Semivolatility-managed portfolios
Daniel Batista da Silva (U. of Geneva) and M. Fernandes (Getulio Vargas Fnd.)
July 2024
There is ample evidence that volatility management helps improve the risk-adjusted performance of momentum portfolios. However, it is less clear that it works for other factors and anomaly portfolios. We show that controlling by the upside and downside components of volatility yields more robust risk-adjusted performances across a broad set of factors and anomaly portfolios, as well as exchange-traded funds. In particular, we propose semivolatility-managed portfolios that, apart from deleveraging when downside volatility is high, also exploit the higher expected returns in times of good volatility. We find that our semivolatility-managed portfolios that control for both skewness and downside volatility perform better than the original portfolios and extant (semi)volatility management proposals.

Does Systematic Tail Risk Matter?
Evarist Stoja (University of Bristol), et al.
July 2024
Systematic tail risk is considered an important determinant of expected returns on risky assets. We examine its impact from two perspectives in a unified framework which originates from a simple asset pricing model. From the first perspective, systematic tail risk is proxied by a generalized tail dependence coefficient and is compensated with an economically sizeable and statistically significant premium. From the second perspective, systematic tail risk is proxied by the product of the same coefficient with a normalised tail risk measure and does not appear to earn a premium. We examine these contradictory findings and attempt to reconcile them. Evidence suggests that the components of our second systematic tail risk measure may be subject to common features. This finding may help explain the contradictory evidence in the literature.

Beyond Trend Following: Deep Learning for Market Trend Prediction
Fernando Berzal (U. of Granada) and Alberto Garcia (ACCI Capital Inv.)
June 2024
Trend following and momentum investing are common strategies employed by asset managers. Even though they can be helpful in the proper situations, they are limited in the sense that they work just by looking at past, as if we were driving with our focus on the rearview mirror. In this paper, we advocate for the use of Artificial Intelligence and Machine Learning techniques to predict future market trends. These predictions, when done properly, can improve the performance of asset managers by increasing returns and reducing drawdowns. Index Terms—trend following, momentum investing, stock prediction, market prediction, trend prediction, investment strategy, machine learning, deep learning, hyperparameter tuning.

The Risk and Reward of Investing
Ronald Q. Doeswijk (independent) and Laurens Swinkels (Erasmus U. Rotterdam)
August 2024
We examine the risks and rewards of investing by constructing a comprehensive market portfolio valued at $150 trillion in global assets and spanning 1970-2022 at a monthly frequency. The monthly frequency allows for a more accurate estimation of investment risks compared with previous studies. Even though the Sharpe ratio of the global market portfolio is not much higher than that of equities, it is much more stable over time. Moreover, drawdowns of the global market portfolio are less deep and shorter. When the market portfolio is expressed in currencies other than the U.S. dollar, risks of investing appear larger.

Learn To Use R For Portfolio Analysis
Quantitative Investment Portfolio Analytics In R:
An Introduction To R For Modeling Portfolio Risk and Return
By James Picerno