Journal of Investment Strategies

Ali Hirsa
Professor, Columbia University & Managing Partner, Sauma Capital LLC

Welcome to the first issue of the thirteenth volume of The Journal of Investment Strategies, which contains two research papers and one forum paper.

In the first paper in the issue, “An entropy-based class of moving averages”, Andreas Kull explores the application of information-theoretical concepts to the backward filtering of time series. Using the maximum entropy principle, Kull defines maximum entropy (MaxEnt) moving averages for time series. By constraining the width and timescale, he recovers the simple moving average and the exponential moving average, respectively. By incorporating Tsallis entropy, Kull generalizes the framework to obtain a diverse family of MaxEnt moving averages with heavytail kernels or kernels with finite support. As an application, he discusses simple time series forecasting and a risk-neutral valuation scheme. He concludes by looking ahead to future work: MaxEnt moving averages can be used for smoothing time series, trend identification, financial valuation and technical analysis in trading. Future research may delve deeper into those applications that are particularly relevant for practitioners.

In the issue’s second paper, “Does investors’ sentiment influence stock market volatility? Evidence from India during pre- and post-Covid-19 periods”, Versha Patel, S. Amilan and P. Vairasigamani investigate the impact of sentiment on stock volatility during the periods before and after the Covid-19 outbreak. They utilize generalized autoregressive conditional heteroscedasticity (GARCH) models with lagged sentiment to predict volatility under nonlinear conditions. Their findings reveal that sentiment influenced stock volatility before Covid, but the relationship intensified during the pandemic, leading to more pronounced volatility patterns. The impact of sentiment on volatility was asymmetric: significant before Covid but more pronounced during the pandemic, with varying effects of positive and negative news. The study used threshold GARCH to capture this asymmetry, which intensified after the Covid outbreak. Understanding the impact of sentiment on market volatility during crises is essential for financial institutions and policymakers. Negative sentiment shifts can lead to downturns, requiring measures to stabilize the financial system. Predicting market reactions to crisis-related news improves decision-making, allowing for better communications and risk management strategies to mitigate panic-driven decisions. Recognizing the relationship between market sentiment and volatility should help to stabilize markets and reassure investors, empowering them to make informed decisions during crises.

The forum paper in this issue is “Luxury watches: a viable alternative investment or mere speculative trend? An analysis of two decades before the pandemic” by Simon Ulmer, Patrick Schmid and Andreas Widenhorn. Luxury watch investments have grown in popularity, as evidenced by rising auction prices, volume and media attention. The authors analyzed the investment performance of collectible watches traded on the secondary market using a novel data set of over 60 000 watch auction results from 1999 to 2020, and they identified the risk and return characteristics of collectible watches: an uninvestigated category. Between 1999 and 2020, collectible watches had an annualized real US dollar geometric mean return of 5.5% (7.7% nominal), outperforming the Standard & Poor’s 500 and other collectible assets such as art and classic cars. The relatively low price volatility of collectible watches results in attractive risk-adjusted nominal Sharpe ratios, second only to gold. Additionally, Ulmer et al found that returns are positively correlated with inflation and equity investments. A hedonic pricing model revealed price determinants such as authenticity, rarity, watch type, brand and famous previous owners. There were some notable complexities within the model, such as steel versions fetching higher prices than gold and difficulty in quantifying emotional price determinants. The authors’ data sample may overemphasize high prices and returns due to a focus on the upper end of the market, introducing survivorship bias. Future research could reduce this bias by including unsold lots at their highest bid or reserve price estimates. The paper captures valuations from the first two decades of the new millennium, and future research should also consider the impact of the Covid-19 pandemic.

The editorial board and I extend our gratitude to you, our valued readers, for your unwavering support and interest in our journal. We are excited to present a growing collection of practical papers on diverse topics related to modern investment strategies, sourced from both academic and industry experts.