ML-QuantSubscribe

SSRNLLMs & Text

Look-Ahead Bias in Stock Return Predictions

Large language models like ChatGPT can generate profitable trading signals from news sentiment, but backtesting can yield biased results due to overlapping periods.

Featured in No. 18 on 4 Oct 2023 · 6 days after release

Released
28 Sep 2023
First featured
No. 18 · 4 Oct 2023
Published in
Not yet, as far as Semantic Scholar knows
Shares when featured
5
Identifier
SSRN 4586726

Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).

    Type to search. Try rough volatility, LLM agents or FinGPT.

    ↑↓ move↵ openesc closeFull search page