Predicting Firms' Credit Ratings Using Ensembles of Artificial Immune Systems and Machine Learning - An Over-Sampling Approach

This paper examines the classification performance of artificial immune systems on the one hand and machine learning and neural networks on the other hand on the problem of forecasting credit ratings of firms. The problem is realized as a two-class problem, for investment and non-investment rating grades. The dataset is usually imbalanced in credit rating predictions. We address the issue by over-sampling the minority class in the training dataset. The experimental results show that this approach leads to significantly higher classification accuracy. Additionally, the use of the ensembles of classifiers makes the prediction even more accurate.

[1]  Jason Brownlee,et al.  Clonal selection theory and Clonalg: the clonal selection classification algorithm (CSCA) , 2005 .

[2]  Tim Loughran,et al.  When is a Liability not a Liability? Textual Analysis, Dictionaries, and 10-Ks , 2010 .

[3]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[4]  Petr Hájek,et al.  Municipal credit rating modelling by neural networks , 2011, Decis. Support Syst..

[5]  William F. McColl.  Parallel Algorithms and Architectures , 1988, Shell Conference.

[6]  Vadlamani Ravi,et al.  Bankruptcy prediction in banks and firms via statistical and intelligent techniques - A review , 2007, Eur. J. Oper. Res..

[7]  Nicolás García-Pedrajas,et al.  Construction of classifier ensembles by means of artificial immune systems , 2008, J. Heuristics.

[8]  G. A. Zee,et al.  Parallel Computing 1988 , 1989, Lecture Notes in Computer Science.

[9]  D. Dasgupta.  Artificial Immune Systems and Their Applications , 1998, Springer Berlin Heidelberg.

[10]  Jonathan Timmis,et al.  Artificial Immune Recognition System (AIRS): An Immune-Inspired Supervised Learning Algorithm , 2004, Genetic Programming and Evolvable Machines.

[11]  Petr Hájek,et al.  Credit rating modelling by kernel-based approaches with supervised and semi-supervised learning , 2011, Neural Computing and Applications.

[13]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[14]  Petr Hájek,et al.  Evaluating Sentiment in Annual Reports for Financial Distress Prediction Using Neural Networks and Support Vector Machines , 2013, EANN.

[15]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[16]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[17]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[18]  F. Azuaje.  Artificial Immune Systems: A New Computational Intelligence Approach , 2003 .

[19]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .