Papers, ranked by score

Ordered by a blend of empirical rigor (60%) and math complexity (40%).

Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents

Benhamou et al.

Financial research agents can generate and monitor trading rules faster than a human can document the resulting selection process. Candidates appear at data-dependent times, weak rules are abandoned, and promising ones are watched until they cross a reporting threshold. We introduce PROMOTE, a…

Holy Grail Math 7.5 Rigor 8.0
Costs: ModeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Eric Benhamou, Jean-Jacques Ohana, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot
Evaluation
Unclear

Penalize the Common Trade: A Collision-Aware Layer for Learned Portfolios

Benhamou et al.

Different learning systems can make nearly the same trade when they share data, objectives, or representations. The market then sees decision concentration even if the models look diverse. We call exposure to this shared direction a signal collision. A linear-impact game shows the basic…

Holy Grail Math 7.5 Rigor 6.0 capped
Costs: ModeledOut-of-sample: UnclearResolution: Weekly-Monthly Data
More details
Authors
Eric Benhamou, Jean-Jacques Ohana, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot
Evaluation
Trading P&L

Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuning

Lefort et al.

In this paper, we demonstrate that non-generative, small-sized models such as FinBERT and FinDRoBERTa, when fine-tuned, can outperform GPT-3.5 and GPT-4 models in zero-shot learning settings in sentiment analysis for financial news. These fine-tuned models show comparable results to GPT-3.5 when it…

Street Traders Math 4.0 Rigor 7.0 Code
Costs: Not applicableOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Baptiste Lefort, Eric Benhamou, Jean-Jacques Ohana, David Saltiel, Beatrice Guez
Evaluation
Forecast accuracy

Stress index strategy enhanced with financial news sentiment analysis for the equity markets

Lefort et al.

This paper introduces a new risk-on risk-off strategy for the stock market, which combines a financial stress indicator with a sentiment analysis done by ChatGPT reading and interpreting Bloomberg daily market summaries. Forecasts of market stress derived from volatility and credit spreads are…

Street Traders Math 2.5 Rigor 6.0 capped
Costs: ModeledOut-of-sample: NoneResolution: Daily Data
More details
Authors
Baptiste Lefort, Eric Benhamou, Jean-Jacques Ohana, David Saltiel, Beatrice Guez, Thomas Jacquot
Evaluation
Trading P&L

Can ChatGPT Compute Trustworthy Sentiment Scores from Bloomberg Market Wraps?

Lefort et al.

We used a dataset of daily Bloomberg Financial Market Summaries from 2010 to 2023, reposted on large financial media, to determine how global news headlines may affect stock market movements using ChatGPT and a two-stage prompt approach. We document a statistically significant positive correlation…

Street Traders Math 2.5 Rigor 6.0 capped
Costs: Not applicableOut-of-sample: NoneResolution: Daily Data
More details
Authors
Baptiste Lefort, Eric Benhamou, Jean-Jacques Ohana, David Saltiel, Beatrice Guez, Damien Challet
Evaluation
Forecast accuracy

Browse

All authors · Research topics · Papers with code · Download the scored dataset

📬 The Quant Space Weekly

One email a week: the most interesting quant finance papers, scored and summarized. No spam, unsubscribe anytime.