Quantum Temporal Fusion Transformer
By: Krishnakanta Barik, Goutam Paul
Potential Business Impact:
Quantum computer predicts future better than old ones.
The Temporal Fusion Transformer (TFT), proposed by Lim et al. [\textit{International Journal of Forecasting}, 2021], is a state-of-the-art attention-based deep neural network architecture specifically designed for multi-horizon time series forecasting. It has demonstrated significant performance improvements over existing benchmarks. In this work, we propose a Quantum Temporal Fusion Transformer (QTFT), a quantum-enhanced hybrid quantum-classical architecture that extends the capabilities of the classical TFT framework. Our results demonstrate that QTFT is successfully trained on the forecasting datasets and is capable of accurately predicting future values. In particular, our experimental results display that in certain test cases, the model outperforms its classical counterpart in terms of both training and test loss, while in the remaining cases, it achieves comparable performance. A key advantage of our approach lies in its foundation on a variational quantum algorithm, enabling implementation on current noisy intermediate-scale quantum (NISQ) devices without strict requirements on the number of qubits or circuit depth.
Similar Papers
Adaptive Temporal Fusion Transformers for Cryptocurrency Price Prediction
Statistical Finance
Predicts crypto prices better for trading.
Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales
Machine Learning (CS)
Predicts store sales accurately for better stocking.
CNN-TFT explained by SHAP with multi-head attention weights for time series forecasting
Machine Learning (CS)
Predicts future events more accurately using past data.