Fig 1.
LTR-Net model architecture: a financial data prediction and risk assessment framework combining LSTM, transformer, and ResNet.
Fig 2.
LSTM module architecture: application of long short-term memory networks in financial data prediction.
Fig 3.
Multi-head self-attention and feed-forward network in attention mechanism.
Fig 4.
Application of ResNet.
Table 1.
Dataset overview: financial distress and stock market data.
Table 2.
Experimental results comparison between LTR-Net and other state-of-the-art models on two datasets.
Fig 5.
Visualize the results of running the model on two datasets.
Fig 6.
Comparison of actual vs. predicted financial values.
Table 3.
Ablation experiment results on Kaggle financial distress dataset.
Table 4.
Ablation experiment results on Yahoo finance dataset.
Fig 7.
LTR-Net rendering after removing some modules.