Towards Explainable Deep Learning for Credit Lending: A Case Study
arXiv:1811.06471v220 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental study for the financial services industry, focusing on applying known methods to a specific domain.
The paper tackles the problem of limited deep learning adoption in financial services due to lack of interpretability by investigating existing explanation techniques for credit risk assessment with neural networks, but does not report concrete results or numbers.
Deep learning adoption in the financial services industry has been limited due to a lack of model interpretability. However, several techniques have been proposed to explain predictions made by a neural network. We provide an initial investigation into these techniques for the assessment of credit risk with neural networks.