New strategies:
#938 – Daily Momentum in Chinese Equities
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 2005-2019
Indicative performance: 57.96%
Estimated volatility: 31.03%
Source paper:
Gao, Zhenyu and Jiang, Wenxi and Xiong, Wei: Daily Momentum and New Investors in an Emerging Stock Market
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4527729
Abstract:
The absence of medium-term price momentum in the Chinese stock market, despite its dominance by retail investors prone to cognitive biases, is a well-known puzzle. Our study finds that daily returns, instead of monthly returns, display price momentum and attributes it to the trading behaviors of new investors using account-level transaction data. The results highlight the heterogeneity among retail investors and the significant impact of new investors, whose presence is particularly relevant for emerging stock markets. We also show that daily price momentum is present in several other emerging markets but less prevalent in developed markets.
#939 – Monthly Reversal in Chinese Equities
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 2005-2019
Indicative performance: 15.53%
Estimated volatility: 25.78%
Source paper:
Gao, Zhenyu and Jiang, Wenxi and Xiong, Wei: Daily Momentum and New Investors in an Emerging Stock Market
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4527729
Abstract:
The absence of medium-term price momentum in the Chinese stock market, despite its dominance by retail investors prone to cognitive biases, is a well-known puzzle. Our study finds that daily returns, instead of monthly returns, display price momentum and attributes it to the trading behaviors of new investors using account-level transaction data. The results highlight the heterogeneity among retail investors and the significant impact of new investors, whose presence is particularly relevant for emerging stock markets. We also show that daily price momentum is present in several other emerging markets but less prevalent in developed markets.
#940 – Multireference Alignment for Lead-Lag Detection in Stocks
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 2000-2020
Indicative performance: 9.83%
Estimated volatility: 10.92%
Source paper:
Shi, D., Cucuringu, M. and Calliess, J.-P.: Multireference Alignment for Lead-Lag Detection in Multivariate Time Series and Equity Trading
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4560780
Abstract:
We introduce a methodology based on Multireference Alignment (MRA) for lead-lag detection in multivariate time series, and demonstrate its applicability in developing trading strategies. Specifically designed for low signal-to-noise ratio (SNR) scenarios, our approach estimates denoised latent signals from a set of time series. We also investigate the impact of clustering the time series on the recovery of latent signals. We demonstrate that our lead-lag detection module outperforms commonly employed cross-correlation-based methods. Furthermore, we devise a cross-sectional trading strategy that capitalizes on the lead-lag relationships uncovered by our approach and attains significant economic benefits. Promising backtesting results on daily equity returns illustrate the potential of our method in quantitative finance and suggest avenues for future research.
#941 – Intraday Stock Market Predictability with Machine Learning
Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 2005-2016
Indicative performance: 10.4%
Estimated volatility: 10%
Source paper:
Liu, F. and Stentoft, L.: Intraday Stock Predictability Everywhere
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4496917
Abstract:
With approximately 900 million observations we conduct, to our knowledge, the largest study ever of intraday stock return predictability using machine learning techniques finding consistent out-of-sample predictability across market, sector, and individual stock returns at various time horizons. While linear models have the strongest statistical predictive power, nonlinear models economically dominate them and machine learning intraday long-short portfolios based on their forecasts attain Sharpe ratios of 4 after transaction costs. Predictability is short-lived, highest in the middle of the day, and more pronounced for less liquid firms, which indicates that slow-moving capital is an economic source of mispricing.
#942 – MACD-V: Volatility Normalised Momentum
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: CDFs, ETFs, futures
Complexity: Moderately complex strategy
Backtest period: 1991-2021
Indicative performance: 13.68%
Estimated volatility: –
Source paper:
Spiroglou, Alex: MACD-V: Volatility Normalised Momentum
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4099617
Abstract:
The paper will focus on the study of momentum, using a very popular technical analysis indicator, the Moving Average Convergence Divergence (MACD), created by one of the most respected analysts of our time – Gerald Appel. This paper is comprised of 6 parts. 1. In the first section we will examine why this topic matters to you; 2. Then we will focus on the MACD itself. We will do a brief description of its construction, the most elementary ways to use it and then a review of the five limitations it has. This is a section that is familiar territory to all technicians; 3. In the third section, we will show a widely known suggestion to deal with these limitations, that does improve one, but does not solve all of them; 4. In the fourth section we will present our own solution, which remedies the shortcomings, while creating unique advantages (edges) that would not be possible to obtain via the classic MACD; 5. Subsequently we will create another novel indicator (MACD-VH); 6. In the last section, we will use our framework to improve existing tools in TA literature and explore new techniques.
#943 – Mercury Retrograde Astrology Trading Strategy in Chinese Market
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: CDFs, ETFs, futures
Complexity: Simple strategy
Backtest period: 2015-2021
Indicative performance: 22.12%
Estimated volatility: 40.28%
Source paper:
Kou, Shubo and Ma, Xiyuan: Mercury, Mood, and Mispricing: A Natural Experiment in the Chinese Stock Market
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4593107
Abstract:
This paper examines the effects of superstitious psychology on investors’ decision making in the contex tof Mercury retrograde, a special astronomical phenomenon meaning “everything going wrong”. Using natural experiments in the Chinese stock market, we find a significant decline in stock prices, approximately -3.14% in the vicinity of Mercury retrogrades, with a subsequent reversal following these periods. The Mercury effect is robust after considering seasonality, the calendar effect, and well-known firm-level characteristics. Our mechanism tests are consistent with model-implied conjectures that stocks covered by higher investor attention are more influenced by superstitious psychology in the extensive and intensive channels. A superstitious hedge strategy motivated by our findings can generate an average annualized market-adjusted return of 8.73%.
New research papers related to existing strategies:
#3 – Sector Momentum – Rotational System
Rothe, John: Dynamic Sector Rotation
https://ssrn.com/abstract=4573209
Abstract:
The investment world is characterized by its multifaceted and dynamic nature, which continually presents challenges and opportunities for academic exploration.
This whitepaper presents a rigorous examination of a novel investment approach based on momentum investing using a risk-managed methodology based on volatility.
The academic research of momentum, relative strength, and risk-managed volatility are analyzed and combined to create a dynamic sector rotation mode that is designed to outperform the S&P 500 momentum index while exposing the portfolio to lower drawdowns.
#498 – Value in Anomalies
Zhang, Shaojun: Factor Value
https://ssrn.com/abstract=4588171
Abstract:
This paper finds that the value and long-term reversal anomalies summarize time series predictability in factors using value and reversal spreads, representing the difference in value-weighted book-to-market ratios and minus past long-term stock returns between long and short legs of factors. Factors only yield positive and significant returns when the value or reversal spread exceeds the historical median. Derived time-series strategies, namely factor value and reversal, outperform and explain various value-style anomalies. Cross-sectional value and reversal strategies long other factors during high spreads and short them otherwise. Factor predictability is consistent with asymmetric limits of arbitrage and persistent overpricing correction.
#931 – Forecasting Crude Oil Prices
Gifuni, Luigi: Do High Frequency Text Data Help Forecast Crude Oil Prices? MF-VAR vs. MIDAS
https://ssrn.com/abstract=4574350
Abstract:
This paper investigates the predictability of monthly real oil prices when daily and weekly text data are combined with oil market fundamentals. Text data are retrieved from 140,096 full oil-related articles featured in The Financial Times, Thomson Reuters and The Independent from 1982M1 to 2021M12. I show that models containing high-frequency financial and commodity variables do not yield significant improvements on the no-change forecast. In contrast, when text data are used along with commodity variables and oil market fundamentals, the preferred models reduce the MSPE by 18%. However, despite this marginal improvement, gains are low. Indeed, the corresponding models with variables observed at homogeneous frequency, generate similar out-of-sample forecasts in terms of accuracy. I thus conclude that variables sampled at different frequencies do not significantly improve the predictability of monthly real oil prices. This is true for point and density forecasts.
#132 – Dynamic Commodity Timing Strategy
Jakubowski, Paweł and Ślepaczuk, Robert and Windorbski, Franciszek: Ensembling Arimax Model in Algorithmic Investment Strategies on Commodities Market
https://ssrn.com/abstract=4577441
Abstract:
This paper presents the results of investment strategies based on predictions from an ARIMA with exogenous variables (ARIMAX/ARIMAX-Garch) model, using the prices of selected commodities and companies from the Dow Jones Industrial Average index as explanatory variables. The explained variables used for the study are four Invesco ETF funds (DBE, DBA, DBP, DBB) corresponding to baskets of energy, agricultural, precious metal, and industrial metal commodities. The models are optimized using the Walk-Forward technique, and the selection of exogenous variables is based on the Granger causality test. By analyzing the results in the form of equity lines and performance metrics, we conclude that ARIMAX/ARIMAX-Garch models are not useful tools for making buy or sell decisions for the selected commodity baskets. Out of the 80 estimated models, 44 outperform the Buy & Hold strategy however, none achieved statistically significant results. Combining individual models into an investment portfolio reduced the risk without significantly reducing the profit, which enabled us to beat the benchmark strategy even more consistently. We also observe that using returns of commodities listed on stock exchanges is more effective than using stocks returns. Sensitivity analysis showes instability in results with changes in the length of the training and testing windows. The highest annual return rate of 15.37% from 02.01.2008 to 01.12.2022 was characterized by an ARIMAX model with one commodity exogenous variable.
#628 – Social Media Sentiment Factor
Zhang, Hai and Zhang, Wenjia: Video Sentiment and Stock Returns
https://ssrn.com/abstract=4569776
Abstract:
This paper introduces a novel monthly video sentiment index (VNEG) by utilizing machine learning to extract sentiment from the facial expressions of millions of investors in videos. This index provides a real-time and continuous measure of sentiment. Our analysis reveals that VNEG is a robust and inversely correlated index for explaining and predicting stock returns, whether in-sample or in out-of-sample forecasting scenarios. In comparison to previous sentiment indices and commonly examined macroeconomic variables, VNEG demonstrates superior performance. Furthermore, our study highlights the notable effectiveness of VNEG in forecasting portfolios, particularly those categorized by Consumer (Cnsmr) and High Technology (HiTec) industry sectors, as well as in contexts involving large-cap stocks and high-momentum investments.
#869 – Market Timing Corporate Bonds with Machine learning – Random Forests
#872 – Machine Learning – Random Forests Predicts Cross Section of Corporate Bonds
Duraj, Jetlir and Giesecke, Oliver: Deep Learning for Corporate Bonds
https://ssrn.com/abstract=4527372
Abstract:
We estimate an asset pricing model for the U.S. corporate bonds market using bond portfolios, as well as a large longitudinal dataset of individual bonds that we augment with fundamental characteristics of the issuer. We further enrich the information set with a large set of macroeconomic time series. We estimate diverse model architectures with two approaches: (1) minimizing the mispricing loss, and (2) maximizing the Sharpe ratio. We find that, contrary to the equivalence of these two approaches in the sense of financial theory, maximizing the Sharpe ratio performs better for individual bonds, whereas the difference is smaller for bond portfolios. The out-of-sample annual SDF portfolio Sharpe ratios are in the range of .59 to 1.00, and show statistically significant excess returns (alphas) relative to conventional risk factors. Our results are robust to the exclusion of financials and REITs.
And several interesting free blog posts that have been published during the last 2 weeks:
Decreasing Returns of Machine Learning Strategies
Traditional asset pricing literature has yielded numerous anomaly variables for predicting stock returns, but real-world outcomes often disappoint. Many of these predictors work best in small-cap stocks, and their profitability tends to decline over time, particularly in the United States. As market efficiency improves, exploiting these anomalies becomes harder. The fusion of machine learning with finance research offers promise. Machine learning can handle extensive data, identify reliable predictors, and model complex relationships. The question is whether these promises can deliver more accurate stock return predictions…
Less is More? Reducing Biases and Overfitting in Machine Learning Return Predictions
Machine learning models have been successfully employed to cross-sectionally predict stock returns using lagged stock characteristics as inputs. The analyzed paper challenges the conventional wisdom that more training data leads to superior machine learning models for stock return predictions. Instead, the research demonstrates that training market capitalization group-specific machine learning models can yield superior results for stock-level return predictions and long-short portfolios. The paper showcases the impact of model regularization and highlights the importance of careful model design choices.
Military Expenditures and Performance of the Stock Markets
“Si vis pacem, para bellum”, is an old Roman proverb translated to English as “If you want peace, prepare for war”, and it is the main idea behind the military policy of a lot of modern national states. In the current globally interconnected world, waging a real “hot war” has very often really negative trade and business repercussions (as the Russian Federation realized in 2022). Still, even though wars among developed nations are luckily not as popular as they used to be, modern states heavily invest in their own defense. Nobody wants to be caught military unprepared in case of a local or global geopolitical crisis. A strong military should bring a safe environment to do business, and trade should flourish uninterrupted. But are all those national military expenditures financially rewarded? Do stock markets of countries with a strong military outperform their peers? That’s the question we have decided to answer in the following analysis.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
933 – The Effect of Market Returns on Factor Returns
938 – Daily Momentum in Chinese Equities
939 – Monthly Reversal in Chinese Equities
