@inproceedings{f4e90eea7bf142f7838382a914ee4199,
title = "Bayesian Automatic Relevance Determination for Feature Selection in Credit Default Modelling",
abstract = "This work develops a neural network based global model interpretation mechanism - the Bayesian Neural Network with Automatic Relevance Determination (BNN-ARD) for feature selection in credit default modelling. We compare the resulting selected important features to those obtained from the Random Forest (RF) and Gradient Tree Boosting (GTB). We show by re-training the models on the identified important features that the predictive quality of the features obtained from the BNN-ARD is similar to that of the GTB and outperforms those of RF in terms of the predictive performance of the retrained models.",
keywords = "Automatic Relevance Determination, Bayesian, Credit default modelling, Hybrid Monte Carlo, Neural networks",
author = "Rendani Mbuvha and Illyes Boulkaibet and Tshilidzi Marwala",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 28th International Conference on Artificial Neural Networks, ICANN 2019 ; Conference date: 17-09-2019 Through 19-09-2019",
year = "2019",
month = sep,
day = "11",
doi = "10.1007/978-3-030-30493-5_42",
language = "English",
isbn = "9783030304928",
series = "Lecture Notes in Computer Science",
publisher = "Springer Cham",
pages = "420--425",
editor = "Vera Kurkov{\'a} and Tetko, {Igor V.} and Pavel Karpov and Fabian Theis",
booktitle = "Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions",
address = "Switzerland",
}