FinForesight: A Backtesting Benchmark for Deep Research Financial Forecasting
Fengyuan Liu · hf · 2026-11-05
Researchers from HKU, PolyU, Cambridge and others released FinForesight, a diagnostic backtesting benchmark for deep research systems in financial forecasting.
- Problem: historical backtests can reward memorized outcomes or post-cutoff retrieval, while live forecasting gives slow feedback.
- Method: evaluates forecasting under time-restricted retrieval across three temporal regimes — pretraining-era history (T1), post-cutoff resolved events (T2), and live unresolved events (T3).
- Key claim: backtest-to-live transfer must be explicitly validated, not assumed.
The preprint is dated Nov 1, 2026.
More from Research
- LongTails: 25+ new optimization results with Lean 4-verified proofs, improving known complexity bounds — IgorCarron · 2026-11-05
- The Economist's Babbage podcast asks how science should be reimagined for the AI age — james_y_zou · 2026-11-05
- NYU and Meta FAIR introduce ID-WM, a hierarchical world model beating baselines by 38.5% — ylecun · 2026-11-05
- Guidelight ships Capability Testing standard v1.0 with sandbagging-detection practice — dfrsrchtwts · 2026-11-05
- mjorbit: open-source space robotics simulator runs thousands of parallel worlds on one GPU — ChongZzZhang · 2026-11-05
- CMU paper unifies pretraining, SFT and RL into one likelihood-based algorithm — burny_tech · 2026-11-05