Institution profile

School of Computing and Information

Academic institution
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Adaptive Temporal Fusion Transformers for Cryptocurrency Price Prediction

Sep 06, 2025

To address the low accuracy of short-term cryptocurrency price forecasting caused by high volatility and non-stationarity, this paper proposes an Adaptive Temporal Fusion Transformer (ATFT) framework. The method introduces three key innovations: (1) a dynamic subsequence partitioning mechanism based on relative extrema; (2) subsequence categorization according to fixed-pattern endings to decouple and model distinct market response patterns; and (3) a multi-branch Temporal Fusion Transformer architecture that integrates initial trend features to enable conditional forecasting. Evaluated on 10-minute ETH-USDT data, ATFT achieves statistically significant improvements over standard TFT and LSTM in both prediction error (MAE/RMSE) and simulated trading profitability. These results empirically validate the effectiveness of pattern-aware modeling for high-frequency cryptocurrency asset forecasting.

0 citationsRead paper
Recent publications

Latest Papers

Adaptive Temporal Fusion Transformers for Cryptocurrency Price Prediction

Sep 06, 2025

To address the low accuracy of short-term cryptocurrency price forecasting caused by high volatility and non-stationarity, this paper proposes an Adaptive Temporal Fusion Transformer (ATFT) framework. The method introduces three key innovations: (1) a dynamic subsequence partitioning mechanism based on relative extrema; (2) subsequence categorization according to fixed-pattern endings to decouple and model distinct market response patterns; and (3) a multi-branch Temporal Fusion Transformer architecture that integrates initial trend features to enable conditional forecasting. Evaluated on 10-minute ETH-USDT data, ATFT achieves statistically significant improvements over standard TFT and LSTM in both prediction error (MAE/RMSE) and simulated trading profitability. These results empirically validate the effectiveness of pattern-aware modeling for high-frequency cryptocurrency asset forecasting.

0 citationsRead paper