Sentiment Indicators

Throughout each month, the National Federation of Independent Businesses surveys members on ten components of business conditions they anticipate six months hence. They issue findings on the second Tuesday of the following month in “Small Business Economic Trends”, including a Small Business Optimism Index (SBOI). Are the expectations of responding small business owners a “grass roots” predictor of U.S. stock market behavior? To check, we relate changes in SBOI to U.S. stock market returns. Using monthly levels of SBOI, the S&P 500 Index (a proxy for the U.S. stock market) and the Russell 2000 Index (representing smaller stocks) during January 2003 through January 2024, we find that: Keep Reading

Is ChatGPT useful for predicting stock market returns based on financial news headlines? In the December 2023 version of their paper entitled “ChatGPT, Stock Market Predictability and Links to the Macroeconomy”, Jian Chen, Guohao Tang, Guofu Zhou and Wu Zhu investigate whether ChatGPT 3.5 can predict U.S. stock market (S&P 500 Index) returns based on Wall Street Journal front-page news headlines/alerts. The instruction they give ChatGPT 3.5 is:

“Forget all previous instructions. You are now a financial expert giving investment advice. I’ll give you a news headline, and you need to answer whether this headline suggests the U.S. stock prices are GOING UP or GOING DOWN. Please choose only one option from GOING UP, GOING DOWN, UNKNOWN, and do not provide any additional responses.”

They first compute monthly ratios of good news to total news (NR^G) and bad news to total news (NR^B) and then relate these ratios to S&P 500 Index excess returns over the next 1, 3, 6, 9 or 12 months. They compare the ability of ChatGPT to predict returns to that of traditional human interpretation and to those of BERT and RoBERTa as ChatGPT alternatives. Using daily Wall Street Journal front-page news headlines/alerts and monthly S&P 500 Index excess returns during January 1996 through December 2022, they find that:

Keep Reading

Can ChatGPT find red flags in firm earnings calls? In their January 2024 paper entitled “Unusual Financial Communication – Evidence from ChatGPT, Earnings Calls, and the Stock Market”, Lars Beckmann, Heiner Beckmeyer, Ilias Filippou, Stefan Menze and Guofu Zhou test the ability of ChatGPT-4 Turbo to identify and analyze unusual content and tone aspects of S&P 500 earnings calls. Unusualness has 25 dimensions derived from executive behaviors, analyst questions, specific content or technical issues. They examine correlations of unusualness with firm characteristics, industry and macroeconomic indicators across business cycles. They validate unusualness by looking at associated stock returns and trading volumes from one day before through one day after earnings calls. Using transcripts of S&P 500 earnings calls from Refinitiv, firm characteristics/stock trading data and macroeconomic data during January 2015 through December 2022, they find that:

Keep Reading

The quarterly CFO Survey asks chief financial officers, owner-operators, vice presidents and directors of finance, accountants, controllers, treasurers and others with financial decision-making roles in small to very large companies across all major industries to “rate optimism about the overall U.S. economy on a scale from 0 to 100.” Does the average economic sentiment of these financial experts predict U.S. stock market returns? To investigate, we relate quarterly sentiment averages and quarterly changes in these averages to quarterly S&P 500 Index (SP500) returns. Using the specified quarterly data during June 2002 through December 2023, we find that:

Keep Reading

Do different proxies for investor disagreement widely used as stock return predictors (analyst forecast dispersion, idiosyncratic volatility and trading volume) generally agree? In their November 2023 paper entitled “Disagreement of Disagreement”, Christian Goulding, Campbell Harvey and Hrvoje Kurtović examine relationships among these three types of investor disagreement and propose a non-linear composite of them. They then test the ability of this composite metric to predict differences in stock returns. Using daily data for all publicly traded U.S. firms with stock prices over $5 and adequate price series during January 1994 through December 2016, they find that:

Keep Reading

Does financial news sentiment as interpreted by large language models (LLM) such as ChatGPT and BARD predict short-term stock market returns? In their September 2023 paper entitled “Large Language Models and Financial Market Sentiment”, Shaun Bond, Hayden Klok and Min Zhu separately test the abilities of ChatGPT and BARD to predict daily, weekly and monthly S&P 500 Index returns based on sentiments they extract from daily financial news summaries. ChatGPT is trained on information available on the web through September 2021. In contrast, BARD is connected to the web and updates itself on live information. The authors:

1. Ask each of ChatGPT and BARD to summarize the most important news from the Thomson Reuters News Archives for each trading day starting in January 2000.
2. Consolidate each set of daily summaries.
3. Ask each of ChatGPT and BARD to use their respective set of summaries to quantify market sentiment each day on a scale from 1 (weakest) to 100 (strongest) and separately evaluate the sentiment as positive, neutral or negative.
4. Relate via regressions each set of daily sentiment measurements to next-day, next-week and next-month S&P 500 Index returns. These regressions control for same-day index return, VIX, short-term credit risk and the term spread (plus additional variables when predicting monthly returns). 

For ChatGPT, analysis extends through September 2021 (the end of its training period). For BARD, analysis continues through July 2023. As benchmarks, they consider sentiment measurements from two traditional dictionary methods and two simple transformer classifiers. To estimate economic value of predictions, they compute certainty equivalent returns (CER) for a mean-variance investor who allocates between the S&P 500 Index and a risk-free asset each day according to out-of-sample sentiment measurements starting in 2006. Using Thomson Reuters News Archives and daily, weekly and monthly S&P 500 Index returns since January 2000, they find that: Keep Reading

Does quantified uncertainty in government economic policy reliably predict stock market returns? To investigate, we consider the U.S. Economic Policy Uncertainty (EPU) Index, created by Scott Baker, Nicholas Bloom and Steven Davis and constructed from three components:

1. Coverage of policy-related economic uncertainty by prominent newspapers.
2. Number of temporary federal tax code provisions set to expire in future years.
3. Level of disagreement in one-year forecasts among participants in the Federal Reserve Bank of Philadelphia’s Survey of Professional Forecasters for both (a) the consumer price index (CPI) and (b) purchasing of goods and services by federal, state and local governments.

They normalize each component by its own standard deviation prior to 2012 and then compute a weighted average of components, assigning a weight of one half to news coverage and one sixth each to tax code uncertainty, CPI forecast disagreement and government purchasing forecast disagreement. They update the index monthly at the beginning of the following month, potentially revising recent months. Using monthly levels of the EPU Index and the S&P 500 Index during January 1985 through August 2023, we find that: Keep Reading

A subscriber asked how Apple Inc. (AAPL) stock behaves around unveiling of new iPhone models. To investigate, we identify 19 distinct iPhone series release dates from 6/29/07 through 9/16/22 and calculate average daily cumulative returns for AAPL from 21 trading days before release date (Day 0) through 63 trading days after release date. Two pairs of iPhone release dates overlap somewhat for this specification. As a benchmark, we calculate average daily cumulative returns for AAPL during this interval for all trading days. In case there is some confounding factor (seasonal?), we repeat these calculations for Invesco QQQ Trust (QQQ). Using the selected iPhone series release dates and daily dividend/split-adjusted prices for AAPL and QQQ from the end of May 2007 through mid-December 2022, we find that: Keep Reading

Business media and expert commentators sometimes cite the monthly University of Michigan Consumer Sentiment Index as an indicator of U.S. economic and stock market health, generally interpreting a jump (drop) in sentiment as good (bad) for future consumption and stocks. The release schedule for this indicator is mid-month for a preliminary reading on the current month and end-of-month for a final reading. Is this indicator predictive of U.S. stock market behavior in subsequent months? Using monthly final Consumer Sentiment Index data and monthly levels of the S&P 500 Index during January 1978 through July 2023, we find that: Keep Reading

Do stock market return volatility (as a measure of risk) and aggregate investor sentiment (as a measure of risk tolerance) work well jointly to explain stock market returns? In their June 2023 paper entitled “Time-varying Equity Premia with a High-VIX Threshold and Sentiment”, Naresh Bansal and Chris Stivers investigate the in-sample power an optimal CBOE Volatility Index (VIX) threshold rule and a linear Baker-Wurgler investor sentiment relationship to explain future variation in U.S. stock market excess return (relative to U.S. Treasury bill yield). They skip one month between VIX/sentiment measurements and stock market returns to accommodate investor digestion of new information. They consider return horizons of 1, 3, 6 and 12 months. They also extend this 2-factor model to include the lagged Treasury implied-volatility index (ICE BofAML MOVE Index) as a third explanatory variable. Using monthly excess stock market return and VIX during January 1990 through December 2022, monthly  investor sentiment during January 1990 through June 2022 and monthly MOVE index during October 1997 through December 2022, they find that:

Keep Reading