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

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-01391290
Contributor : Hal Ifip <>
Submitted on : Thursday, November 3, 2016 - 10:50:29 AM
Last modification on : Friday, December 1, 2017 - 1:16:45 AM
Long-term archiving on : Saturday, February 4, 2017 - 1:22:58 PM

File

978-3-662-44654-6_3_Chapter.pd...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Petr Hájek, Vladimír Olej. Predicting Firms’ Credit Ratings Using Ensembles of Artificial Immune Systems and Machine Learning – An Over-Sampling Approach. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.29-38, ⟨10.1007/978-3-662-44654-6_3⟩. ⟨hal-01391290⟩

Share

Metrics

Record views

89

Files downloads

266