A TCN plus Attention-LSTM model trained on 2014-2024 Chinese A-share data outperforms static baselines and identifies prolonged undervaluation as the long-term driver and sudden cash-flow increases as the short-term trigger for repurchases.
En- hancing the locality and breaking the memory bottle- neck of transformer on time series forecasting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamic Forecasting and Temporal Feature Evolution of Stock Repurchases in Listed Companies Using Attention-Based Deep Temporal Networks
A TCN plus Attention-LSTM model trained on 2014-2024 Chinese A-share data outperforms static baselines and identifies prolonged undervaluation as the long-term driver and sudden cash-flow increases as the short-term trigger for repurchases.