MGPraxis6,400 papers identified by name

LLM-Driven Investment Models: Can Large Language Models Extract Alpha from Earnings Call Transcripts?

Akash Ghosal·2026

Ghosal (2026) studies news sentiment and text signals in equities using a large language model over 2019–2023. The abstract mentions alpha, an out-of-sample test and transaction costs but not a benchmark, multiple testing or the size of the universe.

“Compared with a TF-IDF benchmark model, LLM embeddings produce stronger risk-adjusted performance and improved portfolio stability.”

AssetEquities
StrategyNews sentimentmachine learning
TechniqueLarge language model
Sample window2019–2023

Also stated: Alpha, Fundamentals, Text and news, out-of-sample test, costs

Missing from abstract: benchmark, multiple testing, universe

Institutional-grade audit of this strategy.
£5 — Request the audit
  • Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
  • Reproduction code integratable into Bloomberg, IBKR, etc.
  • Bias-free datasets for backtesting included
  • Delivered in 2 working days
The paper's neighbourhoodNews sentiment and text signals by year
■ equities■ crypto■ commodities■ currencies■ other assets20102015202073This paper2026■ equities■ crypto■ commodities■ currencies■ other assets20102015202073This paper2026
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
Similar paperscitationsame methodsame assetsame authors
LLM-Driven Investment Models: Evidence from Earnings Call Transcripts by Ghosal2026
Execution-Aware Alpha Mining: Teaching LLM Factor Agents to Account for Trading Costs​ by Nagireddy2026
Memorisation or Alpha? Detecting Look-Ahead Contamination in Cross-Sectional Equity Signals by Nguyen2026
Beta Recall, Alpha Recall, and a Contamination Detector that Needs No Labels * Measuring Training-data Leakage in LLM Equity Signals by Nguyen2026
LLM-Based High-Growth Potential Ranking and Portfolio Selection: Evidence from China's Optical Industry by Lin and Xue2026
Not yet audited by MarketGraphs Praxis. Tags from the abstract. Counts from the universe.
RSS · Contacts