# WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series

arXiv: https://arxiv.org/abs/1909.10801 · HTML: https://mlsanity.com/paper/1909.10801/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Latent State Space Models for Time-Series Generation](https://mlsanity.com/paper/2212.12749/) (2022)
- [Reinforcement Learning for Quantitative Trading](https://mlsanity.com/paper/2109.13851/) (2021)
- [Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path](https://mlsanity.com/paper/2208.11639/) (2022)
- [Optimizing Trading Strategies in Quantitative Markets using Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.11959/) (2023)
- [Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance](https://mlsanity.com/paper/2307.03119/) (2023)
- [Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2210.07636/) (2022)
- [A Framework for Incentivized Collaborative Learning](https://mlsanity.com/paper/2305.17052/) (2023)
- [CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification](https://mlsanity.com/paper/2203.04298/) (2022)

## Abstract (arXiv)

Finance is a particularly challenging application area for deep learning models due to low noise-to-signal ratio, non-stationarity, and partial observability. Non-deliverable-forwards (NDF), a derivatives contract used in foreign exchange (FX) trading, presents additional difficulty in the form of long-term planning required for an effective selection of start and end date of the contract. In this work, we focus on tackling the problem of NDF tenor selection by leveraging high-dimensional sequential data consisting of spot rates, technical indicators and expert tenor patterns. To this end, we construct a dataset from the Depository Trust & Clearing Corporation (DTCC) NDF data that includes a comprehensive list of NDF volumes and daily spot rates for 64 FX pairs. We introduce WaveATTentionNet (WATTNet), a novel temporal convolution (TCN) model for spatio-temporal modeling of highly multivariate time series, and validate it across NDF markets with varying degrees of dissimilarity between the training and test periods in terms of volatility and general market regimes. The proposed method achieves a significant positive return on investment (ROI) in all NDF markets under analysis, outperforming recurrent and classical baselines by a wide margin. Finally, we propose two orthogonal interpretability approaches to verify noise stability and detect the driving factors of the learned tenor selection strategy.