How Good Are LLMs at Sentiment Scoring?
We find that open-weight models, especially in an ensemble, approach frontier models’ performance. As with labeling, sentiment scoring is now…
Data Science
Local LLMs can now handle ticker mapping for alternative data
Benchmarking open-weight LLMs for alt data pipelines
How good are LLMs at tickerization?
For data to be marketable to investors, it usually must be mapped to asset-level identifiers, commonly known as tickers. An…
Your LLM’s alpha might be mere memorization
A new benchmark, Look-Ahead-Bench, shows that LLM-based investment strategies can generate spectacular in-sample alpha that collapses once the test window…
Why quants pay more for point-in-time data
When quant investors encounter a new dataset, one of the first questions they ask is whether the data is “point-in-time”…
Whose data is worth more?
A tale of two data vendors Imagine two companies go into business selling data to hedge funds. Both analyze satellite…