nazeeh Ghatasheh1 · Hossam Faris2 · Ruba Abukhurma3 · Pedro A. Castillo4 Antonio M. Mora6 · Ala’ M. Al-Zoubi7 · Ahmad Hassanat8,9
· Nailah Al-Madi5 ·
Received: 11 November 2019 / Accepted: 8 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Bankruptcy is an issue of interest in the business world since decades. It is a crucial endeavor for survival to predict this phenomenon in periods of economic turmoil and recession. In fact, bankruptcy modeling is challenging due to the complexity of contributing factors and the highly imbalanced distribution of available data sets. This work aims at improving the prediction power of bankruptcy modeling, by applying cost-sensitive ensemble methods on a real-world Spanish bankruptcy data set to generate prediction models. The performance of the prediction models is highly competitive in comparison with the related research in the field. Cost-sensitive random forests over-performed other approaches in predicting bankruptcy, achieving a geometric mean of 90.7%, 0.094 and 0.088 type I & type II errors, respectively. Keywords Bankruptcy prediction · Business analytics · Cost-sensitive ensemble · Imbalanced data analysis
1 Introduction
B
Pedro A. Castillo [email protected] Nazeeh Ghatasheh [email protected] Hossam Faris [email protected] Ruba Abukhurma [email protected] Nailah Al-Madi [email protected] Antonio M. Mora [email protected]
1
2
3
Businesses nowadays operate in stringent environment in which pressures may force a firm to become insolvent. There are several dramatic consequences of insolvency on firms or individuals, e.g., put the firm in one of liquidation types (a.k.a. winding up), or declaring bankruptcy [1,5,39]. The implications of a financial crisis might cease the operations of a firm, diminish the profession of legal representatives, affect external entities, and probably impose negative impacts on the society [2,38]. In extreme cases, the global economy may
4
Ala’ M. Al-Zoubi [email protected]; [email protected]
Department of Computer Architecture and Computer Technology, ETSIIT and CITIC, University of Granada, Granada, Spain
5
Ahmad Hassanat [email protected]
Data Science Department, Princess Sumaya University for Technology (PSUT), Amman, Jordan
6
Department of Signal Theory, Telematics and Communications, ETSIIT and CITIC, University of Granada, Granada, Spain
7
School of Sciences, Technology and Engineering, University of Granada, Granada, Spain
8
Department of Information Technology, Mutah University, Karak, Jordan
9
Industrial Innovation and Robotics Center, University of Tabuk, Tabuk 71491, Saudi Arabia
Information Technology Department,Faculty of Information Technology and Systems, The University of Jordan, Aqaba, Jordan Information Technology Department, King Abdullah II School for Information Technology, The University of Jordan, Amman
Data Loading...
