VWAP Execution with Signature-Enhanced Transformers: A Multi-Asset Learning Approach

In this paper I propose a novel approach to Volume Weighted Average Price (VWAP) execution that addresses two key practical challenges: the need for asset-specific model training and the capture of complex temporal dependencies. Building upon my recent work in dynamic VWAP executionarXiv:2502.18177, I demonstrate that a single neural network trained across multiple assets can achieve performance comparable to or better than traditional asset-specific models. The proposed architecture combines a transformer-based design inspired byarXiv:2406.02486with path signatures for capturing geometric features of price-volume trajectories, as inarXiv:2406.17890. The empirical analysis, conducted on hourly cryptocurrency trading data from 80 trading pairs, shows that the globally-fitted model with signature features (GFT-Sig) achieves superior performance in both absolute and quadratic VWAP loss metrics compared to asset-specific approaches. Notably, these improvements persist for out-of-sample assets, demonstrating the model's ability to generalize across different market conditions. The results suggest that combining global parameter sharing with signature-based feature extraction provides a scalable and robust approach to VWAP execution, offering significant practical advantages over traditional asset-specific implementations.

@article{genet2025_2503.02680,
  title={ VWAP Execution with Signature-Enhanced Transformers: A Multi-Asset Learning Approach },
  author={ Remi Genet },
  journal={arXiv preprint arXiv:2503.02680},
  year={ 2025 }
}