Over the last decade, investing responsibly and deploying capital for “ethically” correct and sustainable growth has been quite a theme. We dedicated a few blogs to this theme and have a separate ESG category for trading strategies in our database. It is often easy to commit financial resources to noble ideas during liquidity abundance. However, how do these methodologies fare during crisis times, such as when the GFC (Global Financial Crisis) or COVID-19 hit? That’s the question that a new paper by Henk Berkman and Mihir Tirodkar tries to answer.

There was a time in history when researchers believed that we, as a human species, act ultimately reasonably and rationally (for example, when dealing with financial matters). What arrived with the advent of Animal spirits (Keynes) and later Behavioral Finance pioneers such as Kahneman and Tversky was the realization that it is different from that. We often do not do what is in our best interest; quite the contrary. These emotions are hardly reconcilable with normal reasoning but result in market anomalies.

Researchers love to find causes and reasons and link behavioral anomalies to stock market performance. A lot of anomalies are related to various sentiment measures, derived from a alternative data sources and today, we present an interesting new possible relationship – investors’ mood and sentiment proxied by music sentiment!

More and more, a few mega-cap companies dominate the US stock market performance. Financial journals come up with different names for those stocks every few years. They are now called the “Magnificent Seven”, but we all remember FAANG, right? Naturally, several questions arise – Is the current status quo, when the stock market capitalization is highly concentrated among the few extremely large companies, an exception or rule over history? And what’s the impact of this concentration on the performance of the one particular factor – the Size premium? We present the research paper written by Emery and Koëter that tries to answer those questions. 

The aim of this article is multifold. It aims to answer the research question: does a portfolio consisting of top innovators outperform the S&P 500 index? To address this question, a strategy of investing long in top innovators according to their ranking is developed, and its performance is compared to that of the broad-based index. Based on the common belief that higher innovativeness carries higher risk, it aims to evaluate the volatility associated with innovative stocks. Additionally, it aims to analyze the impact of sector factors on the portfolio’s performance. Finally, it conducts a comparative analysis between the portfolio’s performance and that of the ARK Innovation ETF (ARKK), which specifically focuses on investing in companies relevant to the theme of disruptive innovation.

Two weeks ago, we promised you a surprise, and now it’s finally time to unveil what we have prepared for you :).

Our Quantpedia Awards 2024 aims to be the premier competition for all quantitative trading researchers. If you have an idea in your head about systematic/quantitative trading or investment strategy, and you would like to gain visibility on the professional scene, then submit your research paper, and you can compete for an attractive list of prizes. All info about the prizes, submission process, expert committee, and our partners are described in detail on our dedicated subpage: Quantpedia Awards 2024. But we will also give you a quick overview in this blog post.

Machine Learning will quite certainly continue to be a hot topic in 2024, and we are committed to bringing you new developments and keeping you in the loop. Today, we will review original research from Demirbaga and Xu (2023) that highlights the critical role of machine learning model execution time (combination of time for ML training and prediction) in empirical asset pricing. The temporal efficiency of machine learning algorithms becomes more pivotal, given the necessity for swift investment decision-making based on the predictions generated from a lot of real-time data. Their study comprehensively evaluates execution time across various models and introduces two time-saving strategies: feature reduction and a reduction in time observations. Notably, XGBoost emerges as a top-performing model, combining high accuracy with relatively low execution time compared to other nonlinear models.