Strategies reacting to corporate events like earnings, mergers, or insider activity.
This paper introduces a multi-step prompt strategy called Classify-and-Rethink (CAR) to help ChatGPT overcome behavioral biases—especially the framing effect—in financial decision-making. Applied to gold news, CAR improves score rationality and generates higher Sharpe ratios.
This paper introduces HAID—a novel measure that captures new information in earnings call Q&As by comparing executive answers to ChatGPT’s responses. A higher HAID predicts more trading, stronger price reactions, improved analyst forecasts, and greater liquidity.
ChatGPT-based sentiment from full earnings call transcripts predicts stock returns up to six months ahead. After its democratization, retail investors’ trading aligns more closely with AI insights—narrowing the gap with informed traders.
ChatGPT can generate profitable day trading signals by analyzing real-time Twitter news and selecting stock tickers to buy and sell. The strategy earns significant intraday alpha, especially from short positions, even without firm-specific prompts.
This paper shows that hedge funds adopting ChatGPT saw a 3–5% boost in annualized returns post-2022.
ChatGPT can classify Federal Reserve policy tone and identify monetary shocks with high accuracy—matching or outperforming traditional methods. The paper shows GPT-4 can replicate expert-level reasoning, offering a powerful tool for analyzing central bank communication.
ChatGPT can classify crypto tweets into bullish or bearish and predict Bitcoin returns better than BERT or VADER. Its sentiment signals show strong predictive power for daily returns.
ChatGPT can predict future UK interest rate decisions by analyzing central bank speeches—turning policy tone into a reliable forecasting signal.
ChatGPT can turn bloated disclosures into sharp summaries. The sentiment from these summaries predicts stock returns better than traditional methods — revealing alpha in plain sight.
This paper shows that a simple, model-free valuation approach using all available accounting data can identify stock mispricing. A strategy that buys underpriced and sells overpriced firms earns **4–10% alpha per year**, outperforming many known anomalies—even without complex valuation models.
Short sellers face unique risks, including loan recalls and rising borrow fees. This paper shows that higher short-selling risk predicts **lower future returns**, **more mispricing**, and **less efficient prices**. These effects are stronger for trades with long expected horizons.
This paper develops the Policy Change Index (PCI) for China, a machine learning-based, language-free signal that predicts upcoming policy shifts by analyzing the page placement of articles in the People’s Daily. The PCI successfully anticipates major Chinese policy events.