VWAP Execution with Signature-Enhanced Transformers: A Multi-Asset Learning Approach
This work offers a scalable and robust approach to VWAP execution for traders, though it is incremental as it builds upon existing transformer and signature methods.
The paper tackles the problem of Volume Weighted Average Price (VWAP) execution by proposing a single neural network trained across multiple assets to address asset-specific model training and capture complex temporal dependencies, achieving superior performance in absolute and quadratic VWAP loss metrics on cryptocurrency trading data from 80 pairs, with improvements persisting for out-of-sample assets.
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 execution arXiv: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 by arXiv:2406.02486 with path signatures for capturing geometric features of price-volume trajectories, as in arXiv: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.