A GRU-KAN hybrid predicts loan defaults 3 and 8 months ahead with reported accuracies of 92% and 88% on a balanced Freddie Mac test set, outperforming LSTM, GRU, and attention baselines.
Stabilizing machine learning models with Age-Period- Cohort inputs for scoring and stress testing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Kolmogorov-Arnold Networks-based GRU and LSTM for Loan Default Early Prediction
A GRU-KAN hybrid predicts loan defaults 3 and 8 months ahead with reported accuracies of 92% and 88% on a balanced Freddie Mac test set, outperforming LSTM, GRU, and attention baselines.