New strategies:
#476 – Speculator Spreading Pressure and the Commodity Futures Risk Premium
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures, CFDs
Complexity: Complex strategy
Backtest period: 2005-2018
Indicative performance: 21.19%
Estimated volatility: 24.42%
Source paper:
Yujing Gong: Speculator Spreading Pressure and the Commodity Futures Risk Premium
https://editorialexpress.com/cgi-bin/conference/download.cgi?db_name=AFAPS2020&paper_id=302
Abstract:
This paper investigates the impact of speculators’ trading activities on the commodity futures risk premium. In particular, we focus on speculators’ spread positions, and study the asset pricing implications of spreading pressure on the cross-section of commodity futures returns. We document that spreading pressure negatively predicts futures excess returns even after controlling for well-known determinants of futures returns such as basis-momentum. Furthermore, the spreading pressure factor-mimicking portfolio carries a significant risk premium of 21.55% per annum after commodity market financialization. Our single-factor model provides a better cross-sectional fit than the existing 2-factor or 3-factor models in the literature. We interpret these results as spreading pressure reflecting speculators’ expectation on the change in the slope and curvature of futures term structures and our spreading pressure factor linking to innovations in real economic uncertainty.
#477 – Generalised Risk-Adjusted Momentum in Commodities
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures, CFDs
Complexity: Complex strategy
Backtest period: 1984-2018
Indicative performance: 10.10%
Estimated volatility: 17.40%
Source paper:
Fan, Minyou and Kearney, Fearghal Joseph and Li, Youwei and Liu, Jiadong: Momentum and the Cross-Section of Stock Volatility
https://ssrn.com/abstract=3541766
Abstract:
Recent literature shows that momentum strategies exhibit significant downside risks over certain periods, or called “momentum crashes.” We find that the high uncertainty of momentum strategies is sourced from the cross-sectional volatility of individual stocks. Stocks with high realised volatility over the formation period tend to lose momentum effect, while stocks with low realised volatility show strong momentum. A new approach, generalised risk-adjusted momentum (GRJMOM), is introduced to mitigate the negative impact of high momentum risks. GRJMOM is proven to be more profitable and less risky than the existing momentum ranking approaches in multiple asset classes, including the UK stock, commodity, global equity index, and fixed income markets.
#478 – Generalised Risk-Adjusted Momentum in Equity Indexes
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: ETFs, futures
Complexity: Complex strategy
Backtest period: 1970-2018
Indicative performance: 12.70%
Estimated volatility: 19.90%
Source paper:
Fan, Minyou and Kearney, Fearghal Joseph and Li, Youwei and Liu, Jiadong: Momentum and the Cross-Section of Stock Volatility
https://ssrn.com/abstract=3541766
Abstract:
Recent literature shows that momentum strategies exhibit significant downside risks over certain periods, or called “momentum crashes.” We find that the high uncertainty of momentum strategies is sourced from the cross-sectional volatility of individual stocks. Stocks with high realised volatility over the formation period tend to lose momentum effect, while stocks with low realised volatility show strong momentum. A new approach, generalised risk-adjusted momentum (GRJMOM), is introduced to mitigate the negative impact of high momentum risks. GRJMOM is proven to be more profitable and less risky than the existing momentum ranking approaches in multiple asset classes, including the UK stock, commodity, global equity index, and fixed income markets.
#479 – Generalised Risk-Adjusted Momentum in Stocks
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1965-2018
Indicative performance: 30.30%
Estimated volatility: 23.00%
Source paper:
Fan, Minyou and Kearney, Fearghal Joseph and Li, Youwei and Liu, Jiadong: Momentum and the Cross-Section of Stock Volatility
https://ssrn.com/abstract=3541766
Abstract:
Recent literature shows that momentum strategies exhibit significant downside risks over certain periods, or called “momentum crashes.” We find that the high uncertainty of momentum strategies is sourced from the cross-sectional volatility of individual stocks. Stocks with high realised volatility over the formation period tend to lose momentum effect, while stocks with low realised volatility show strong momentum. A new approach, generalised risk-adjusted momentum (GRJMOM), is introduced to mitigate the negative impact of high momentum risks. GRJMOM is proven to be more profitable and less risky than the existing momentum ranking approaches in multiple asset classes, including the UK stock, commodity, global equity index, and fixed income markets.
#480 – Machine Learning-Based Financial Statement Analysis
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1991-2017
Indicative performance: 47.47%
Estimated volatility: 18.00%
Source paper:
Amel-Zadeh, Amir and Calliess, Jan-Peter and Kaiser, Daniel and Roberts, Stephen: Machine Learning-Based Financial Statement Analysis
https://ssrn.com/abstract=3520684
Abstract:
This paper explores the application of machine learning methods to financial statement analysis. We investigate whether a range of models in the machine learning repertoire are capable of forecasting the sign and magnitude of abnormal stock returns around earnings announcements based on financial statement data alone. We find random forests and recurrent neural networks to outperform deep neural networks and linear models such as OLS and Lasso. Using the models’ predictions in an investment strategy we find that random forests dominate all other models and that non-linear methods perform relatively better for predictions of extreme market reactions, while the linear methods are relatively better in predicting moderate market reactions. Analysing the underlying economic drivers of the performance of the random forests, we find that the models select as most important predictors accounting variables commonly used to forecast free cash flows and firm characteristics that are known cross-sectional predictors of stock returns.
New research papers related to existing strategies:
#454 – Time Series Momentum Strategies Using Deep Neural Networks
Zhang, Zohren, Roberts: Deep Reinforcement Learning for Trading
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3519858
Abstract:
We adopt Deep Reinforcement Learning algorithms to design trading strategies for continuous futures contracts. Both discrete and continuous action spaces are considered and volatility scaling is incorporated to create reward functions which scale trade positions based on market volatility. We test our algorithms on the 50 most liquid futures contracts from 2011 to 2019, and investigate how performance varies across different asset classes including commodities, equity indices, fixed income and FX markets. We compare our algorithms against classical time series momentum strategies, and show that our method outperforms such baseline models, delivering positive profits despite heavy transaction costs. The experiments show that the proposed algorithms can follow large market trends without changing positions and can also scale down, or hold, through consolidation periods.
#117 – Lottery Effect in Stocks
#268 – Expected Skewness and Momentum in Stocks
#390 – Lottery Stocks and the 52-Week High
Chung: Retail Trading and Momentum Profitability
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3486843
Abstract:
Monthly momentum returns increase monotonically across quintile portfolios of stocks sorted by retail trading participation with a top-minus-bottom spread of 1.42% (t-statistics = 3.46). Stocks that are heavily traded by retail investors exhibit lottery-like features such as low prices, high idiosyncratic volatilities/skewness, and high past maximum returns. Using lottery characteristics to proxy for the extent of retail trading, future momentum profits monotonically increase in the cross-sectional lotteryness of stocks over a 77-year back-testing period for which retail trading data is unavailable. Further analysis shows that lottery-like stocks exhibit stronger comovements that amplify momentum profits.
#460 – ESG Factor Investing Strategy
#461 – ESG Momentum
MELAS, NAGY, NISHIKAWA, LEE, GIESE: Foundations of ESG Investing – Part 1: How ESG Affects Equity Valuation, Risk and Performance
https://www.msci.com/www/research-paper/foundations-of-esg-investing/0795306949
Abstract:
Many studies have focused on the relationship between companies with strong ESG characteristics and corporate financial performance. However, these have often struggled to show that positive correlations — when produced — can in fact explain the behavior. This paper provides a link between ESG information and the valuation and performance of companies, both through their systematic risk profile (lower costs of capital and higher valuations) and their idiosyncratic risk profile (higher profitability and lower exposures to tail risk). The research suggests that changes in a company’s ESG characteristics may be a useful financial indicator. ESG ratings may also be suitable for integration into policy benchmarks and financial analyses.
And four interesting free blog post has been published during last 2 weeks:
A Comparison of Global Factor Models
Mirror, mirror on the wall, what’s the best factor model of them all? We at Quantpedia are probably not the only one asking this question. A lot of competing factor models are described in the academic literature and used in practice. That’s the reason why we consider a new research paper written by Matthias Hanauer really valuable. He compared several commonly employed factor models across non-U.S. developed and emerging market countries and answered the question from the beginning of this paragraph. Which model seems the winner? The six-factor model proposed in Barillas et al. (2019) that substitutes the classic value factor in the Fama and French (2018) six-factor model for a monthly updated value factor …
Authors: Hanauer
Title: A Comparison of Global Factor Models
Rational Panic on Markets Because of Coronavirus?
Financial markets are in panic mode. Everybody is talking about the next bear market and economic implications of spreading coronavirus to the whole world. People are split into two groups. One group reasons that a new covid-19 virus is just a stronger flu. Other are worried and draw parallels to Spanish flu pandemic with tens of millions of dead. We would like to show you two charts which can explain why the high market volatility can be completely rational.
Author: Vojtko
Bitcoin in a Time of Financial Crisis
One of the very often promoted attributes of Bitcoin is said to be its “safe heaven” characteristic. Some cryptocurrency proponents advocate that Bitcoin can be used as a store of value mainly during the economic and financial crisis. We argue that it’s not so. Bitcoin (and all cryptocurrencies too) is, in our opinion, fundamentally more similar to stocks of small companies from the technological sector. It is a very speculative bet on blockchain technology. It may seem unrelated to the broader equity market (like the S&P 500 index) during normal times. But when a stressful time comes, investors are more concerned to meet a deadline for the next mortgage payment. This is the time when the speculative bets are closed, and cash is raised. And this is precisely the time when Bitcoin falls as equities do too.
Authors: Vojtko, Cisar
Modelling the Bottom of the Covid-19 Financial Crisis
The global pandemic of current scope is something that was experienced by only a few living people. We have some historical accounts of how it unfolded in the past, but otherwise, it is uncharted territory. It is a true Black Swan event – event that I believe was in nobody’s lineup of stress testing scenarios. But we can still try to get some understanding of the scope of the current situation. The actual global crisis is a mix of 2 crisis. The first one is the health-care / pandemic crisis, during which millions of people will be infected, and unfortunately, a lot of people will die. The second crisis is the economic crisis/recession, which will follow simultaneously with (or soon after) the first one (due to the decrease in worldwide supply and demand). The second crisis cannot end before the first one is solved. We cannot exactly say when the market bottom will occur, but at least we can try to model the minimum time needed for things to get under control during the pandemic.
Author: Vojtko
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
