Quantpedia Premium Update – 16th March 2021

New strategies:

#601 – Learning to Rank and Cross-sectional Momentum

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1980-2019
Indicative performance: 35.9%
Estimated volatility: 16.6%

Source paper:

Poh, Daniel and Lim, Bryan and Zohren, Stefan and Roberts, Stephen: Building Cross-Sectional Systematic Strategies By Learning to Rank
https://ssrn.com/abstract=3751012
Abstract:
The success of a cross-sectional systematic strategy depends critically on accurately ranking assets prior to portfolio construction. Contemporary techniques perform this ranking step either with simple heuristics or by sorting outputs from standard regression or classification models, which have been demonstrated to be sub-optimal for ranking in other domains (e.g. information retrieval). To address this deficiency, we propose a framework to enhance cross-sectional portfolios by incorporating learning-to-rank algorithms, which lead to improvements of ranking accuracy by learning pairwise and listwise structures across instruments. Using cross-sectional momentum as a demonstrative case study, we show that the use of modern machine learning ranking algorithms can substantially improve the trading performance of cross-sectional strategies — providing approximately threefold boosting of Sharpe Ratios compared to traditional approaches.

#602 – Pure Growth Strategy

Period of rebalancing: Yearly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 2007-2021
Indicative performance: 11.01%
Estimated volatility: 17.78%

Source paper:

S&P Dow Jones Indices: S&P U.S. Style Indices Methodology
https://www.spglobal.com/spdji/en/documents/methodologies/methodology-sp-us-style.pdf
Abstract:
The S&P U.S. Style Indices measure the performance of U.S. equities fully or partially categorized as either growth or value stocks, as determined by Style Scores for each security. The Style series is weighted by float-adjusted market capitalization (FMC), and the Pure Style index series is weighted by Style Score subject to the rules described in Index Construction. The S&P U.S. Style Indices address two distinct needs. The first is for exhaustive style indices that provide broad exposure to a certain style segment. The second need is for narrow, style-pure indices. The Style index series divides the complete market capitalization of each parent index approximately equally into growth and value indices. This series covers all stocks in the parent index universe, and is FMC weighted. The Pure Style index series identifies a portion of the parent index’s market capitalization as Pure Growth and a portion as Pure Value. There are no overlapping stocks, and stocks are weighted in proportion to their relative style propensity.

#603 – Slope Carry

Period of rebalancing: Monthly
Markets traded: bonds
Instruments used for trading: bonds, futures, ETFs
Complexity: Simple strategy
Backtest period: 2007-2018
Indicative performance: 5.73%
Estimated volatility: 8.59%

Source paper:

Spencer Andrews, Ric Colacito, Mariano (Max) Massimiliano Croce, Federico Gavazzoni: Concealed Carry
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3743205
Abstract:
The slope carry consists of taking a long (short) position in the long-term bonds of countries with steeper (flatter) yield curves. The traditional carry is a long (short) position in countries with high (low) short-term rates. We document that: (i) the slope carry risk premium is negative (positive) in the pre (post) 2008 period, whereas it is concealed over longer samples; (ii) the traditional carry risk premium is lower post-2008; and (iii) there has been a sharp decline in expected global growth and global inflation post-2008. We connect these empirical findings through an equilibrium model in which investors price news shocks, financial markets are complete, and countries feature heterogeneous exposure to news shocks about both global output expected growth and global inflation.

#604 – Reversal on Straddles

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: options
Complexity: Complex strategy
Backtest period: 1996 – 2019
Indicative performance: 49.71%
Estimated volatility: 36.8%

Source paper:

Christopher S. Jones, Mehdi Khorram, Haitao Mo :Momentum, Reversal, and Seasonality in Option Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3705500
Abstract:
Option returns display substantial momentum using formation periods ranging from 6 to 36 months long, with long/short portfolios obtaining annualized Sharpe ratios above 1.5. In the short term, option returns exhibit reversal. Options also show marked seasonality at multiples of three and 12 monthly lags. All of these results are highly significant and stable in the cross section and over time. They remain strong after controlling for other characteristics, and momentum and seasonality survive factor risk-adjustment. Momentum is mainly explained by an underreaction to past volatility and other shocks, while seasonality reflects unpriced seasonal variation in stock return volatility.

#605 – Momentum on Straddles

Source paper:

New research papers related to existing strategies:

#49 – S&P 500 Index Addition Effect
#460 – ESG Level Factor Investing Strategy

Kang, Moonsoo and Viswanathan, Kalpathy G. and White, Nancy A and Zychowicz, Edward J.: Sustainability Efforts, Index Recognition, and Stock Performance
https://ssrn.com/abstract=3747343
Abstract:
We examine the long-term performance of stocks appearing in the Dow Jones Sustainability Index North America. We find that sustainability stocks exhibit abnormal returns for 12 to 30 months after the index listing while those stocks generate no excess returns before the index listing. Moreover, sustainability stocks experience an increase in institutional ownership after the index listing. However, we find no evidence that short sellers increase their position to exploit a possible overpricing for sustainability stocks. Overall, our analysis suggests that sustainability efforts translate into a permanent increase in demand for stocks, leading to the superior performance.

#460 – ESG Level Factor Investing Strategy

de Groot, Wilma and de Koning, Jan and van Winkel, Sebastian: Sustainable Voting Behavior of Asset Managers: Do They Walk the Walk?
https://ssrn.com/abstract=3783454
Abstract:
We investigate asset manager characteristics that influence ESG voting patterns using a decade of voting data with more than 20 million observations. Asset managers predominantly vote against social and environmental proposals. Especially, large and passive asset managers vote the least in favor of these proposals and despite the increased attention to sustainability integration, they hardly vote more in favor of these proposals than a decade ago. Moreover, signatories of the PRI do not vote more often in favor of environmental and social issues. Our results have important implications for investors striving for direct impact on the sustainability agenda of corporates.

#460 – ESG Level Factor Investing Strategy

Chen, Linquan and Chen, Yao and Kumar, Alok and Leung, Woon Sau, Firm-Level ESG News and Active Fund Management
https://ssrn.com/abstract=3747085
Abstract:
Using artificial intelligence and big data generated ESG news indices, we examine whether firm-level ESG news affects the investment choice of actively managed U.S. mutual funds. We find a positive relation between firm-level ESG news index and fund holdings. Fund managers incorporate ESG news to cater to investor demand and achieve higher risk-adjusted returns. Further, the ESG news-holding relation is stronger during periods of high ESG demand, and among funds located in Democratic states, with retail-oriented clienteles, better ESG ratings, higher marketing fees, and “domestic” fund managers. These results suggest that mutual fund managers successfully integrate ESG information into their portfolio decisions.

#460 – ESG Level Factor Investing Strategy

Faccini, Renato and Matin, Rastin and Skiadopoulos, George, Dissecting Climate Risks: Are they Reflected in Stock Prices?
https://ssrn.com/abstract=3795964
Abstract:
We construct novel proxies of physical and transition climate risks by conducting textual analysis of climate-change news over 2000-2018. This analysis uncovers four textual risk factors related to the topics of U.S. climate policy, international summits, natural disasters, and global warming, respectively. The first two factors proxy transition risks, whereas the last two proxy physical risks. We find that only the climate policy factor is priced in the U.S. stock market, with the evidence being more pronounced over 2012-2018. The documented positive premium is consistent with the argument that investors hedge short-term transition risks. We validate this explanation using a narrative approach to mark the content of climate news. Our results imply that investors’ attention is an important driver of asset returns.

#480 – Machine Learning-Based Financial Statement Analysis

Chen, Xi and Cho, Yang Ha and Dou, Yiwei and Lev, Baruch Itamar: Fundamental Analysis of XBRL Data: A Machine Learning Approach
https://ssrn.com/abstract=3741015
Abstract:
Since 2012, all U.S. public companies must tag quantitative amounts in financial statements and footnotes of their 10-K reports using the eXtensible Business Reporting Language (XBRL). We conduct a fundamental analysis of this large set of detailed financial information to predict earnings. Using machine learning methods, we combine the XBRL data into a summary measure for the direction of one-year-ahead earnings changes. Hedge portfolios are formed based on this measure during the period 2015-2018. The annual size-adjusted returns to the hedge portfolios range from 5.02 to 9.7 percent. These returns persist after accounting for transaction costs and risk. Our strategies outperform those of Ou and Penman (1989), who extract the summary measure from 65 accounting variables using logistic regressions. Additional analyses suggest that the outperformance stems from both nonlinear predictor interactions missed by regressions and more detailed financial data in XBRL documents.

#480 – Currency Factor Momentum

Zhang, Shaojun, Dissecting Currency Momentum
https://ssrn.com/abstract=3759017
Abstract:
This paper shows that the cross-sectional and time series momentum in currencies, which cannot be explained by carry and dollar factors, summarize the autocorrelation of these factors. These momentum strategies long currency factors following positive factor returns and short them following losses. Carry and dollar factors are strongly autocorrelated and only earn significantly positive excess returns following positive factor returns. In contrast, idiosyncratic currency returns contain little momentum. Consequently, factor momentum not only outperforms the cross-sectional and time series momentum but also explains them. Limits to arbitrage and time-varying risk premium help explain carry and dollar momentum, respectively.

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

An Introduction to Volatility Targe t ing

One of the most popular reports in the Portfolio Analysis section of our Quantpedia Pro tool is “Volatility Targeting”. In this article, we will explain some theory behind this portfolio management method. And then, we will go more in-depth, pick several examples and explain some common volatility targeting variants.

Does Social Media Sentiment Matter in the Pricing of U.S. Stocks?

Although the models cannot entirely capture the reality, they are essential in the analysis and problem solving, and the same could be said about asset pricing models. These models had a long journey from the CAPM model to the most recent Fama French five-factor model. However, the asset pricing models still rely on fundamentals, and as we see in the practice every day, the financial markets or investors are not always rational, and prices tend to deviate from their fundamental values. Past research has already suggested that the assets are driven by both the fundamentals and sentiment. The novel research of Koeppel (2021) continues in the exploration of the hypothesis mentioned above and connects the sentiment with the factors in Fama’s and French’s methodology. The most interesting result of the research is the construction of the sentiment risk factor based on the direct search-based sentiment indicators. The data are sourced by the MarketPsych that analyze information flowing on social media. For comparison, public news is not a source of such exploitable sentiment indicator.

The sentiment score extracted from social media can be exploited to augment the Fama French five factors model. Based on the results, this addition seems to be justified. Adding the sentiment to the pure fundamental model explains more variation and reduce the alphas (intercepts). Moreover, the factor is unrelated to the well-known and established risk factors utilized in the previous asset pricing models, including the momentum. Finally, the sentiment factor seems to be outperforming several other factors, even those established as the smart beta factors.

Plus, the following six trading strategies have been backtested in QuantConnect in the previous two weeks:

#17 – Momentum Effect in Anomalies/Trading Systems
#295 – Seasonality Effect in Anomalies
#510 – Factor Momentum
#548 – The Intraday Momentum in China
#595 – Notional Value Effect in Futures Markets
#598 – Lottery and Hot Potato Stocks

Are you looking for more strategies to read about? Sign up for our newsletter or visit our Blog or Screener.

Do you want to learn more about Quantpedia Premium service? Check how Quantpedia works, our mission and Premium pricing offer.

Do you want to learn more about Quantpedia Pro service? Check its description, watch videos, review reporting capabilities and visit our pricing offer.

Are you looking for historical data or backtesting platforms? Check our list of Algo Trading Discounts.

Would you like free access to our services? Then, open an account with Lightspeed and enjoy one year of Quantpedia Premium at no cost.

Or follow us on:

Facebook Group, Facebook Page, Twitter, Linkedin, Medium or Youtube