Bankruptcy prediction using Extreme Learning Machine and financial expertise

Bankruptcy prediction has been widely studied as a binary classification problem using financial ratios methodologies. In this paper, Leave-One-Out-Incremental Extreme Learning Machine (LOO-IELM) is explored for this task. LOO-IELM operates in an incremental way to avoid inefficient and unnecessary calculations and stops automatically with the neurons of which the number is unknown. Moreover, Combo method and further Ensemble model are investigated based on different LOO-IELM models and the specific financial indicators. These indicators are chosen using different strategies according to the financial expertise. The entire process has shown its good performance with a very fast speed, and also helps to interpret the model and the special ratios.

[1]  Amaury Lendasse,et al.  OP-ELM: Optimally Pruned Extreme Learning Machine , 2010, IEEE Transactions on Neural Networks.

[2]  Amaury Lendasse,et al.  Ensemble KNNs for Bankruptcy Prediction , 2009 .

[3]  Charles L. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[4]  Edward I. Altman,et al.  FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY , 1968 .

[5]  Nan Liu,et al.  Voting based extreme learning machine , 2012, Inf. Sci..

[6]  Eric Séverin,et al.  Dynamic analysis of the business failure process: A study of bankruptcy trajectories , 2010 .

[7]  H. Frydman,et al.  Introducing Recursive Partitioning for Financial Classification: The Case of Financial Distress , 1985 .

[8]  Stephanie M. Bryant,et al.  A case-based reasoning approach to bankruptcy prediction modeling , 1997, Intell. Syst. Account. Finance Manag..

[9]  Kyung-shik Shin,et al.  A genetic algorithm application in bankruptcy prediction modeling , 2002, Expert Syst. Appl..

[10]  W. Beaver.  Financial Ratios As Predictors Of Failure , 1966 .

[11]  Guang-Bin Huang,et al.  Convex incremental extreme learning machine , 2007, Neurocomputing.

[12]  Amaury Lendasse,et al.  TROP-ELM: A double-regularized ELM using LARS and Tikhonov regularization , 2011, Neurocomputing.

[13]  Amaury Lendasse,et al.  Bankruptcy Prediction with Missing Data , 2011 .

[14]  Yoram Reich,et al.  Ensemble modelling or selecting the best model: Many could be better than one , 1999, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[15]  Michel Verleysen,et al.  Ensemble Modeling with a Constrained Linear System of Leave-One-Out Outputs , 2010, ESANN.

[16]  Benoît Frénay,et al.  Ensembles of Local Linear Models for Bankruptcy Analysis and Prediction , 2011 .

[17]  Qinyu. Zhu.  Extreme Learning Machine , 2013 .

[18]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[19]  Robert K. L. Gay,et al.  Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning , 2009, IEEE Transactions on Neural Networks.

[20]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  Erkki Oja,et al.  GPU-accelerated and parallelized ELM ensembles for large-scale regression , 2011, Neurocomputing.

[22]  Chee Kheong Siew,et al.  Extreme learning machine: RBF network case , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[23]  Lei Chen,et al.  Enhanced random search based incremental extreme learning machine , 2008, Neurocomputing.

[24]  Mark J Funt.  Financial ratios. , 2009, Pennsylvania dental journal.

[25]  P. Jardin.  Prévision de la défaillance et réseaux de neurones : l'apport des méthodes numériques de sélection de variables , 2007 .

[26]  Zexuan Zhu,et al.  A fast pruned-extreme learning machine for classification problem , 2008, Neurocomputing.

[27]  Alan J. Mayne,et al.  Generalized Inverse of Matrices and its Applications , 1972 .

[28]  J. Efrim Boritz,et al.  Effectiveness of neural network types for prediction of business failure , 1995 .

[29]  K. S. Banerjee.  Generalized Inverse of Matrices and Its Applications , 1973 .

[30]  C. Siew,et al.  Extreme Learning Machine with Randomly Assigned RBF Kernels , 2005 .

[31]  Mauro Birattari,et al.  Recursive Lazy Learning for Modeling and Control , 1998, ECML.

[32]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[33]  Yuan Lan,et al.  Two-stage extreme learning machine for regression , 2010, Neurocomputing.

[34]  Christophe Biernacki.  Simultaneous t-Model-Based Clustering for Data Differing over Time Period : Application for Understanding Companies Financial Health , 2011 .

[35]  J. Patell,et al.  The Experimental Design of Classification Models: An Application of Recursive Partitioning and Bootstrapping to Commercial Bank Loan Classifications , 1984 .

[36]  Marjorie B. Platt,et al.  Probabilistic Neural Networks in Bankruptcy Prediction , 1999 .

[37]  Yuan Lan,et al.  Random search enhancement of error minimized extreme learning machine , 2010, ESANN.

[38]  Yuan Lan,et al.  Constructive hidden nodes selection of extreme learning machine for regression , 2010, Neurocomputing.

[39]  Chee Kheong Siew,et al.  Incremental extreme learning machine with fully complex hidden nodes , 2008, Neurocomputing.