Quantpedia Premium Update – 16th September 2021

New strategies:

#661 – Market Sentiment and an Overnight Anomaly

Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 2018-2021
Indicative performance: 15.58%
Estimated volatility: 7.33%

Source paper:

Vojtko, Hanicová: Market Sentiment and an Overnight Anomaly
https://\/\/new-fmhwbzh6ghd9hede.swedencentral-01.azurewebsites.net/www/Market_Sentiment_and_an_Overnight_Anomaly.pdf
Various research shows that market sentiment, also called investor sentiment, plays a role in market returns. Market sentiment refers to the general mood on the financial markets and investors’ overall tendency to trade. The mood on the market is divided into two main types, bullish and bearish. Naturally, rising prices indicate bullish sentiment. On the other hand, falling prices indicate bearish sentiment. This paper shows various ways to measure market sentiment and its influence on returns.
Additionally, we take a look at an overnight anomaly in combination with three market sentiment indicators. We analyse the Brain Market sentiment indicator in addition to VIX and the short-term trend in SPY ETF. Our aim is not to build a trading system. Instead, it is to analyse financial markets behaviour. Overall the transaction costs of this kind of strategy would be very high. However, more appropriate than using this system on its own would be to use it as an overlay when deciding when to make trades.

#662 – How to Use Lexical Density of Company Filings

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 2010-2021
Indicative performance: 8.16%
Estimated volatility: 10.40%

Source paper:

Hanicova, Kalus, Vojtko: How to Use Lexical Density of Company Filings
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3921091
This paper analyzes the application of natural language processing (NLP) on the 10-K and the 10-Q company reports. Using the Brain Language Metrics on Company Filings (BLMCF) dataset, which monitors numerous language metrics on 10-Ks and 10-Qs company reports, we analyze various lexical metrics such as lexical richness, lexical density, and specific density.
In simple words, lexical richness says how many unique words are used by the author. The idea is that the more varied vocabulary the author has, the more complex the text is. Secondly, lexical density measures the structure and complexity of human communication in a text. A high lexical density indicates a large amount of information-carrying words. And lastly, specific density measures how dense the report’s language is from a financial point of view. In other words, how many finance- related words are used in the text.
Overall, we can say that this type of alternative data exhibits interesting results. Even though lexical richness produced the weakest results (of our strategies) when applied to the investment universe consisting of 500 stocks, it significantly improved when we expanded the investment universe to 3000 stocks. Moreover, the strategies based on the lexical density and specific density improved the Sharpe ratio even further.
In the Last section, we combine the two metrics (Lexical density and Specific density) in one strategy. Applying both of these metrics to the investment universe with 500 stocks produces a Sharpe ratio of 0.688.

#663 – R&D Expenditures and Stock Returns

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 2003-2020
Indicative performance: 4.67%
Estimated volatility: 8.20%

Source paper:

Louis K. C. Chan, Josef Lakonishok and Theodore Sougiannis: The Stock Market Valuation of Research and Development Expenditures
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=227564
Abstract:
We examine whether stock prices fully reflect the value of firms’ intangible assets, focusing on research and development (R&D). Since intangible assets are not reported on financial statements under current U.S. accounting standards and R&D spending is expensed, the valuation problem may be especially challenging. Nonetheless we find that historically the stock returns of firms doing R&D on average matches the returns on firms with no R&D. For companies engaged in R&D, high R&D intensity has a distinctive effect on returns for two groups of stocks. Within the set of growth stocks, R&D-intensive stocks tend to out-perform stocks with little or no R&D. Companies with high R&D relative to equity market value (who tend to have poor past returns) show strong signs of mis-pricing. In both cases the market apparently fails to give sufficient credit for firms’ R&D investments. Our exploratory investigation of the effects of advertising on returns yields similar results. We also provide evidence that R&D intensity is positively associated with return volatility, everything else equal. Insofar as the association reflects investors’ lack of information about firms’ R&D activity, increased accounting disclosure may be beneficial.

#664 – Return Asymmetry Effect in Commodity Futures

Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures
Complexity: Moderately complex strategy
Backtest period: 1991-2021
Indicative performance: 4.36%
Estimated volatility: 7.53%

Source paper:

Ďurian, Ladislav and Padyšák, Matúš, Return Asymmetry in Commodity Futures
https://ssrn.com/abstract=3918896
Abstract:
This paper aims to examine the return asymmetry in commodity futures. Instead of using skewness as a proxy for the return asymmetry, we rely on a new asymmetric measure IE, that uses the difference between upside and downside return probabilities to capture the degree of asymmetry and has a low correlation to the original skewness effect. Our study documents that the high (low) IE commodities are overvalued (undervalued), and their subsequent returns are lower (higher). These results are consistent with the high (low) demand by the risk-averse investors for the high (low) IE commodities. A strategy that takes a long position in the bottom seven commodities with the lowest IE in the previous month and shorts the top seven commodities with the highest IE exhibits an economically large and statistically significant return. Besides, it can serve as a hedge to the stock portfolio because of its negative correlation with the stock market. Our results contribute to the existing literature by expanding an asymmetric measure IE to the new asset class.

#665 – Style-Integrated Portfolios of Commodity Futures

Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures
Complexity: Moderately complex strategy
Backtest period: 2001-2020
Indicative performance: 7.71%
Estimated volatility: 8%

Source paper:

Rad, Hossein and Low, Rand Kwong Yew and Miffre, Joelle and Faff, Robert W.: The strategic allocation to style-integrated portfolios of commodity futures
https://ssrn.com/abstract=3881179
Abstract:
We contribute to the literature on the diversification benefits of commodity futures by integrating it with the literature on style integration. Our work augments the traditional asset mix of investors with a long-short portfolio that integrates the styles that matter to the pricing of commodity futures. The style-integrated portfolio offers remarkable out-of-sample performance and low correlations with stocks and bonds, in particular in periods of heightened volatility in equity markets. As such, it is a worthy candidate for inclusion to the strategic asset allocation of investors. Treating the style-integrated portfolio as part of the strategic mix is found to enhance out-of-sample performance and reduce crash risk compared to the alternatives considered thus far. The conclusion holds across traditional asset mix and portfolio allocation methods. Albeit lower, the diversification benefits of style integration also persist in a long-only setting.

#666 – When Retail Investors Learn from Insiders

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 2010-2018
Indicative performance: 5.33%
Estimated volatility: 2.59%

Source paper:

Boehmer, Ekkehart and Sang, Bo and Zhang, Zhe: Can Retail Investors Learn from Insiders?
https://ssrn.com/abstract=3827062
Abstract:
This paper examines the trading patterns of retail investors following insider trading and the corresponding price impact. Retail investors follow the opportunistic purchases by insiders, but not their routine purchases. The abnormal retail downloads of the Form 4 filings from the EDGAR database also increase for opportunistic insider purchases. Neither investor attention nor common information such as earnings announcements or analysts forecast revisions explains the results. Moreover, for stocks with opportunistic insider purchases, those that retail investors bought yield higher cumulative abnormal returns than those that retail investors sold. The effect is mostly driven by the information component of the retail trades, rather than liquidity provision or temporary price pressure, and stronger for stocks with greater informational uncertainty and higher arbitrage costs. Variance ratio tests also suggest price efficiency improvements for stocks bought by retail investors following opportunistic insider purchases. The evidence is mostly consistent with retail investors learning from opportunistic insider purchases, and their trading helping expedite price discovery.

#667 – Idiosyncratic Asymmetry Factor in China

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 2000-2019
Indicative performance: 10.20%
Estimated volatility: 15.75%

Source paper:

Wu, Ke and Zhu, Yifeng and Chen, Dongxu, Stock Return Asymmetry in China
https://ssrn.com/abstract=3724761
Abstract:
In this paper, we find that the upside asymmetry calculated based on a new distribution-based asymmetry measure proposed by Jiang, Wu, Zhou, and Zhu (2020) is negatively related to average future returns in the crosssection of Chinese stock returns. By contrast, when using a conventional skewness measure, the relationship between asymmetry and average returns is unclear. Furthermore, the asymmetry factor constructed from the new asymmetry measure cannot be explained by the three-factor (CH-3) and four-factor (CH-4) models proposed by Liu, Stambaugh, and Yuan (2019). When augmenting the CH-3 model with our asymmetry factor, the augmented four-factor model is able to explain 32 anomalies out of a universe of 37 significant anomalies in the Chinese stock market, outperforming both the CH-3 and CH-4 models.

#668 – Idiosyncratic Asymmetry in US Stocks

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 1963-2015
Indicative performance: 2.25%
Estimated volatility: 6.03%

Source paper:

Lei Jiang, Ke Wu, Guofu Zhou, Yifeng Zhu: Stock Return Asymmetry: Beyond Skewness
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2660598
Abstract:
In this paper, we propose two asymmetry measures for stock returns. Unlike the popular skewness measure, our measures are based on the distribution function of the data rather than just the third central moment. We present empirical evidence that greater upside asymmetries calculated using our new measures imply lower average returns in the cross-section of stocks. In contrast, when using the skewness measure, the relationship between asymmetry and returns is inconclusive.

New research papers related to existing strategies:

#52 – Asset Growth Effect

Rizova, Savina and Saito, Namiko: Investment and Expected Stock Returns
https://ssrn.com/abstract=3646575
Abstract:
Valuation theory predicts that, all else equal, expected investment should be negatively related to expected returns. We study the relation between expected investment and expected stock returns globally. We show that recent asset growth is a systematic proxy for future investment not only in the US, but also in developed ex US and emerging markets. Using this proxy, we find a negative investment effect across developed and emerging markets as well as across sectors in those regions, consistent with the prediction of valuation theory. Globally, the effect is much stronger among small caps than large caps and is mainly driven by the underperformance of high investment firms. Examining the different components of asset growth related to raising of capital as well as those related to use of capital, we find that all components contribute to the investment effect.

#582 – Carbon Risk in the Cross Section of Corporate Bond Returns

Yousaf, Imran and Suleman, Tahir and Demirer, Riza: Green Investments: A Luxury Good or a Financial Necessity?
https://ssrn.com/abstract=3855125
Abstract:
This study examines the diversification and hedging benefits of green investments for conventional stock portfolios in the context of the recent COVID-19 pandemic. While the findings confirm the status of gold as a strong hedge against stock market downturns, we find that clean energy investments, green bonds, in particular, have the potential to serve as a safe haven as well. In fact, compared to the other alternative and sustainable investments in our sample, green bonds are found to be the only asset that serves as a strong safe haven against large stock market fluctuations due to the COVID-19 pandemic. Portfolio analysis further shows that supplementing conventional stock portfolios with green bonds during the COVID-19 pandemic resulted in the highest risk-adjusted returns, compared to those supplemented with other alternative assets in the sample. Our findings support the emergence of green investments not as a luxury good, but a necessity for improved financial stability and performance, particularly during the turbulent market states driven by the recent pandemic.

#578 – ESG Level Factor Investing Strategy

Jacob, Andrea and Wilkens, Marco: What drives sustainable indices? A framework for analyzing the sustainable index landscape
https://ssrn.com/abstract=3874437
Abstract:
This article presents an encompassing four-step customizable framework for analyzing the heterogeneous sustainable index landscape. Compared to previous studies, we present means and methods to move the measurement and impact of sustainability performance in the center of attention and emphasize the often neglected aim of sustainable indices: incorporating sustainability into investment tools. Besides traditional comparisons of return and risk indicators (step one), we analyze the sustainability profile of sustainable indices while actively managing the presence of ESG rating disagreement (step two). For the determination of index-specific return and risk sources, we integrate sustainability factors in factor analyses and risk decomposition approaches (step three). A performance attribution analysis based on sustainability classes increases the transparency on the composition strategies of sustainable indices (step four). Our framework facilitates the analyses of sustainable investment tools and thus supports investors in making more meaningful and forward-looking investment decisions in line with their sustainability-related preferences.

#581 – Equity Index and Risk-free Asset Allocation Using Neural Networks
#496 – Using Machine Learning to Pick the Right Combination of Risky and Risk-Free Asset

Benhamou, Eric and Ohana, Jean-Jacques and Saltiel, David and Guez, Beatrice: Explainable AI (XAI) Models Applied to Planning in Financial Markets
https://ssrn.com/abstract=3862437
Abstract:
Regime changes planning in financial markets is well known to be hard to explain and interpret. Can an asset manager ex-plain clearly the intuition of his regime changes prediction on equity market ? To answer this question, we consider a gradi-ent boosting decision trees (GBDT) approach to plan regime changes on S&P 500 from a set of 150 technical, fundamen-tal and macroeconomic features. We report an improved ac-curacy of GBDT over other machine learning (ML) methods on the S&P 500 futures prices. We show that retaining fewer and carefully selected features provides improvements across all ML approaches. Shapley values have recently been intro-duced from game theory to the field of ML. This approach allows a robust identification of the most important variables planning stock market crises, and of a local explanation of the crisis probability at each date, through a consistent features attribution. We apply this methodology to analyse in detail the March 2020 financial meltdown, for which the model of-fered a timely out of sample prediction. This analysis unveils in particular the contrarian predictive role of the tech equity sector before and after the crash.

#581 – Equity Index and Risk-free Asset Allocation Using Neural Networks
#496 –Using Machine Learning to Pick the Right Combination of Risky and Risk-Free Asset

Dichtl, Hubert and Drobetz, Wolfgang and Otto, Tizian: Forecasting Stock Market Crashes via Machine Learning
https://ssrn.com/abstract=3843319
Abstract:
This paper uses a comprehensive set of variables from the five largest Eurozone countries to compare the performance of simple univariate and machine learning-based multivariate models in predicting stock market crashes. The statistical predictive performance of a support vector machine-based stock market crash prediction model is significantly different from zero and among the best-performing univariate benchmarks, while still being truly out-of-sample. The ability to forecast subsequent stock market crashes out-of-sample translates into value-added to investors under realistic trading assumptions (net of transaction costs). Incorporating nonlinear and interactive effects is both imperative and foundation for the predictive performance of support vector machines. This adds an economic component to the advantageousness of machine learning-based multivariate crash prediction models over their univariate counterparts. It helps identify and explain the complex relationships in the underlying economic conditions (key economic drivers) that precede substantial stock market downturns.

And several interesting free blog posts have been published during last 2 weeks:

Find Your Crisis Hedge – Quantpedia Highlights in August 2021

Currently, the stocks indexes around the world are close to all-time highs, and an optimistic mood is in the air. Corona crisis is nearly forgotten (at least financial markets act as if nothing had happened), but there will be a crisis at some time in the future. And it’s better to prepare for the worst during calm periods than to look for quick help under stress in volatile times. Therefore, we have prepared a new report for our Quantpedia Pro clients, which allows you to pick any asset, trading strategy or a mix of assets/factors into your model portfolio and find a trading strategy that works as a Crisis Hedge during negative months or bear markets. How does it work?

A New Return Asymmetry Investment Factor in Commodity Futures

As mentioned several times, Quantpedia is a big fan of transferring ideas from one asset class to another. This article is another example; we use an idea originally tested on Chinese stocks and apply it to the commodity futures investment universe. The resultant return new asymmetry investment factor in commodities is an interesting trading strategy unrelated to other common factors and has a slightly negative correlation to the equity market and can be therefore used as an excellent diversifier in multi-asset multi-strategy portfolios.

How to Use Lexical Density of Company Filings

The application of alternative data is currently a strong trend in the investment industry. We, too, analyzed few datasets in the past, be it ESG data, sentiment, or company fillings. This article continues the exploration of the alt-data space. This time, we use the research paper by Joenväärä et al., which shows that lexically diverse hedge funds outperform lexically homogeneous as an inspiration for us to analyze various lexical metrics in 10-K & 10-Q reports. Once again, we show that it makes sense to transmit ideas from one research paper to completely different asset class.

Does Gambling Influence Stock Markets Around the World?

Is there any association between the country’s stock market and its gambling policy? Surprisingly, yes, and there’s more to it than one would think. In a new research paper, Kumar, Nguyen and Putnins offer a complex study of gambling activities in 38 countries worldwide to estimate the impact on their financial markets.

The research’s dataset follows that around 86% of the estimated total global gaming revenue comprises traditional gambling forms – casinos, lotteries, sports betting, and many others. Moving to the financial markets, the authors introduce a split of stocks into lottery-like and non-lottery stocks to estimate the amount of gambling in stock markets. Lottery-like stocks are expected to be traded much more often than other stocks. It turns out that 14% of developed markets, 18% of emerging ones and 33% of retail-dominated Asian markets (China, Thailand) is being gambled. Generally, there is 3.5 times more capital gambled in the stock market around the world compared to the traditional ways combined together.

Introduction to Clustering Methods In Portfolio Management – Part 1

At the beginning of October, we plan to introduce for our Quantpedia Pro clients a new Quantpedia Pro report dedicated to clustering methods in portfolio management. The theory behind this report is more extensive; therefore, we have decided to split the introduction into our methodology into three parts. We will publish them in the next few weeks before we officially unveil our reporting tool. This first short blog post introduces three clustering methods as well as three methods that select the optimal number of clusters. The second blog will apply all three methods to model ETF portfolios, and the final blog will show how to use portfolio clustering to build multi-asset trading strategies.