ChatGPT can extract forward-looking investment signals from earnings calls. The paper shows that its investment score predicts firm capex up to 9 quarters ahead and negatively forecasts future stock returns—revealing information not yet priced by markets.
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.
Can ChatGPT predict stocks? Yes—GPT-4 applied to headlines yields a high-Sharpe intraday strategy with 650%+ returns. Predictive power emerges only in large models.
This paper shows that ChatGPT-3.5 can predict aggregate U.S. stock returns using WSJ headlines. DeepSeek and smaller LLMs (like BERT) do not match this predictive performance.
This paper introduces a ChatGPT-based Commodity News Ratio Index (CNRI) to forecast excess returns on commodity futures. Using over 2.5 million articles across 18 commodities and 80 years, the CNRI significantly outperforms traditional predictors both in- and out-of-sample.
When the euro gets stronger, European investors tend to sell government bonds from emerging countries if those bonds are in the local currencies of those countries. They do this because a stronger euro means those investments are now worth less to them, even if countries themselves aren’t riskier.
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 compares machine learning methods to predict stock returns and measure equity risk premia. The best-performing model (a 3-layer neural net) earns out-of-sample Sharpe ratios as high as 2.45.
This paper introduces a new class of asset pricing models using autoencoders. By embedding firm characteristics into a neural network architecture, the authors construct a nonlinear conditional factor model that enforces no-arbitrage. It dramatically outperforms linear benchmarks.