Credit Risk Prediction Model for Listed Companies Based on CNN-LSTM and Attention Mechanism

Abstract

The financial market has been developing rapidly in recent years, and the issue of credit risk concerning listed companies has become increasingly prominent. Therefore, predicting the credit risk of listed companies is an urgent concern for banks, regulators and investors. The commonly used models are the Z-score, Logit (logistic regression model), the kernel-based virtual machine (KVM) and neural network models. However, the results achieved could be more satisfactory. This paper proposes a credit-risk-prediction model for listed companies based on a CNN-LSTM and an attention mechanism, Our approach is based on the benefits of the long short-term memory network (LSTM) model for long-term time-series prediction combined with a convolutional neural network (CNN) model. Furthermore, the advantages of being integrated into a CNN-LSTM model include reducing the complexity of the data, improving the calculation speed and training speed of the model and solving the possible lack of historical data in the long-term sequence prediction of the LSTM model, resulting in prediction accuracy. To reduce problems, we introduced an attention mechanism to assign weights independently and optimize the model. The results show that our model has distinct advantages compared with other CNNs, LSTMs, CNN-LSTMs and other models. The research on the credit-risk prediction of the listing formula has significant meaning.

Influencing the Variable Selection and Prediction of Carbon Emissions in China

“…At the same time, large and small values in the data will affect the robustness of the model, leading to a large error in the prediction effect compared to the actual. Therefore, a new model (called CNN-LSTM model) is built by combining the advantages of extracting CNN and LSTM, respectively, which makes full use of CNN's feature information extraction capability and LSTM's sensitivity to time series data [25][26][27][28], thus improving the prediction of carbon dioxide emissions.…”

Implementation of a Fusion Classification Model for Efficient Pen-Holding Posture Detection

“…For example, recent work in urban planning has shown that CNNs can be combined with LSTM models to predict particulate matter such as PM2.5 (very small particles in air with diameters less than or equal to 2.5 µm) in urban areas, as shown in the work of [28]. The fusion model can also be used to predict other things, such as credit risk prediction [29] and emotion monitoring [30]. All experimental results proved that the fusion model has the highest prediction accuracy.…”