{"id":35766,"date":"2024-09-09T13:54:04","date_gmt":"2024-09-09T11:54:04","guid":{"rendered":"https:\/\/quantpedia.com\/?p=35766"},"modified":"2024-09-29T12:07:22","modified_gmt":"2024-09-29T10:07:22","slug":"quantpedia-premium-update-september-5th","status":"publish","type":"post","link":"https:\/\/vvv.quantpedia.com\/es\/quantpedia-premium-update-september-5th\/","title":{"rendered":"Quantpedia Premium Update – September 5th"},"content":{"rendered":"

New Strategies: <\/h4>\n\n\n\n

#1042 – Turnaround Tuesday in High-Yield Bond Market<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Daily
Markets traded:<\/strong> bonds
Instruments used for trading:<\/strong> ETFs
Complexity:<\/strong> Simple strategy
Backtest period:<\/strong> 2007-2024
Indicative performance:<\/strong> 2.63%
Estimated volatility:<\/strong> 2.34%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Vojtko, Radovan and Dujava, Cyril: Overnight Reversal Effects in the High-Yield Market<\/strong>
https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4940369<\/a>
Abstract:
High-yield bond ETFs represent a unique financial vehicle: they are highly liquid instruments that hold inherently illiquid securities, creating a fertile ground for predictable market behaviors. Our latest research uncovers an intriguing anomaly within these ETFs, similar to those observed in the stock market: overnight returns are systematically higher than intraday returns. This overnight anomaly in high-yield bonds is not only prevalent but also exhibits a distinct seasonal pattern, primarily from Monday\u2019s close to Tuesday\u2019s open and from Tuesday\u2019s close to Wednesday\u2019s open. Additionally, this anomaly displays a reversal characteristic, where overnight performance is typically more robust following a negative close-to-close performance in the preceding period. These findings reveal potential opportunities for trading strategies that leverage these consistent overnight return patterns, offering new insights into high-yield bond trading dynamics.<\/p>\n\n\n\n

#1043 – Lunch Effect in the U.S. Stock Market Indices<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Intradays
Markets traded:<\/strong> equities
Instruments used for trading:<\/strong> CFDs, ETFs, futures
Complexity:<\/strong> Simple strategy
Backtest period:<\/strong> 2010-2024
Indicative performance:<\/strong> 5.17%
Estimated volatility:<\/strong> 8.03%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Vojtko, Radovan and Dujava, Cyril: Lunch Effect in the U.S. Stock Market Indices<\/strong>
https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4934614<\/a>
Abstract:
The Lunch Effect is a well-known anomaly in the U.S. stock market, characterized by increased stock prices following the lunch break. This article explores the Lunch Effect, examining evidence that supports and contradicts its existence. Proponents of the Lunch Effect suggest that investor behavior, specifically a shift towards algorithmic trading during lunch hours, contributes to the price increase.<\/p>\n\n\n\n

#1044 – ARIMA Gold-Bitcoin Optimizer<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Daily
Markets traded:<\/strong> commodities, cryptos
Instruments used for trading:<\/strong> CFDs, cryptos, ETFs, futures
Complexity:<\/strong> Simple strategy
Backtest period:<\/strong> 2016-2022
Indicative performance:<\/strong> 24.49%
Estimated volatility:<\/strong> 21.57%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Benchen Liu: Research on Optimal Investment Strategy Combination Based on ARIMA Model and mean-variance analysis \u2014 Taking Gold and Bitcoin assets as examples<\/strong>
https:\/\/drpress.org\/ojs\/index.php\/HBEM\/article\/view\/8111<\/a>
Abstract:
Gold and Bitcoin are popular trading products in today\u2019s trading market. In order to build a trading portfolio that maximizes returns, the prices of two trading products need to be predicted first. This article utilizes ARIMA to deal with the non-stationarity and predict the future prices of gold and bitcoin. In this article, the choice of parameters is ARIMA (4, 1, 4) for both bitcoin and gold. To find the best timing to sell and buy the two assets, the article first rate them with well-designed rating system by three important factors: Changes in value, Moving averages, and Bias. Then based on these factors, the model further linearly composes the indicator for risk and trend. By utilizing the information, the model gets with the main factor to make trading decisions.<\/p>\n\n\n\n

#1045 – LSTM-ARIMA as a Hybrid Approach in Algorithmic Investment Strategies<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Daily
Markets traded:<\/strong> equities
Instruments used for trading:<\/strong> CFDs, ETFs, futures
Complexity:<\/strong> Very complex strategy
Backtest period:<\/strong> 2005-2023
Indicative performance:<\/strong> 11.82%
Estimated volatility:<\/strong> 11.96%<\/p>\n\n\n\n

Source paper<\/strong>:<\/p>\n\n\n\n

Kashifa, Kamil and \u015alepaczuk, Robert: LSTM-ARIMA as a Hybrid Approach in Algorithmic Investment Strategies
<\/strong>https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4877100<\/a>
Abstract:
This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA. This unique algorithm uses LSTM to produce final predictions but boost results of this RNN by adding the residuals obtained from ARIMA predictions among other inputs. The algorithm is tested across three equity indices (S&P 500, FTSE 100, and CAC 40) using daily frequency data spanning from January, 2000 to August, 2023. The architecture of testing is based on the walk-forward procedure which is applied for hyperparameter tunning phase that uses using Random Search and backtesting the algorithms. The selection of the optimal model is determined based on adequately selected performance metrics combining focused on risk-adjusted return measures. We considered two strategies for each algorithm: Long-Only and Long-Short in order to present situation of two various groups of investors with different investment policy restrictions. For each strategy and equity index, we compute the performance metrics and visualize the equity curve to identify the best strategy with the highest modified information ratio (IR**). The findings conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms across all the equity indices what confirms strong potential behind hybrid ML-TS (machine learning – time series) models in searching for the optimal algorithmic investment strategies.<\/p>\n\n\n\n

#1046 – Dynamic Asset Allocation with Asset-Specific Regime Forecasts<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Daily
Markets traded:<\/strong> bonds, commodities, equities, REITs
Instruments used for trading:<\/strong> ETFs
Complexity:<\/strong> Very complex strategy
Backtest period:<\/strong> 1991-2023
Indicative performance:<\/strong> 8.9%
Estimated volatility:<\/strong> 8.7%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Shu, Yizhan and Yu, Chenyu and Mulvey, John M.: Dynamic Asset Allocation with Asset-Speci\ufb01c Regime Forecasts
<\/strong>https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4864358<\/a>
Abstract:
This article introduces a novel hybrid regime identi\ufb01cation-forecasting framework designed to enhance multi-asset portfolio construction by integrating asset-speci\ufb01c regime forecasts. Unlike traditional approaches that focus on broad economic regimes a\ufb00ecting the entire asset universe, our framework leverages both unsupervised and supervised learning to generate tailored regime forecasts for individual assets. Initially, we use the statistical jump model, a robust unsupervised regime identi\ufb01cation model, to derive regime labels for historical periods, classifying them into bullish or bearish states based on features extracted from an asset return series. Following this, a supervised gradient-boosted decision tree classi\ufb01er is trained to predict these regimes using a combination of asset-speci\ufb01c return features and cross-asset macro-features. We apply this framework individually to each asset in our universe. Subsequently, return and risk forecasts which incorporate these regime predictions are input into Markowitz mean-variance optimization to determine optimal asset allocation weights. We demonstrate the e\ufb03cacy of our approach through an empirical study on a multi-asset portfolio comprising twelve risky assets, including global equity, bond, real estate, and commodity indexes spanning from 1991 to 2023. The results consistently show outperformance across various portfolio models, including minimum-variance, mean-variance, and naive-diversi\ufb01ed portfolios, highlighting the advantages of integrating asset-speci\ufb01c regime forecasts into dynamic asset allocation.<\/p>\n\n\n\n

#1047 – Idiosyncratic Earnings Hedge Strategy<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Yearly
Markets traded:<\/strong> equities
Instruments used for trading:<\/strong> stocks
Complexity:<\/strong> Complex strategy
Backtest period:<\/strong> 1975-2017
Indicative performance:<\/strong> 15.3%
Estimated volatility:<\/strong> 12.64%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Han, Miaodi and Jackson, Andrew B. and Monroe, Gary S.: Idiosyncratic Earnings and Market Efficiency
<\/strong>https:\/\/ssrn.com\/abstract=4890319<\/a>
Abstract:
This study investigates the influence of market, industry, and firm-idiosyncratic components of earnings on stock pricing decisions and whether a trading strategy based on the idiosyncratic component is able to generate significant hedge portfolio abnormal returns. Our findings reveal that investors underestimate the importance of idiosyncratic earnings. Based on this result, we develop a trading strategy based on idiosyncratic earnings that is able to generate significant hedge portfolio returns. We argue that the idiosyncratic component of earnings represents the outcome of a firm\u2019s strategy and therefore reflects a fundamental aspect of firm performance. Incorporating idiosyncratic earnings into our analysis is consistent with the approach in financial statement analysis. Our results shed light on stock return predictability and enhance financial economics discourse, underscoring the intricate relationship between earnings components and investor behavior, offering valuable insights into market inefficiencies.<\/p>\n\n\n\n

#1048 – News Sentiment and Commodity Futures Investing<\/a><\/strong><\/h5>\n\n\n\n

Period of rebalancing:<\/strong> Weekly
Markets traded:<\/strong> commodities
Instruments used for trading:<\/strong> CFDs, futures
Complexity:<\/strong> Complex strategy
Backtest period:<\/strong> 1998-2021
Indicative performance:<\/strong> 10.25%
Estimated volatility:<\/strong> 18.39%<\/p>\n\n\n\n

Source paper:<\/strong><\/p>\n\n\n\n

Vu, Thanh and Chi, Yeguang and El-Jahel, Lina:  News Sentiment and Commodity Futures Investing<\/strong>
https:\/\/ssrn.com\/abstract=4870724<\/a>
Abstract:
We investigate the role of media news sentiment in commodity futures investing. The weekly rebalanced long-short portfolio sorted by news sentiment generates a significant average annualized return of around 10%. The time-series spanning test reveals that the abnormal return of the long-short portfolio sorted by news sentiment still remains above 7% and is statistically significant after controlling for various benchmark factors. The premium of the news sentiment factor is also significantly priced at above 8% in the cross-section of commodity futures returns. Furthermore, we show that incorporating the news-sentiment factor into commodity futures investment portfolio leads to meaningful performance enhancement.<\/p>\n\n\n\n

New research papers related to existing strategies:<\/h4>\n\n\n\n

#383 – Moving Average Strategies for Cryptocurrencies<\/a><\/strong><\/p>\n\n\n\n

Le, Trinh and Ruthbah, Ummul: Trend-following Strategies for Crypto Investors<\/strong>
https:\/\/ssrn.com\/abstract=4551518<\/a>
Abstract:
In the rapidly evolving landscape of financial markets, the emergence of cryptocurrencies as a distinct asset class has opened up new avenues for investors. However, investors need to establish a comprehensive investment strategy and implement risk-management measures before entering this space to mitigate the potential for market crashes. This paper develops and evaluates trendfollowing investment strategies in the context of cryptocurrencies. Secondly, it investigates the commonly held belief of a correlation between the movements of the Nasdaq 100 index and cryptocurrencies, which has significant implications for investment strategy development. We find that trend following strategies perform well over the researched period. Moreover, the effect of transaction costs is very substantial on portfolio performances. We also find no correlation between Nasdaq 100 index and our investigated cryptos, inconsistent with common perception in the market.<\/p>\n\n\n\n

#696 – Fair Spread Value Factor in Corporate Bonds<\/a><\/strong><\/p>\n\n\n\n

Wu, Liuren and Zaman, Hashim: Finding value in the U.S. corporate bond market<\/strong>
https:\/\/ssrn.com\/abstract=4852548<\/a>
Abstract:
This paper identifies value-investing opportunities in the U.S. corporate bond market through the joint construction of a bond valuation model and a return factor model. The valuation model explains the cross-sectional corporate bond yield variation with a flexible functional form in bond risk characteristics including bond duration, credit rating, historical yield change volatility, bond liquidity, and the optionality-induced yield spread adjustment for callable bonds. The return factor model embeds the residual from the valuation model as a mispricing factor while capturing the stronger co-movements between bonds from the same industry, similar rating classes, and similar duration segments, and accounting for differential pricing of bond return risk, liquidity cost, and the optionality exposure. Historical analysis over the past two decades shows that the valuation model can explain the cross-sectional bond yield variation very well, and the value-investing portfolio constructed from the return factor model generates highly positive average excess returns with low risk.<\/p>\n\n\n\n

#1037 – Leading Stocks and the Stock Market Expected Returns<\/a><\/strong><\/p>\n\n\n\n

Hulley, Hardy and Liu, Leo and Phua, Jing Wen Kenny: Investor Search and Asset Prices<\/strong>
https:\/\/ssrn.com\/abstract=4793323<\/a>
Abstract:
Firms can have fundamental similarities and relatedness, such as operating in the same geographic area and industries, being customers or suppliers, etc. Understanding these connections has implications for cross-asset return predictability because information can flow through these linkages sluggishly. We introduce a novel peer momentum by linking firms that are co-searched by investors on the SEC EDGAR server. A trading strategy based on this peer momentum generates an annualized return alpha of 17%, and it remains robust when controlling for other peer momentum, known asset pricing anomalies, and firm characteristics. Moreover, it outperforms the shared-analyst peer momentum identified by Ali and Hirshleifer (2020).
<\/p>\n\n\n\n

#1048 – News Sentiment and Commodity Futures Investing<\/a><\/strong><\/p>\n\n\n\n

Chi, Yeguang and El-Jahel, Lina and Vu, Thanh: Media Emotion Intensity and Commodity Futures Pricing<\/strong>
https:\/\/ssrn.com\/abstract=4850227<\/a>
Abstract:
This study investigates the impact of media emotion intensity on commodities futures returns. Emotion intensity measures the proportion of emotional content relative to factual content in media news. The media emotion intensity factor exhibits an annual premium of 14.40% and is more pronounced for commodities with low media coverage, high momentum, high basis-momentum, high hedging pressure, and backwardation. Emotion intensity significantly predicts the trading tendencies of both commercial and non-commercial traders and the cross-section of commodity futures returns at both portfolio and individual levels. Further, other commonly considered risk sources cannot subsume the predictability of the media emotion intensity factor.<\/p>\n\n\n\n

And several interesting free blog posts that have been published during the last 2 weeks:<\/h4>\n\n\n\n
Overnight Reversal Effects in the High-Yield Market<\/strong><\/a><\/h5>\n\n\n\n

High-yield bond ETFs represent a unique financial vehicle: they are highly liquid instruments that hold inherently illiquid securities, creating a fertile ground for predictable market behaviors. Our latest research uncovers an intriguing anomaly within these ETFs, similar to those observed in the stock market: overnight returns are systematically higher than intraday returns. This overnight anomaly in high-yield bonds is not only prevalent but also exhibits a distinct seasonal pattern, primarily from Monday\u2019s close to Tuesday\u2019s open and from Tuesday\u2019s close to Wednesday\u2019s open. Additionally, this anomaly displays a reversal characteristic, where overnight performance is typically more robust following a negative close-to-close performance in the preceding period. These findings reveal potential opportunities for trading strategies that leverage these consistent overnight return patterns, offering new insights into high-yield bond trading dynamics.<\/p>\n\n\n\n

Insights from the Geopolitical Sentiment Index made with Google Trends<\/strong><\/a><\/h5>\n\n\n\n

Throughout history, geopolitical stress and tension has been ever-present. From ancient civilizations to today\u2019s world, global dynamics have been largely shaped by wars, terrorism, and trade disputes. Financial markets, as always, have keenly observed and been significantly influenced as a result.<\/p>\n\n\n\n

Our article delves into understanding this relation between geopolitical stress and financial markets, particularly the equity market. To briefly explain our approach, we seek to quantify geopolitical stress through an observable Geopolitical Stress Index (GSI). Using this index, we can explore the relation between geopolitical sentiment, good and bad, and instruments available on financial market. Lastly, we seek to see if geopolitical sentiment is something that can be used to impact trading decisions and develop profitable trading strategies.<\/p>\n\n\n\n

Plus, the following trading strategies have been backtested in QuantConnect<\/a> in the previous two weeks:<\/h4>\n\n\n\n

987 – Economic Trend in Futures<\/a><\/strong>
1023 – Front-Running the Goldman Roll<\/a><\/strong>
1042 – Turnaround Tuesday in High-Yield Bond Market<\/a><\/strong><\/p>","protected":false},"excerpt":{"rendered":"

Seven new strategies have been added. Three new related research papers have been included into existing strategy reviews and two short free blog posts<\/strong><\/a> have been published during last few weeks. Plus, three trading strategies have been backtested in QuantConnect<\/strong><\/a> in the previous two weeks.<\/p>","protected":false},"author":25721,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-35766","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/posts\/35766","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/users\/25721"}],"replies":[{"embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/comments?post=35766"}],"version-history":[{"count":0,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/posts\/35766\/revisions"}],"wp:attachment":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/media?parent=35766"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/categories?post=35766"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/tags?post=35766"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}