用KAN改进GRU/LSTM，提前8个月预测贷款违约
Kolmogorov-Arnold Networks-based GRU and LSTM for Loan Default Early Prediction
- 将Kolmogorov-Arnold网络融合进GRU和LSTM架构
- 提前3个月预测准确率超92%，8个月达88%以上
- 适合需要早期风控的金融机构使用
本研究针对时间序列异常检测中的关键挑战——提升贷款违约模型在风险事件发生前超过三个月的预测能力，以实现早期识别违约事件，帮助金融机构在风险发生前采取预防措施。现有方法存在早期预测精度不足、依赖同年内训练测试等缺陷，限制了其在跨时序数据上的实际应用。为此，本文提出两种创新架构：GRU-KAN与LSTM-KAN，将柯尔莫戈洛夫-阿诺德网络（KAN）与门控循环单元（GRU）及长短期记忆网络（LSTM）结合。在不同特征窗口长度、样本规模和提前预测区间下，对比基线模型（LSTM、GRU、LSTM-Attention、LSTM-Transformer）的准确率、精确率、召回率、F1值与AUC指标。结果表明，所提模型在提前3个月预测中准确率超过92%，提前8个月仍保持88%以上，显著优于现有基线。
原文摘要 · Abstract (English)
This study addresses a critical challenge in time series anomaly detection: enhancing the predictive capability of loan default models more than three months in advance to enable early identification of default events, helping financial institutions implement preventive measures before risk events materialize. Existing methods have significant drawbacks, such as their lack of accuracy in early predictions and their dependence on training and testing within the same year and specific time frames. These issues limit their practical use, particularly with out-of-time data. To address these, the study introduces two innovative architectures, GRU-KAN and LSTM-KAN, which merge Kolmogorov-Arnold Networks (KAN) with Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) networks. The proposed models were evaluated against the baseline models (LSTM, GRU, LSTM-Attention, and LSTM-Transformer) in terms of accuracy, precision, recall, F1 and AUC in different lengths of feature window, sample sizes, and early prediction intervals. The results demonstrate that the proposed model achieves a prediction accuracy of over 92% three months in advance and over 88% eight months in advance, significantly outperforming existing baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。