arXiv q-fin· Adir Saly-Kaufmann, Kieran Wood, Jan-Peter Calliess, Stefan Zohren·· 1 days agoAI Score58
How Well Do Standard Time-Series Forecasting Benchmarks Transfer to Finance? A Large-Scale Study Covering Risk-Adjusted Performance
How do standard time series forecasting benchmarks translate to finance? A broad study of risk adjusted performance
AI summary
This paper tests 16 deep learning time-series forecasting architectures on a 15-year daily futures dataset, using end-to-end volatility-targeted Sharpe ratio optimization as the benchmark, covering Transformers, state space models (SSMs), xLSTM, and recurrent hybrid architectures.
Source:arXiv q-fin · arxiv.org