Quantpedia Premium Update – August 9th

New Strategies:

#1031 – Seasonal Electricity Futures Strategy

Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures
Complexity: Simple strategy
Backtest period: 2006-2021
Indicative performance: 5.3%
Estimated volatility: 11.8%

Source paper:

Størdal; Ståle; Ewald; Christian-Oliver; Lien; Gudbrand; Haugom; Erik: Trading time seasonality in electricity futures
https://doi.org/10.1016/j.jcomm.2022.100291
Abstract:
Trading time seasonality reflects the seasonal behavior of futures prices with the same time of maturity. Hence, it differs from classical seasonality, which reflects seasonal behavior induced by the spot price observed for varying maturities. This type of seasonality is linked to the pricing kernel which in turn accounts for seasonal changes in preferences of agents and tied to risk aversion and thus the demand for hedging. In the present study we empirically examine trading time seasonality in yearly Nordic and German electricity futures contracts. Visual inspection of both average monthly futures prices and the futures backward curves provides strong indications of futures prices systematically varying over the trading year. On average both Nordic and German futures prices are lowest in first quarter and highest in third quarter trading months. This is confirmed by statistical tests of stochastic dominance. Exploiting this insight in a simple trading strategy induces positive and significant alphas in the sense of the capital asset pricing model. We relate the findings to potential seasonal risk preferences and hedging pressure in the electricity futures market.

#1032 – MACD Trend Following in Chinese Commodities

Period of rebalancing: Daily
Markets traded: commodities
Instruments used for trading: futures
Complexity: Complex strategy
Backtest period: 2012-2020
Indicative performance: 26.07%
Estimated volatility: 14.15%

Source paper:

Zhu; Haotian; Li; Yanxiao: The Implementation and Refinement Hedge Fund Strategy in Chinese Commodity Market: MACD Trend Following
https://www.ewadirect.com/proceedings/aemps/article/view/3096
Abstract:
This work aims to explore the performance of the MACD Trend Following Strategy within the context of the Chinese market. This paper organizes a universe to study this strategy methodically and applies this traditional hedge fund strategy to the universe. This work gets a generally positive result by running a backtest using historical data. To solve some difficulties, the work includes double Confirmation of MACD and other technical indicators and adjusting the holding period. The strategy has been successful in Chinese futures trading. In addition, additional considerations for the strategy and trading recommendations are discussed. This work enhances the comprehension and application of the strategy.

#1033 – Improving Option Writing Performance with Put-Call Ratios

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: options
Complexity: Simple strategy
Backtest period: 2007-2023
Indicative performance: 20.41%
Estimated volatility: 21.92%

Source paper:

Chien-Ling Lo, Wen-Rang Liu: Low Risk, High Return: Improving Option Writing Performance with Put-Call Ratios
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4889026
Abstract:
This study employs the put-call ratio (PCR) to enhance option writing performance. Unlike the conventional buy-write strategy, we fully invest in the market during high PCR periods and sell options to generate income only when the PCR is low, greatly reducing trade frequency. Utilizing index options in Taiwan, which stands out as one of the few global markets developing tradable products for covered call strategies, and where retail investors play a predominant role, our approach yields higher returns with lower risk compared to the market index and outperforms VIX-based conditional strategies. The findings remain robust across institutional investors’ positions, various PCR definitions, and alternative writing strategies such as put-write or covered combo.

#1034 – Maximizing Portfolio Predictability with Machine Learning

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1990-2020
Indicative performance: 15.6%
Estimated volatility: 15.23%

Source paper:

Pinelis, M., Ruppert, D.: Maximizing Portfolio Predictability with Machine Learning
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4622042
Abstract:
We construct the maximally predictable portfolio (MPP) of stocks using machine learning. Solving for the optimal constrained weights in the multi-asset MPP gives portfolios with a high monthly coefficient of determination, given the sample covariance matrix of predicted return errors from a machine learning model. Various models for the covariance matrix are tested. The MPPs of S&P 500 index constituents with estimated returns from Elastic Net, Random Forest, and Support Vector Regression models can outperform or underperform the index depending on the time period. Portfolios that take advantage of the high predictability of the MPP’s returns and employ a Kelly criterion style strategy consistently outperform the benchmark.

#1035 – Mixing Financial Stress with GPT-4 News Sentiment Analysis for Optimal Risk-On/Risk-Off Decisions

Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: CFDs, ETFs, futures
Complexity: Very complex strategy
Backtest period: 2005-2024
Indicative performance: 11%
Estimated volatility: 7.5%

Source paper:

Lefort, B., Benhamou, E., Ohana, J. J., Saltiel, D., Guez, B., Jacquot, T.: Mixing Financial Stress with GPT-4 News Sentiment Analysis for Optimal Risk-On/Risk-Off Decisions
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781752
Abstract:
This paper introduces a new risk-on risk-off strategy for the stock market, which combines a financial stress indicator with a sentiment analysis done by ChatGPT reading and interpreting Bloomberg daily market summaries. Forecasts of market stress derived from volatility and credit spreads are enhanced when combined with the financial news sentiment derived from GPT4. As a result, the strategy shows improved performance, evidenced by higher Sharpe ratio and reduced maximum drawdowns. The improved performance is consistent across the NASDAQ, the S&P 500 and the six major equity markets, indicating that the method generalises across equities markets.

#1036 – Forecasting Real Oil Returns Using a Deep Forest Ensemble Approach

Period of rebalancing: Daily
Markets traded: commodities
Instruments used for trading: CFDs, ETFs, futures
Complexity: Very complex strategy
Backtest period: 2005-2024
Indicative performance: 11%
Estimated volatility: 7.5%

Source paper:

Xu, X., Liu, W-H.:Forecasting Real Oil Returns Using a Deep Forest Ensemble Approach
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781192
Abstract:
We made an application of a cutting-edge machine learning method, the deep forest ensemble approach (DFEA, Zhou and Feng (2017, 2019)), to empirically predict crude oil prices. We used a large data set with 36 explanatory variables to compare the predictability of the DFEA with seven popular machine learning models and their mean combination method. The out-of-sample forecasting results showed that the DFEA statistically and economically outperforms all the competing models in terms of out-of-sample R square and success ratio. The DEFA also displayed sizable certainty equivalent return (CER) gains for a mean-variance investor in practice. Furthermore, we found that the predictive power of the DFEA mainly stems from technical indicators, especially momentum predictors. In terms of economic value, the DFEA can also deliver substantial average returns and Sharpe ratios from a market timing perspective. Our results survived in various robustness checks.

#1037 – Leading Stocks and the Stock Market Expected Returns

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: CFDs, ETFs, futures
Complexity: Very complex strategy
Backtest period: 1980-2019
Indicative performance: 4.11%
Estimated volatility: 6.51%

Source paper:

Chen, Z., Hao, X., Yu, H., Zhou, G.: Leading Stocks and the Stock Market Expected Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4768908
Abstract:
We identify leading stocks using machine learning and show that these leaders have closer link to the expected market returns than those from existing methods. We find that the negative leaders, which lead other stocks negatively, have a strong predictive power on the future stock market returns both in- and out-of-sample, whereas the positive leaders do not. The predictability generates significant economic value to a mean-variance investor in asset allocation. Economically, underreaction of the followers appears the driving force for the predictability. Our study provides the first empirical evidence that bridges the lead-lag literature to market predictability.

New research papers related to existing strategies:

#22 – Term Structure Effect in Commodities

Cooper, Ricky and Day, Theodore E. and Lewis, Craig M. and Molyboga, Marat: Commodity Futures and the Limits to Arbitrage
https://ssrn.com/abstract=4898331
Abstract:
This study examines the origin of term premiums in commodity futures prices, building on past research that identifies them as emerging from commodity futures becoming a distinct investment class. We analyze the effect of heightened financial activity on these premiums, considering arbitrage limitations. Utilizing futures trading data and Commitment of Traders Reports, we test predictions regarding the impact of increased financial involvement. Additionally, through a natural experiment comparing term premiums of wheat futures contracts, we show institutional investors significantly influence commodity futures term premiums, introducing distortions not fully eliminated by arbitrage, especially in distant expiration contracts.

#887 – Pairs Trading in Cryptocurrencies

Yang, Hongshen and Malik, Avinash: Optimal market-neutral multivariate pair trading on the cryptocurrency platform
https://www.semanticscholar.org/reader/e7fbc8ebbb1ab29581bb4146a2ce4b8251aaab7d
Abstract:
This research proposes a novel arbitrage approach in multivariate pair trading, termed the Optimal Trading Technique (OTT). We present a method for selectively forming a “bucket” of fiat currencies anchored to cryptocurrency for monitoring and exploiting trading opportunities simultaneously. To address quantitative conflicts from multiple trading signals, a novel bi-objective convex optimization formulation is designed to balance investor preferences between profitability and risk tolerance. This process includes tunable parameters such as volatility penalties and action thresholds. In experiments conducted in the cryptocurrency market from 2020 to 2022, which encompassed a vigorous bull-run followed by a bear-run, the OTT achieved an annualized profit of 15.49%. Further experiments in bull, bear, and full-cycle market conditions demonstrated that OTT consistently achieves stable profits across various market conditions. Additionally, OTT’s arbitrage operation offers a new trading perspective, requiring no external shorting and avoiding intermediate cryptocurrency holdings during the arbitrage period.

And several interesting free blog posts that have been published during the last 2 weeks:

Combining Discretionary and Algorithmic Trading

The area we want to explore today is an interesting intersection between quantitative and more technical approaches to trading that employ intuition and experience in strictly data-driven decision-making (completely omitting any fundamental analysis!). Can just years of screen time and trading experience improve the metrics and profitability of trading systems through discretionary trading actions and decisions?

The Expected Returns of Machine-Learning Strategies

Does the investment in sophisticated machine learning algorithm research and development pay off? It is an important question, especially in light of the increasing costs related to the R&D of such algorithms and the possibility of decreasing returns for some methods developed in the more distant past. A recent paper by Azevedo, Hoegner, and Velikov (2023) evaluates the expected returns of machine learning-based trading strategies by considering transaction costs, post-publication decay, and the current high liquidity environment. The obstacles are not low, but research suggests that despite high turnover rates, some machine learning strategies continue to yield positive net returns.

Outperforming Equal Weighting

Equal-weighted benchmark portfolios are sometimes overshadowed by the more popular market capitalization benchmarks but are still popular and often used in practice. One of the advantages of equal-weighted portfolios is that academic research shows that in the long term, they tend to outperform their market-cap-weighted peers, mainly due to positive loadings on well-known factor premiums like size and value. So, if equal weighting outperforms market-cap weighting (in the long term), what options do we have if we want to outperform equal weighting? A recent paper by Cirulli and Walker comes to our aid with an interesting proposal …