New strategies:
#920 – Financial Uncertainty Explains Cryptocurrency Returns
Period of rebalancing: Monthly
Markets traded: cryptos
Instruments used for trading: cryptos
Complexity: Complex strategy
Backtest period: 2014 – 2022
Indicative performance: 20.7%
Estimated volatility: 10.69%
Source paper:
Colak, Gonul and Della Vedova, Joshua and Foley, Sean and Mai, Sinh Thoi: Financial Uncertainty and the Cross-Section of Cryptocurrency Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4510856
Abstract:
Our study evaluates the return sensitivity of cryptocurrencies to various measures of uncertainty (uncertainty beta). We identify that crypto returns react primarily to financial uncertainty, which is the unforecastable component of multiple financial indicators. However, crypto returns are not sensitive to other forms of uncertainty such as macro, real, or policy uncertainty, as well as VIX, and inflation. The portfolio analysis yields a significant financial uncertainty premium of around 21% per month, which is driven by the outperformance (underperformance) of cryptocurrencies with a negative (positive) uncertainty beta. The portfolio returns are more potent in coins with speculative, rather than transactional, features such as proof-of-work, non-token, and mineable. Our findings suggest that large investors exhibit a willingness to pay higher premiums for cryptocurrencies with positive uncertainty betas, as these assets can be used as a hedging tool within a larger financial portfolio.
#921 – Measuring Firm Quality Using Machine Learning
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1976-2018
Indicative performance: 29.53%
Estimated volatility: 31.75%
Source paper:
Chen, Ch. and Ke, B. and Zhao Q. : Measuring Firm Quality Using Machine Learning
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4434498
Abstract:
Firm quality is a foundational construct in the fundamental analysis literature. Asness et al. (2019), a recent representative example of this literature, measures firm quality based on 19 fundamental ratios guided by valuation theory (referred to as Asness’ Q score). We examine whether it is possible to leverage the power of machine learning to construct a better measure of firm quality using the same 19 fundamental signals. We show that an advanced machine learning model called XGBoost based on the 19 ratios can outperform a linear OLS regression model based on Asness’ Q score (our benchmark) by 27%. However, we fail to find economically significant evidence that adding more raw accounting data items identified by the prior literature or financial statements or using alternative ratios derived from the DuPont decomposition can yield stronger prediction models. We show that our measure of firm quality based on XGBoost and the 19 ratios can better explain contemporaneous stock prices than Asness’ Q score. In addition, a value investing trading strategy using our XGBoost model outperforms the same trading strategy based on Asness’ Q score by an economically significant margin.
#922 – Price-Based Quantitative Strategy for Country Valuation
Period of rebalancing: Quarterly
Markets traded: equities
Instruments used for trading: ETFs, funds
Complexity: Simple strategy
Backtest period: 1992-2023
Indicative performance: 2.39%
Estimated volatility: 14.78%
Source paper:
Dujava, Cyril and Vojtko, Radovan: Analysis of Price-Based Quantitative Strategies for Country Valuation
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4579947
Abstract:
The article delves deeper into the concept of value investing, which involves finding stocks that are trading below their intrinsic value or book value. Unlike the efficient market hypothesis, which holds that stock prices always reflect their intrinsic value, value investors believe that stocks can be overvalued or undervalued due to a variety of factors. element. The article emphasizes the long-term nature of value investing, exemplified by Warren Buffett’s approach. The thrust of the study is to simplify the concept of relative valuation across countries using only price data and not non-price data such as GDP or gross income. The article explores different strategies, such as Price vs Price. MA, Past Momentum signal and linear regression, to determine the relative value of countries. However, the results indicate that pricing signals based solely on price are weaker than those using variables other than price.
#923 – Intraday Market Return Predictability Based on the Factor ZOO
Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1996-2020
Indicative performance: 17.45%
Estimated volatility: 16.78%
Source paper:
Aleti, S. and Bollerslev, T. and Siggaard, M.: Liquidity Forecasts and Stock Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4388560
Abstract:
We document strong intraday market return predictability based on lagged high-frequency cross-sectional returns of the factor zoo. Our results rely crucially on LASSO to regularize our predictive regressions along with techniques from financial econometrics to differentiate between continuous and discontinuous price increments. Trading strategies that utilize our forecasts generate sizeable out-of-sample Sharpe ratios and alphas after accounting for transaction costs. We trace the superior performance to periods of high economic uncertainty and a few key factors related to tail risk and liquidity, pointing to slow-moving capital and the gradual incorporation of new information as the underlying economic mechanisms at work.
#924 – Profitability Context and the Cross-Section of Stock Returns
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1999-2020
Indicative performance: 6.8%
Estimated volatility: 10.46%
Source paper:
Kim., G. A. and Nikolaev, V. V.: Profitability Context and the Cross-Section of Stock Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4459383
Abstract:
Asset pricing models implicitly assume that firm characteristics are context-free. At the same time, companies provide a substantial narrative context that helps investors to put numeric information in perspective. Management may discuss non-quantitative factors that influence performance, such as changes in competitive strategies, future plans, etc. We study the importance of contextual information for asset pricing by focusing on the narrative context surrounding profitability numbers. We use machine learning to incorporate contextual information into the measurement of profitability. Context-adjusted profitability has a superior ability to explain expected returns, both statistically and economically, compared to conventional operating profitability. Further, the context-adjusted profitability factor performs better in portfolio tests and helps to resolve the biggest challenge facing the five-factor model (Fama and French [2015]). Overall, we find that accounting for context adds significant value for investors and can improve the asset pricing models.
#925 – Option Factor Momentum
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: options
Complexity: Very complex strategy
Backtest period: 1996-2021
Indicative performance: 13.62%
Estimated volatility: 14.93%
Source paper:
Käfer, Niclas and Moerke, Mathis and Wiest, Tobias: Option Factor Momentum
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4405852
Abstract:
We document profitable cross-sectional and time-series momentum in a broad set of 56 option factors constructed from monthly sorts on daily delta-hedged option positions. Option factor returns are highly autocorrelated, but momentum profits of strategies with longer formation periods are mainly driven by high mean returns that persistently differ across factors. Momentum effects are the strongest in the factors’ largest principal components, consistent with findings for stock factor momentum. Finally, we find a new form of momentum in options markets: momentum in single delta-hedged option returns. Option factor momentum fully subsumes option momentum, whereas option momentum cannot explain option factor momentum. Our findings provide insights into the channels that drive option momentum and have implications for designing profitable option trading strategies.
New research papers related to existing strategies:
#656 – Machine Learning for Extracting Pessimism from Newspaper Pictures and Text
Okada, Katsuhiko and Hamuro, Yukinobu and Nakasuji, Moe: Decoding the Unique Price Behavior in the Japanese Stock Market with Convolutional Neural Networks
https://ssrn.com/abstract=4478013
Abstract:
Technical analysis charts contain a wealth of information in a two-dimensional space, depicting price, volume, and moving averages, which include relational attributes that are challenging to discern using one-dimensional time series methods. In this study, we investigate return predictability in the Japanese stock market, a unique setting where the common momentum effect remains unobservable. We employ a statistical learning approach to uncover the predictive patterns underlying the data, using a Convolutional Neural Network (CNN) designed to automatically extract a large number of features from chart images. Our findings suggest that the features extracted from past stock charts possess predictive power for subsequent returns, particularly in larger, more liquid stocks. This result reveals the distinctive characteristics of return predictability in the Japanese stock market, highlighting that factors other than the common momentum effect play a significant role. It suggests that two-dimensional historical data may uncover valuable information about the future, offering insights into the unique price behavior observed in this market. The implications of our findings extend to the development of sophisticated trading strategies and the reevaluation of market inefficiency in different contexts.
#11 – Stock Return Reversal within Industries
#13 – Short Term Reversal Effect in Stocks
#115 – Short-Term Residual Reversal
#124 – Industry Momentum Combined with Reversal
#156 – Reversal Combined with Volatility Effect in Stocks
Blitz, David and van der Grient, Bart and Honarvar, Iman: Reversing the Trend of Short-Term Reversal
https://ssrn.com/abstract=4575689
Abstract:
The classic short-term reversal effect has steadily weakened over time, to the point of now having vanished entirely in most regions. However, the strategy can be revived by countering its tendency to go against short-term momentum in industry and factor returns. Enhanced short-term reversal strategies show a higher return with lower risk and have remained effective over time, culminating in more than double the risk-adjusted performance. Implementation challenges can best be overcome by combining short-term reversal with other short-term alpha signals. Various features of the short-term reversal strategy indicate that the premium stems from temporary imbalances between supply and demand. Investors in the strategy therefore effectively act as liquidity providers, contributing to a more efficient functioning of capital markets.
#468 – Dynamic Momentum Strategy
#171 – Market Timing Filter Applied to a Momentum and Other Factor Strategies
Ma, Siyuan: Arbitrage Asymmetry, Persistent Mispricing, and Momentum Prediction
https://ssrn.com/abstract=4138394
Abstract:
The Mispricing Gap (Mgap) between overpriced winners and underpriced losers is a strong predictor of stock momentum. This predictability remains even when accounting for various state-of-the-art common risk factors and existing predictors. Moreover, it is not limited to a specific time window used for calculating the formation period return and mispricing score. A one standard deviation increase in Mgap leads to a 1.02\% increase in momentum profit in the following month, indicating significant economic implications. This predictive power seems to stem from market efficiency determined by the dynamics of both sentiment investors and arbitrageurs.
#71 – Short Term Reversal with Futures
#107 – Short Term Reversal with ETFs
Micaletti, Raymond: A Comparison of Short-Term Mean-Reversion Indicators for Global Equities
https://ssrn.com/abstract=4339128
Abstract:
We examine an array of short-term mean-reversion indicators for global equities. The indicators encompass the most widely known price oscillators from the field of technical analysis along with several modified versions first developed by the author in the 2009- 2010 time frame. Constructing simple trading strategies from a wide range of indicator parameters, triggering thresholds, and holding periods, we find the modified oscillators tend to dominate the performance rankings on both the long and short sides of the market. Consequently, this study may serve as a point of reference for day traders, swing traders, or even asset managers looking to better time their rebalances.
#18 – Liquidity Effect in Stocks
Feng, LinJun and Li, Ya and Xu, Jing: Picking a Thorny Rose: Optimal Trading with Spread-Based Return Predictability
https://ssrn.com/abstract=4163240
Abstract:
Small stocks’ time-varying spreads predict future return gap between small and large stocks. To optimally exploit such predictability, the investor captures current risk premium by purchasing at large spreads with substantially reduced turnover; uses an aim-in-front-of-the-target approach to trade-off between future risk premium and current transaction costs; and meets hedging demand at low costs. Strong interaction between transaction costs and return predictability leads to large losses from myopic trading. Greater variability of the spread is advantageous for investors who trade optimally but detrimental for investors who trade myopically. The spread-based return predictability significantly increases the investment value of small stocks.
#616 – Output Gap Predicts FX Returns
Sakemoto, Ryuta: Risk Price Decomposition and the Output Gap
https://ssrn.com/abstract=4267778
Abstract:
We employ a time-varying risk price model that allows us to track the change in risk prices. We find that the output gap generates the time-varying market and momentum risk prices, but the exposures to the output gap have the opposite signs. In contrast, we do not observe that the output gap is linked to time variations of value and investment risk prices. We also uncover that the output gaps strongly impact the market risk prices for European and Japanese portfolios, while there are weak relationships between the momentum risk prices and the output gaps.
#628 – Social Media Sentiment Factor
Lee, Kang-Pyo and Song, Suyong: Informational Content of CEO Tweets and Stock Market Predictability
https://ssrn.com/abstract=4228651
Abstract:
This paper shows that CEO tweets contain informational content on the U.S. stock markets and provide investors with value-relevant information on predicting the stock price movement. We create a large, unique sample of CEO users on Twitter, extract hashtags and sentiments that can be used as features for prediction from large, unstructured tweet text, and construct hashtag and sentiment time series data. To prove the stock market predictability of CEO tweets using machine learning, we predict three numeric stock market indicators as a regression problem and the direction of stock prices as a classification problem. Findings confirm that the select list of hashtags and sentiments have predictive power on the stock return, trading volume, volatility, and stock price direction. We also find that the predictive power of CEO sentiments still stands after controlling for well-known macroeconomic and financial variables.
And several interesting free blog posts have been published during last 2 weeks:
Are Commodities a Good Investment? It Depends on the Country
In recent years, the diversification potential of commodities has come under scrutiny. While the majority of studies examining the role of commodities in a portfolio typically focus on U.S. investors or those dealing primarily with U.S. dollar-denominated assets, Dequiedt et al. (2023) offer a unique perspective by considering the viewpoint of domestic investors in a sample of 38 developed and emerging countries. The study explores the relationship between diversification benefits of commodities for local investors and country’s level of commodity risk exposure. Findings reveal that incorporating commodities tends to enhance the Sharpe ratio of the optimal domestic asset portfolios in most countries with low commodity dependence but doesn’t benefit highly commodity-dependent ones.
An Introduction to Machine Learning Research Related to Quantitative Trading
Following the recent release of the popular large language model ChatGPT, the topic of machine learning and AI seems to have skyrocketed in popularity. The concept of machine learning is, however, a much older one and has been the topic of various research and technology projects over the last decade and even longer. In this article, we would like to discuss what machine learning is, how it can be used in quantitative trading, and how has the popularity of ML strategies increased over the years.
Time-Varying Equity Premia with a High-VIX Threshold
What does one of the most popular and well-known metrics, VIX, tell us about future returns? Academic research (Bansal and Stivers, July 2023) shows that a common, intuitive 20/80 thumb rule can be applied as time-variation in the returns earned from equity-market exposure can be explained well by a simple 2-term risk-return specification, which predicts (1) much higher returns 20% of the time following after VIX exceeds a high threshold at around its 80th percentile and (2) lower excess returns following a high market sentiment. They argue that VIX and market sentiment tend to measure complementary aspects of risk: the level of risk (VIX) and the price of risk or risk appetite (sentiment), and that, thus, both terms should be accounted for when evaluating time variation in the equity market’s risk premium.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
263 – Economic Momentum in Currencies
911 – Multi Risk Premia Strategy
915 – On-Chain Cashflows and the Cross-Section of Cryptocurrency Returns
917 – Low-Risk Anomaly in India
918 – Seasonality in Equity Long-Short Factor Strategies
