Izvorni znanstveni članak

https://doi.org/10.17559/TV-20221110173532

Internet Financial Credit Risk Assessment with Sliding Window and Attention Mechanism LSTM Model

Menggang Li ; 1) National Academy of Economic Security, Beijing Jiaotong University, Beijing 100044, China 2) Beijing Laboratory of National Economic Security Early-warning Engineering, Beijing Jiaotong University, Beijing 100044, China 3) Beijing Center for Industrial Security and Development Research, Beijing Jiaotong University, Beijing 100044, China
Zixuan Zhang ; Business School, The University of Hong Kong, Hong Kong
Ming Lu ; School of Economics and Management, Beijing Jiaotong University, Beijing 100044, China
Xiaojun Jia ; 1) National Academy of Economic Security, Beijing Jiaotong University, Beijing 100044, China 2) Beijing Center for Industrial Security and Development Research, Beijing Jiaotong University, Beijing 100044, China
Rui Liu ; Graduate School, Lyceum of the Philippines University Manila, Manila 1002, Philippines
Xuan Zhou ; 1) National Academy of Economic Security, Beijing Jiaotong University, Beijing 100044, China 2) Beijing Laboratory of National Economic Security Early-warning Engineering, Beijing Jiaotong University, Beijing 100044, China
Yingjie Zhang ; School of Economics and Management, Beijing Jiaotong University, Beijing 100044, China

Sažetak

With the accelerated pace of market-oriented reform, Internet finance has gained a broad and healthy development environment. Existing studies lack consideration of time trends in financial risk, and treating all features equally may lead to inaccurate predictions. To address the above problems, we propose an LSTM model based on sliding window and attention mechanism. The model uses sliding windows to enable the model to effectively exploit the contextual relevance of loan data. And we introduce the attention mechanism into the model, which enables the model to focus on important information. The result on the Lending Club public desensitization dataset shows that our model outperforms ARIMA, SVM, ANN, LSTM, and GRU models.

Ključne riječi

attention mechanism; credit risk; internet finance; LSTM; sliding window; time-series prediction

Hrčak ID:

285606

URI

https://hrcak.srce.hr/285606

Datum izdavanja:

15.12.2022.

Posjeta: 1.443 *