Forecasting Sovereign Credit Ratings Using Differential Evolution and Logic Aggregation in IBA Framework

Jelinek, Srđan; Milošević, Pavle; Rakićević, Aleksandar; Petrović, Bratislav

doi:10.1007/978-3-030-85577-2_60

Cited by 2 publications

(4 citation statements)

References 16 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper extends and continues the research started in [44], where the idea of using the DE algorithm for the optimization of a prediction model structure in the IBA framework is presented for the first time. In this paper, the IBA-DE algorithm is elaborated on in detail and used for sovereign credit rating prediction.…”

Section: Introductionsupporting

confidence: 57%

“…The DE algorithm can be further improved by applying some modifications to its hyper-parameters during the optimization process, as well as applying different strategies for the mutation, crossover, and selection processes. Finally, improvement can be made by addressing the high autocorrelation in the credit ratings time series by including the credit rating transition matrices modeled using the DE algorithm which were first presented in a recent study [68].…”

Section: Discussionmentioning

confidence: 99%

“…In this section, we present the application of the IBA-DE approach for sovereign credit rating prediction. The approach was first used for credit rating prediction in [44]. However, the inputs used were from a very narrow domain and many aspects of the economy were not considered.…”

Section: Forecasting Sovereign Credit Ratings With the Iba-de Approachmentioning

confidence: 99%

“…The model is a pseudo-logical function that uses publicly available macroeconomic indicators to predict sovereign credit ratings. Compared to the research presented in [44], where only the financial inputs have been used, the inputs used in this paper are extended to encompass the industrial and social country aspects. The function which is obtained as a model output is easily analyzed and interpretable due to the fuzzy gradation of its elements.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Novel IBA-DE Hybrid Approach for Modeling Sovereign Credit Ratings

et al. 2022

View full text Add to dashboard Cite

Nowadays, the sovereign credit rating is not only an index of a country’s economic performance and political stability but also an overall indicator of development and growth, as well as the trust factor that is associated with the country. Due to its importance, the vast amount of available information, and the lack of a closed-form solution, prediction models based on machine learning (ML) and computation intelligence (CI) techniques are being increasingly used to complement traditional financial approaches. In this paper, we aim to introduce a novel ML-CI approach for sovereign credit rating prediction based on a differential evolution (DE) algorithm and interpolative Boolean algebra (IBA). In fact, the proposed approach is based on a pseudo-logical function in the IBA framework derived from the historical data of publicly available indicators using the DE algorithm. Such functions are easily interpreted and enable a subtle gradation among countries. It is shown that the IBA-DE approach outperforms back-propagation neural networks on the observed problem while also providing a deeper insight into each of the indicators used for prediction and its respective influence on the prediction rating on the other.

show abstract

Section: Introductionsupporting

confidence: 57%

Section: Discussionmentioning

confidence: 99%

Section: Forecasting Sovereign Credit Ratings With the Iba-de Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations