New strategies:
#620 – Long Term Time-series Momentum in India
Period of rebalancing: Weekly
Markets traded: equities
Instruments used for trading: stocks, futures
Complexity: Moderately complex strategy
Backtest period: 2010-2019
Indicative performance: 16.02%
Estimated volatility: 15.1%
Source paper:
Srivastava, Sonam and Chakravorty, Gaurav and Singhal, Mansi: Momentum in the Indian Equity Markets: Positive Convexity and Positive Alpha
https://ssrn.com/abstract=3345280
Abstract:
We present effective momentum strategies over the liquid equity futures market in India. We evaluate and determine the persistence of the returns at various look-backs ranging from quarterly and weekly to more granular look-backs. We look at a universe of the liquid equity instruments traded across the Indian markets to evaluate this anomaly. We evaluate momentum across the two datasets based on frequency – daily data and intraday bar data. On the daily scale we compare momentum with other style factors. In the intraday scale we evaluate time series momentum or absolute momentum and cross-sectional momentum or relative momentum. We demonstrate that at the optimal horizon, momentum strategies on securities in India can be a source of uncorrelated alpha. We use active risk-budgeting at a given target risk for portfolio construction. We will show in a separate publication how it outperforms mean-variance optimization.
#621 – Cross-sectional Inraday Sector Momentum in India
Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks, futures
Complexity: Moderately complex strategy
Backtest period: 2010-2019
Indicative performance: 27.46%
Estimated volatility: 17.48%
Source paper:
Srivastava, Sonam and Chakravorty, Gaurav and Singhal, Mansi: Momentum in the Indian Equity Markets: Positive Convexity and Positive Alpha
https://ssrn.com/abstract=3345280
Abstract:
We present effective momentum strategies over the liquid equity futures market in India. We evaluate and determine the persistence of the returns at various look-backs ranging from quarterly and weekly to more granular look-backs. We look at a universe of the liquid equity instruments traded across the Indian markets to evaluate this anomaly. We evaluate momentum across the two datasets based on frequency – daily data and intraday bar data. On the daily scale we compare momentum with other style factors. In the intraday scale we evaluate time series momentum or absolute momentum and cross-sectional momentum or relative momentum. We demonstrate that at the optimal horizon, momentum strategies on securities in India can be a source of uncorrelated alpha. We use active risk-budgeting at a given target risk for portfolio construction. We will show in a separate publication how it outperforms mean-variance optimization.
#622 – Intraday Time-series Momentum in India
Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks, futures
Complexity: Moderately complex strategy
Backtest period: 2010-2019
Indicative performance: 12.83%
Estimated volatility: 12.95%
Source paper:
Srivastava, Sonam and Chakravorty, Gaurav and Singhal, Mansi: Momentum in the Indian Equity Markets: Positive Convexity and Positive Alpha
https://ssrn.com/abstract=3345280
Abstract:
We present effective momentum strategies over the liquid equity futures market in India. We evaluate and determine the persistence of the returns at various look-backs ranging from quarterly and weekly to more granular look-backs. We look at a universe of the liquid equity instruments traded across the Indian markets to evaluate this anomaly. We evaluate momentum across the two datasets based on frequency – daily data and intraday bar data. On the daily scale we compare momentum with other style factors. In the intraday scale we evaluate time series momentum or absolute momentum and cross-sectional momentum or relative momentum. We demonstrate that at the optimal horizon, momentum strategies on securities in India can be a source of uncorrelated alpha. We use active risk-budgeting at a given target risk for portfolio construction. We will show in a separate publication how it outperforms mean-variance optimization.
#623 – Quality Factor in Stocks
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1986-2016
Indicative performance: 12.2%
Estimated volatility: 12.32%
Source paper:
Michael Cook, Edward Hoyle, Matthew Sargaison, Dan Taylor, Otto Van Hemert: The Best Strategies for the Worst Crises
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2986753
Abstract:
Hedging equity portfolios against the risk of large drawdowns is notoriously difficult and expensive. Holding, and continuously rolling, at-the-money put options on the S&P 500 is a very costly, if reliable, strategy to protect against market sell-offs. Holding ‘safe-haven’ US Treasury bonds, while providing a positive and predictable long-term yield, is generally an unreliable crisis-hedge strategy, since the post-2000 negative bond-equity correlation is a historical rarity. Long gold and long credit protection portfolios appear to sit between puts and bonds in terms of both cost and reliability.
In contrast to these passive investments, we investigate two dynamic strategies that appear to have generated positive performance in both the long-run but also particularly during historical crises: futures time-series momentum and quality stock factors. Futures momentum has parallels with long option straddle strategies, allowing it to benefit during extended equity sell-offs. The quality stock strategy takes long positions in highest-quality and short positions in lowest-quality company stocks, benefitting from a ‘flight-to-quality’ effect during crises. These two dynamic strategies historically have uncorrelated return profiles, making them complementary crisis risk hedges. We examine both strategies and discuss how different variations may have performed in crises, as well as normal times, over the years 1985 to 2016.
#624 – Reference Prices and Bad News
Period of rebalancing: Quarterly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1962-2018
Indicative performance: 15.32%
Estimated volatility: 9.49%
Source paper:
Brad Cannonz, Hannes Mohrschladt: Do Reference Prices Impact How Investors Respond to News?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3712902
Abstact:
We provide evidence that reference prices impact how investors respond to news. When current prices are farther from a reference price, investors react more strongly to news. We first document that individual investors are more (less) likely to sell a stock following bad (good) news when the stock’s trading price is farther from the investor’s purchase price. Motivated by this micro-level evidence, we construct a stock-level measure to capture the distance between a stock’s trading price and its purchase price for the average investor. We provide evidence that this distance from purchase price produces a substantial amount of cross-sectional variation in the degree to which stocks over- or underreact to news. Stocks trading farthest from their purchase price react more strongly to news than stocks trading near their purchase price. Consistent with relative overreaction, stocks trading farthest from their purchase price also exhibit greater return reversals following news days. We document that a cross-sectional strategy exploiting these return patterns earns a monthly alpha of 0.93%. These findings are distinct from alternative explanations related to size, illiquidity, and volatility. Our evidence instead suggests that reference prices have a meaningful impact on how investors respond to news.
New research papers related to existing strategies:
#536 – Machine Learning Stock Picking
Noguer i Alonso, Miquel and Batres-Estrada, Gilberto and Yahiaoui, Ghozlane: A Meta-Learning approach to Model Uncertainty in Financial Time Series
https://ssrn.com/abstract=3814938
Abstract:
Financial markets have experienced several negative sigma events in recent years; these events occur with much more regularity than current risk models can predict. There is no guarantee that the training set’s data generating process will be the same in the test set in finance. Mathematical models are designed to operate with unlimited and changing data, and yet, actual events keep making life hard for most models. The assumption of independent and identically distributed random variables and a stationary time series do not hold in reality. Over-reliance on historical data and backtesting of models is not a sufficient approach to overcome these challenges. Reinforcement-learning faces similar challenges when applied to financial time series. Out-of-distribution generalization is a problem that cannot be solved without assumptions on the data generating process. If the test data is arbitrary or unrelated to the training data, then generalization is not possible. Finding these particular principles could potentially help us build AI and financial modeling systems. N-Beats, Oreshkin et al. [2020], is a deep neural architecture with backward and forward residual links and a deep stack of fully-connected layers. N-Beats can be considered as a meta-learning model for time series prediction. Meta-Learning is a machine learning approach that intends to design models that can learn new skills or adapt to new environments rapidly with few training examples. We explore the performance of N-Beats and compare its performance with other deep learning models. The results are not conclusive in establishing N-Beats as a better model than the other models tested in this study. We show in this study that other neural network-based models offer similar performance.
#536 – Machine Learning Stock Picking
#601 – Learning to Rank and Cross-sectional Momentum
Katongo, Musonda and Bhattacharyya, Ritabrata: The Use of Deep Reinforcement Learning in Tactical Asset Allocation
https://ssrn.com/abstract=3812609
Abstract:
The Tactical Asset Allocation (TAA) problem is a problem to accurately capture short to medium term market trends and anomalies in order to allocate the assets in a portfolio so as to optimize its performance by increasing the risk adjusted returns. This project seeks to address the Tactical Asset Allocation problem by employing Deep Reinforcement Learning (DRL) Algorithms in a Machine Learning Environment as well as employing Neural Network Autoencoders for selection of portfolio assets. This paper presents the implementation of this proposed methodology applied to 30 stocks of the Dow Jones Industrial Average (DJIA). In (1), the Introduction to the project objectives is done with the Problem Description presented in (2). Part (3) presents the literature review of similar studies in the subject area. The methodology used for our implementation is presented in (4) whilst (5) and (6) presents the benchmark portfolios and the DRL portfolios development respectively. The evaluation of the performance of the models is presented in (7) and we present our conclusions and the future works in (8).
#582 – Carbon Risk in the Cross Section of Corporate Bond Returns
Amiraslani, Hami and Lins, Karl V. and Servaes, Henri and Tamayo, Ane Miren: Trust, Social Capital, and the Bond Market Benefits of ESG Performance
https://ssrn.com/abstract=2978794
Abstract:
We investigate whether a firm’s social capital, and the trust that it engenders, are viewed favorably by bondholders. Using firms’ environmental and social (E&S) performance to proxy for social capital, we find no relation between social capital and bond spreads over the period 2006-2019. However, during the 2008-2009 financial crisis, which represents a shock to trust and default risk, high-social-capital firms benefited from lower bond spreads. These effects are stronger for firms with higher expected agency costs of debt and firms whose E&S efforts are more salient. During the crisis, high-social-capital firms were also able to raise more debt, at lower spreads, and for longer maturities. We find no evidence that the governance element of ESG is related to bond spreads.
#26 – Value (Book-to-Market) Factor
Stagnol, Lauren and Lopez, Christian and Roncalli, Thierry and Taillardat, Bruno: Understanding the Performance of the Equity Value Factor
https://ssrn.com/abstract=3813572
Abstract:
After decades of sound performance, doubts have been raised on the ability of the equity value factor to continue to deliver a positive performance in the aftermath of the 2008 Global Financial Crisis. Indeed, in a context dominated by low yields, sluggish growth and subdued inflation combined with an accelerating digitalization of the economy, the performance of value strategies struggled over the past decade. In this paper, we investigate potential drivers behind this performance lag, such as macroeconomic and microeconomic determinants, ESG characteristics or credit-borrowed components. Based on European and American data, we find that inflation and tightening credit spread levels are the most supportive factors for value stocks. As far as interest rates are concerned, their sustained low levels prevented the value stock universe from clearing its most distressed issuers, also known as “deep value”, and thus dampened value performance. As a matter of fact, we show that value has not been systematically an investment strategy bearing a heightened default risk. Our ESG analysis corroborates the “transatlantic divide”, the historical gap between the U.S. and Europe on this front, and shows that value and growth stocks are not necessarily all brown and green stocks. In addition, we demonstrate that the small cap segment has not been the magical cure to value underperformance. Finally, we conclude that value is not dead yet, and might even have bright days ahead considering the current improvements in market sentiment, especially if inflation does materialize. Nevertheless, we also emphasize that the current value risk factor is probably different in nature from the one we observed during the golden age of value investing at the beginning of the 2000s. Indeed, trading facilities, ease of access to fundamental data for a large number of investors, ESG investing and the digitalization of the economy may have changed the rules of the game.
#591 – Machine Learning and Earnings Announcements
POONGJIN CHO,JI HWAN PARK AND JAE WOOK SONG: Equity Research Report-Driven Investment Strategy in Korea Using Binary Classification on Stock Price Direction
https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9382307
Abstract:
This research examines and proposes an investment strategy by combining the natural language processing on the equity research reports published in the Korean financial market and machine learning algorithms for binary classification. At first, we deduce the part-of-speech from the report using the KoNLPy and Mecab. Then, we define 33 features as the input variables and perform the binary classification on the price direction of the stocks recommended in the report using various machine learning algorithms. Note that we investigate the model performance in detail by dividing the entire period into three sub-periods, including pre-COVID-19 for the sideways market, COVID-19 for the crashing market, and post-COVID-19 for the extreme bullish market. We confirm that the random forest is the best classifier for all periods, so we utilize its results on positively predicted stocks in the test set as the investment universe for the monthly re-balancing and buy-and-hold investment. The proposed strategy shows a signicantly higher return on investment than benchmarks during the pre-COVID-19 and COVID-19 periods, whereas the comparable return during the post-COVID-19.
And two interesting free blog posts have been published during last 2 weeks:
This article is a primer into the methodology we use for the Portfolio Risk Parity report, which is a part of our Quantpedia Pro offering. We explain three risk parity methodologies – Naive Risk Parity (inverse volatility weighted), Equal Risk Contribution and Maximum Diversification. Quantpedia Pro allows the design of model risk parity portfolios built not just from the passive market factors (commodities, equities, fixed income, etc.) but also from systematic trading strategies and uploaded user’s equity curves.
ESG Incidents and Shareholder Value
ESG scores are the modern trend in the financial markets, and while this sustainable investing has its critics, it seems to become a regular part of the markets. Frequently, and probably rightfully, ESG is criticized for the lack of commonality across various “scorers”, and as a result, there might be a large dispersion among the score of one firm. The reason is that the score usually consists of different metrics and aggregation methodology. Apart from this “long-term” score, investors can easily recognize the “short-term” score, which can be proxied by negative incidents such as pollution, poor social aspects, social or governance scandals and so on. Moreover, these incidents could be more informative about (un)sustainable practice compared to ESG scores. These ESG incidents are studied by the novel research of Simon Glossner (2021). Using incidents news, the author provides interesting results that mainly support proponents of sustainable investing. Poor ESG performance proxied by incidents predicts more incidents in the future, lower profitability which should subsequently spill to negative performance in future. For example, portfolios consisting of negative incidents stocks significantly underperform the market for both US and European stocks. Therefore, this research paper is a compelling addition to the literature that, apart from social aspects, connects ESG also with performance.
Plus, the following five trading strategies have been backtested in QuantConnect in the previous two weeks:
#319 – Combined Stock and CDS Momentum
#474 – Return Cross-Predictability in Firms with Similar Employee Satisfaction
#610 – Presidential Economic Approval Rating and the Cross-Section of Stock Returns
#617 – Earnings Announcement Beta
#618 – Bond Yield Changes and the Cross Section of Equity Indices
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
