Compares counterfactual generation methods with balancing strategies on bank failure data, finding NICF with cost-sensitive learning produces the highest quality explanations on validity, proximity, and sparsity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk
Compares counterfactual generation methods with balancing strategies on bank failure data, finding NICF with cost-sensitive learning produces the highest quality explanations on validity, proximity, and sparsity.