New strategies:
#575 – Momentum and Low Risk Effects in India
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Simple strategy
Backtest period: 2007-2018
Indicative performance: 10.84%
Estimated volatility: not stated
Source paper:
Mayank Joshipura, Nehal Joshipura: Low-Risk Effect: Evidence, Explanations and Approaches to Enhancing the Performance of Low-Risk Investment Strategies
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3613658
Abstract:
The authors offer evidence for low-risk effect from the Indian stock market using the top-500 liquid stocks listed on the National Stock Exchange (NSE) of India for the period from January 2004 to December 2018. Finance theory predicts a positive risk-return relationship. However, empirical studies show that low-risk stocks outperform high-risk stocks on a risk-adjusted basis, and it is called low-risk anomaly or low-risk effect. Persistence of such an anomaly is one of the biggest mysteries in modern finance. The authors find strong evidence in favor of a low-risk effect with a flat (negative) risk-return relationship based on the simple average (compounded) returns. It is documented that low-risk effect is independent of size, value, and momentum effects, and it is robust after controlling for variables like liquidity and ticket-size of stocks. It is further documented that low-risk effect is a combination of stock and sector level effects, and it cannot be captured fully by concentrated sector exposure. By integrating the momentum effect with the low-volatility effect, the performance of a low-risk investment strategy can be improved both in absolute and risk-adjusted terms. The paper contributed to the body of knowledge by offering evidence for: a) robustness of low-risk effect for liquidity and ticket-size of stocks and sector exposure, b) how one can benefit from combining momentum and low-volatility effects to create a long-only investment strategy that offers higher risk-adjusted and absolute returns than plain vanilla, long-only, low-risk investment strategy.
#576 – Boosted Regression Trees in Corporate Bonds
Period of rebalancing: Monthly
Markets traded: bonds
Instruments used for trading: bonds
Complexity: Very complex strategy
Backtest period: 2005-2020
Indicative performance: 4.21%
Estimated volatility: 2.46%
Source paper:
Kaufmann, Hendrik and Messow, Philip and Vogt, Jonas: Boosting Momentum
https://ssrn.com/abstract=3668928
Abstract:
Machine learning techniques have gained enormously in popularity in recent years, but so far only to a very limited extent in fixed income research. In this paper we therefore like to do some pioneering work and apply Boosted Regression Trees to Equity Momentum in the corporate bond market. We report large performance gains to investors using these machine learning driven forecasts, roughly doubling the alpha and information ratio to industry standard Equity Momentum factors. The most important variables within our model framework are the most recent equity performance, liquidity and size.
#577 – Surprise in Short Interest
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Simple strategy
Backtest period: 1980-2013
Indicative performance: 4.24%
Estimated volatility: 7.24%
Source paper:
Hanauer, Matthias Xaver and Lesnevski, Pavel and Smajlbegovic, Esad: Surprise in Short Interest
https://ssrn.com/abstract=3736891
Abstract:
We extract the news component of short-selling activity by accounting for important cross-sectional, distributional differences in short interest. The resulting measure of surprise in short interest negatively predicts the cross section of both U.S. and international equity returns. Our results also indicate that this predictability originates from short sellers’ informed trading on mispricing and the market’s underreaction to the news component of short-sale reports. Consistent with the notion of costly arbitrage, the return predictability is stronger among illiquid, volatile stocks and stocks with high information uncertainty, but importantly, unrelated short-selling frictions.
#578 – Combining Smart Factors Momentum and Market Portfolio
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1993-2020
Indicative performance: 11.91%
Estimated volatility: 10.46%
Source paper:
Padyšák, Matúš: The active vs passive: smart factors, market portfolio or both?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3745517
Abstract:
While there may be debates about passive and active investing, and even blogs about the numbers of active funds that were outperformed by the market, the history taught us that the outperformance of active or passive investing is cyclical. As a proxy for the active investing, the paper examines factor strategies and their smart allocation using fast or slow time-series momentum signals, the relative weights based on the strength of the signals and even blending the signals. While the performance can be significantly improved, using those smart approaches, the factors still got beaten by the market in both US and EAFE sample. However, the passive approach did not show to be superior. The factor strategies and market are significantly negatively correlated and impressively complement each other. The combined Smart Factors and market portfolio vastly outperforms both factors and market throughout the sample in both markets. With the combined approach, the ever-present market falls can be at least mitigated or profitable thanks to the factors.
#579 – Variance Scaled Momentum in Emerging Markets
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately complex strategy
Backtest period: 1991-2017
Indicative performance: 17.21%
Estimated volatility: 9.74%
Source paper:
Hilal Anwar Butt , James W. Kolari and Mohsin Sadaqat: Revisiting Momentum Profits in Emerging Markets
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3704504
Abstract:
This study investigates the cross-sectional and time-series properties of momentum returns in 19 emerging market countries. In general, consistent with previous studies, momentum strategies in emerging markets underperform those in the U.S. and other developed markets. To help reconcile these differences, we show that momentum profits are negatively exposed to market and liquidity factors, which is more important in down market states. Given higher market returns and lower liquidity in emerging markets, this negative exposure tends to increase momentum crashes when market rebounds after depressed market conditions and, in turn, lower momentum returns in emerging market countries. Finally, risk management of momentum reduces exposure to market and liquidity factors, thereby boosting returns, Sharpe ratios, and asset pricing model alphas.
#580 – Capturing Energy Risk Premia
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures
Complexity: Complex strategy
Backtest period: 2001-2019
Indicative performance: 12.38%
Estimated volatility: 13.75%
Source paper:
Adrian Fernandez-Perez, Ana-Maria Fuertes, and Joelle Miffre: Capturing Energy Risk Premia
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3368936
Abstract:
The article models the risk premium present in energy futures markets. This is done first by analyzing the performance of long-short portfolios based on single styles, and then by integrating these styles into an unique portfolio. Aligned with the hedging pressure hypothesis and the theory of storage, investors earn a premium of at least 7.5% a year for bearing hedgers’ risk of price fluctuation and for holding energy futures with low inventories. Integrating the signals into an unique portfolio increases the premium further to 12.4% a year. Out of all the integration approaches considered, the easiest one is also the best in term of performance; it merely consists of giving equal weights to the styles considered within the integrated portfolio. The results are robust to the consideration of transaction costs, alterative specifications of the integrated portfolio, data mining and various sub-periods.
New research papers related to existing strategies:
#49 – S&P 500 Index Addition Effect
Vijh, Anand M. and Wang, Jiawei: Negative Returns on Addition to S&P 500 Index and Positive Returns on Deletion? New Evidence on Attractiveness of S&P 500 vs. S&P 400 Indexes
https://ssrn.com/abstract=3676340
Abstract:
In recent years, the majority of additions to and deletions from the S&P 500 index have been stocks that were previously or subsequently included in the S&P 400 index. The announcement returns of these changes have been the opposite of what has been documented for all S&P 500 additions and deletions in an extensive literature. During 2016-2019, such ‘upward additions’ to the S&P 500 index resulted in an average announcement excess return of -2.31% over a three-day period while ‘downward deletions’ resulted in an excess return of +1.21%. We explain these new results by the increasing ownership of S&P 400 stocks by institutional investors, the majority of whom are active fund managers. Our results thus show the increasing benefits of being included in the mid-cap S&P 400 index relative to being included in the large-cap S&P 500 index.
#536– Machine Learning Stock Picking
Noguer i Alonso, Miquel and Srivastava, Sonam: Deep Reinforcement Learning for Asset Allocation in US Equities
https://ssrn.com/abstract=3711487
Abstract:
Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. So it is first a prediction problem for the vector of expected returns and covariance matrix and then an optimization problem for returns, risk, and market impact, usually a quadratic programming one. Investors and financial researchers have been working with approaches like mean-variance optimization, minimum variance, risk parity, and equally weighted and several methods to make expected returns and covariance matrices’ predictions more robust and after use mean-variance like the Black Litterman model. This paper demonstrates the application of reinforcement learning to create a financial model-free solution to the asset allocation problem, learning to solve the problem using time series and deep neural networks. We demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. We use a deep reinforcement model on US stocks using different deep learning architectures. We use Long Short Term Memory networks, Convolutional Neural Networks, and Recurrent Neural Networks and compare them with more traditional portfolio management approaches like mean-variance, minimum variance, risk parity, and equally weighted. The Deep Reinforcement Learning approach shows better results than traditional approaches using a simple reward function and only being given the time series of stocks. In Finance, no training to test error generalization results come guaranteed. We can say that the modeling framework can deal with time series prediction and asset allocation, including transaction costs.
#536– Machine Learning Stock Picking
Noguer i Alonso, Miquel and Batres-Estrada, Gilberto and Moulin, Aymeric: Deep Learning for Equity Time Series Prediction
https://ssrn.com/abstract=3735940
Abstract:
We examine the performance of Deep Learning methods applied to equity financial time series. Predicting equity time series is a crucial topic in Finance. To form equity portfolios and do asset allocation, we need to predict returns, compute their risk, and optimize market impact. One of the modeling benefits of Deep Learning architectures is the ability to model non-linear highly dimensional problems. The lack of transparency and a rigorous mathematical theory could be considered less positive sides. The fact that most progress in Deep Learning has been made by trial and error is also cumbersome. Equity financial time series is a challenging domain with some stylized facts: weak stationarity, fat tails in return distributions, small data sets compared to other areas of Artificial Intelligence (AI), slow decay of autocorrelation in returns, and volatility clustering, to name the most important ones. We perform a comparative study between Long ShortTerm Memory Networks (LSTM), Recurrent Neural Networks (RNN), Deep Feed-Forward neural networks (DNN), and Gated Recurrent Unit Networks (GRU). We perform two types of studies. The first focused on a univariate test, and the second a multivariate test. Our tests show that the LSTM performs the best compared to other Deep Learning and classical machine learning models. In terms of performance metrics, the LSTM is better than the baseline model. We also show that the predictions are better than chance. There is enough evidence thatRNN and LSTM can deal with stationary time series and learn the data generating process. Nevertheless, predicting equity non-stationary time series, with market developments like the one caused by the COVID-19 pandemic in 2020, is challenging.
#45 – Short Interest Effect – Long-Short Version
#46 – Short Interest Effect – Long Only version
#514 – Retail Trading and Momentum Profitability
Boehmer, Ekkehart and Song, Wanshan: Smart Retail Traders, Short Sellers, and Stock Returns
https://ssrn.com/abstract=3723096
Abstract:
Using short sell transactions data from 2010 to 2016, this paper is the first to provide a comprehensive sample of short selling initiated by retail investors. We find that retail short selling can predict negative stock returns. A trading strategy that mimics weekly retail shorting earns an annualized risk-adjusted value-(equal-) weighted return of 6% (12.25%). Their predictive power is beyond that coming from retail investors as a group or from off-exchange institutional short sellers. Our results suggest that retail short sellers can profitably exploit public information, especially when it is negative. Retail short sellers also tend to be contrarians who provide liquidity when the market is one-sided due to (institutional) buying pressure.
#533 – FOMC Cycle and Credit Risk
#497 – Monetary (FOMC) Momentum in Stocks
#356 – The Dollar Ahead of FOMC Target Rate Changes
#317 – Trading FOMC Announcements with Summary of Economic Projections
#287– The FOMC Cycle Effect
#256 – Shorting Volatility During FOMC Meeting Days
Liu, Hong and Tang, Xiaoxiao and Zhou, Guofu, Recovering the FOMC Risk Premium
https://ssrn.com/abstract=3553572
Abstract:
The Federal Open Market Committee (FOMC) meetings have significant impact on market returns. We propose a methodology to recover the risk premium associated with FOMC meetings from option prices. We also predict the sizes of upward/downward market price jumps after an imminent FOMC meeting. In our empirical analysis, with observed price data for 83 meetings and with data backed out via machine learning for the remaining 109 meetings from 1996 to 2019, we find that the risk premium varies from 2 to 299 basis points (bps), with an average of 41 bps which is consistent with the average realized returns documented in the literature. The average predicted upward jump size is 101 bps, and the average predicted downward jump size is 129 bps.
And three interesting free blog posts have been published during last 2 weeks:
ESG scores are already well-established, and nobody doubts that the scores affect investors or companies. Investors seem to care more and more about the other aspects of the stocks and not just the profits – the human welfare, ecology or social aspects of our lives. Additionally, numerous researches point out that the ESG scores can positively affect also the portfolios. However, the novel research by Colak et al. (2020), has examined other implications of the ESG scores: how the ESG affect the CEOs. To be more precise, how the adverse ESG events and subsequent negative media attention affects the longevity of the CEOs. The finding is that negative event significantly increase the probability of the CEO being replaced. Overall, the research paper highlights the importance of ESG scores in the corporate world.
Every week, through these posts, we point to interesting academic research papers. This week’s blog is slightly different, yet no less engaging. This blog includes numerous interesting charts from more than hundred charts in the CUSTOM REPORT: U.S. LARGE INDEX by the PHILOSOPHICAL ECONOMICS using OSAM Research Database. The report consists of the visually presented analysis of the U.S. Large index. The analysis includes the composition, returns, individual stocks, sector and factor allocations, and six fundamentals. The report contains comprehensive information about the large caps in the U.S. market from 1963 to 2020 and is worthy of a look.
During the festive season, everything is more relaxed, and this week’s blog is no exception. The stock-picking abilities of animals are not the main research topic for most academics, yet the stock-picking skills, for example, of monkeys, were previously documented. To our best knowledge, the paper of Belmont et al. (2020) is the first that examines the stock-picking abilities of reindeer. Moreover, the performance of reindeer is compared to the US senators during 2020. Trading of US senators or congresspeople is particularly interesting since there are concerns about informed stock trading. Especially during the COVID pandemic, where the governments have a significant influence on the economies. The finding of the paper is that the performance of the senate is behind reindeer. However, the reindeer exhibit herding behaviour and momentum preferences. Perhaps, their abilities should be examined more deeply during a more extended period.
Plus, the following six trading strategies have been backtested in QuantConnect in the previous two weeks:
#91 – Momentum Factor and Style Rotation Effect
#119 – Google Search Effect
#134 – Equity Sector Timing with IPO Factor
#138 – Repurchase/New issue Effect
#564 – Intraday Momentum in Fixed Income
#565 – The Ex-dividend Date in the European Market
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
