Academic Finance Research and Insights

Social Media: The Value of Seeking Alpha’s Recommendations

By |May 17th, 2024|Larry Swedroe, Research Insights, Guest Posts, Behavioral Finance, Active and Passive Investing|

The finding that the recommendations from SA articles resulted in statistically significant risk-adjusted alphas (returns unexplained by conventional academic models using factors such as the market, size, value, momentum, profitability, and quality for equity portfolios) is surprising given that the empirical evidence shows how difficult it is for institutional investors such as mutual funds to show outperformance beyond the randomly expected (as can be seen in the annual SPIVA Scorecards) because of market efficiency.

Comments Off on Social Media: The Value of Seeking Alpha’s Recommendations

How Volatility and Turnover Affect Return Reversals

By |May 13th, 2024|Volatility (e.g., VIX), Liquidity Factor, Transaction Costs, Research Insights, Factor Investing, Basilico and Johnsen, Academic Research Insight, Momentum Investing Research|

Higher volatility is associated with faster, initially stronger reversals, while lower turnover is associated with more persistent, ultimately stronger reversals

Comments Off on How Volatility and Turnover Affect Return Reversals

Using Machine Learning Programs to Forecast the Equity Risk Premium

By |May 10th, 2024|Larry Swedroe, Factor Investing, Research Insights, Guest Posts, AI and Machine Learning, Other Insights, Macroeconomics Research|

To date, the best metric we have for forecasting future equity returns and the ERP is current valuations. An interesting question is whether more complicated methods using newly developed machine learning models can provide superior forecasts.

Comments Off on Using Machine Learning Programs to Forecast the Equity Risk Premium

Can Machine Learning Improve Factor Returns? Not Really

By |April 29th, 2024|Factor Investing, Research Insights, Basilico and Johnsen, Academic Research Insight, AI and Machine Learning|

Can AI models improve on the failures in predicting returns strictly from a practical point of view?  In this paper, the possibilities are tested with a battery of AI models including linear regression, dimensional reduction methods, regression trees and neural networks.  These machine learning models may be better equipped to address the multidimensional nature of stock returns when compared to traditional sorting and cross-sectional regressions used in factor research. The authors hope to overcome the drawbacks and confirm the results of traditional quant methods. As it turns out, those hopes are only weakly fulfilled by the MLM framework.

Comments Off on Can Machine Learning Improve Factor Returns? Not Really

Social Media, Analyst Behavior and Market Efficiency

By |April 26th, 2024|Larry Swedroe, Research Insights, Guest Posts, Other Insights, Behavioral Finance|

Hibbert, Kang, Kumar and Mishra provided us with yet another explanation: social media is providing analysts with information that reduces their forecasting errors. The result has been an increase in market efficiency, leading to a reduction in the PEAD anomaly. The bottom line is that the ability to generate alpha continues to be under assault—trying to outperform the market by stock selection is becoming even more of a loser’s game.  

Comments Off on Social Media, Analyst Behavior and Market Efficiency
Go to Top