Answers are grounded in this paper and cite their sources.
Forecasting financial asset returns is challenging due to low signal‐to‐noise ratios, nonstationarity and heavy‐tailed distributions. We benchmark 16 deep learning architectures for time series forecasting, including Transformers, State Space Models (SSMs), xLSTMs, and recurrent hybrids, on a 15‐year daily futures dataset using an end‐to‐end volatility‐targeted Sharpe ratio optimization task. Our results challenge prevailing assumptions in the literature. Several widely used “state‐of‐the‐art” architectures, including generic Transformers and SSMs, underperformed a simple AR(1) benchmark in a realistic financial forecasting task. The strongest results came from comparatively simple hybrid approaches using recurrent structures: a Variable Selection Network combined with an LSTM achieved the highest Sharpe ratio, while xLSTM showed the greatest robustness to transaction costs. These findings suggest that success on standard time‐series benchmarks does not reliably transfer to finance, and that architectures tailored to the unique properties of asset returns may remain more effective than generic attention‐based approaches for financial forecasting.
No takes yet. Share an insight, caveat, or question.
Saly-Kaufmann et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: