Education & Research on LLMs and Quant Finance | Research Director @ Yale ICF | Managing Editor @ Journal of Financial Data Science | Data Science PhD
Joined May 2020
- Tweets27
- Following181
- Followers126
- Likes88
Finding edgartools to be the best Python package for downloading financial statements from the SEC. This video provides a great overview👇
youtube.com/watch?v=mI6KDerA…
2
212
I often see researchers reaching for LLMs when smaller, embeddings-based models would not only suffice but could also outperform at a fraction of the cost. Before choosing an approach, ask if you have a well-labeled training dataset—sometimes a simpler model is the better fit.
122
Financial markets are complex, and linear approximations of input variables to asset returns fail to capture this complexity. Predictability can be improved by examining large-scale interactions among predictive variables, even when fitting with a linear model—just don’t forget to regularize!
1
1
265
On this point, an under-appreciated paper related to this work is the "Deep Regression Ensembles" paper by Didisheim, Kelly, and Malamud.
Link: arxiv.org/abs/2203.05417
83
For those looking to get started in #FinancialNLP, the Financial Phrasebank dataset on Huggingface is a great place to start playing with LLMs!
huggingface.co/datasets/taka…
1
81
When using LLMs in financial backtesting, a common question is: "Doesn't ChatGPT have forward-looking bias?" 🤔
Paul Glasserman and Caden Lin dive into this in their paper "Assessing Look-Ahead Bias in Stock Return Predictions Generated by GPT Sentiment Analysis."
Their study backtests ChatGPT-based sentiment trading strategies, comparing portfolios with and without anonymized headlines (masking company identifiers). Interestingly, portfolios using anonymized headlines outperform those with original headlines. Why? 🧠
Their findings suggest that including company names creates a “distraction effect,” where the model fixates on names rather than sentiment—a stronger effect than any look-ahead bias! 📉
This work is critical for advancing GPT models in trading and portfolio construction. I’ve observed similar results in my own research too.
Paper: pm-research.com/content/iijj…
1
148
These @notebooklm_pods podcasts are crazy! @ProfJimLiew just sent me a podcast he generated based on my paper, "Cut the Chit-Chat". A bit too much embellishment but otherwise amazing!
1
2
173
Paper link: papers.ssrn.com/sol3/papers.…
Associated repo: github.com/francescoafabozzi…
1
103
1/ 🚀 Sentiment analysis in finance is evolving.
As we move from encoder-only (i.e., embeddings) models to generative language models (GLMs), we must update the research toolset for leveraging this new and rapidly growing class of large language models.
5/ 💻 To make Logit Extraction accessible, I've developed a Python package, TokenProbs, now available on GitHub and PyPi.
PyPi: pypi.org/project/TokenProbs/
GitHub: github.com/francescoafabozzi…
1
73
6/ Follow me here for more insights into cutting-edge applications of LLMs for Finance, and stay tuned for tools, research, and practical tips!
#GenAI #Finance #LLMs #Python #SentimentAnalysis
57
My latest paper, "News-Based Sentiment and the Value Premium," published in #JournalofInternationalMoneyandFinance, is now available in print #valuepremium #sentiment #news #finance
authors.elsevier.com/a/1hBJg…
162
Francesco A. Fabozzi retweeted
Asset Management: Tools and Issues (World Scientific, 2020) provides a gentle introduction to the world of quantitative asset management: amazon.com/dp/B08QG9YY3C/
More publications on the topic can be found here (many of them for free): QuantResearch.org
Francesco A. Fabozzi retweeted
The Journal of Financial Data Science @PM_Research_ provides an analytical look at how big data & machine learning can be used to strengthen financial decisions. Download a copy of the latest issue, featuring leading research in the field of data science: bit.ly/3cUsZ2o
