{"id":14964,"date":"2021-09-01T10:30:29","date_gmt":"2021-09-01T08:30:29","guid":{"rendered":"https:\/\/quantpedia.com\/?p=14964"},"modified":"2025-06-04T14:07:01","modified_gmt":"2025-06-04T12:07:01","slug":"quantpedia-premium-update-31th-august-2021","status":"publish","type":"post","link":"https:\/\/vvv.quantpedia.com\/es\/quantpedia-premium-update-31th-august-2021\/","title":{"rendered":"Quantpedia Premium Update \u2013 31th August 2021"},"content":{"rendered":"

New strategies:<\/strong><\/p>\n\n\n\n

#656 \u2013 Machine Learning for Extracting Pessimism from Newspaper Pictures and Text<\/a><\/strong><\/p>\n\n\n\n

Period of rebalancing:<\/strong> Daily
Markets traded: <\/strong>equities
Instruments used for trading:<\/strong> stocks
Complexity:<\/strong> Very complex strategy
Backtest period:<\/strong> 2008-2020
Indicative performance:<\/strong> 15.06%
Estimated volatility:<\/strong> 15.82%<\/p>\n\n\n\n

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

Obaid, Khaled and Pukthuanthong, Kuntara, A Picture is Worth a Thousand Words: Measuring Investor Sentiment by Combining Machine Learning and Photos from News
<\/strong>https:\/\/ssrn.com\/abstract=3841844
<\/a>Abstracto:
By applying machine learning to the accurate and cost-effective classification of photos based on sentiment, we introduce a daily market-level investor sentiment index (Photo Pessimism) obtained from a large sample of news photos. Consistent with behavioral models, Photo Pessimism predicts market return reversals and trading volume. The relation is strongest among stocks with high limits to arbitrage and during periods of elevated fear. We examine whether Photo Pessimism and pessimism embedded in news text act as complements or substitutes for each other in predicting stock returns and find evidence that the two are substitutes.<\/p>\n\n\n\n

#657 \u2013 Portfolio Optimization with Nonlinear Risk Budgeting using Neural Network<\/a><\/strong><\/p>\n\n\n\n

Period of rebalancing:<\/strong> Monthly
Markets traded: <\/strong>equities, commodities, bonds
Instruments used for trading:<\/strong> ETFs
Complexity:<\/strong> Very complex strategy
Backtest period:<\/strong> 2011-2021
Indicative performance:<\/strong> 12.33%
Estimated volatility:<\/strong> 8.84%<\/p>\n\n\n\n

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

Uysal, A. S., Li, X., & Mulvey, J. M.: End-to-End Risk Budgeting Portfolio Optimization with Neural Networks
<\/strong>https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3883614
<\/a>Abstracto:
Portfolio optimization has been a central problem in finance, often approached with two steps: calibrating the parameters and then solving an optimization problem. Yet, the two-step procedure sometimes encounter the \u201cerror maximization\u201d problem where inaccuracy in parameter estimation translates to unwise allocation decisions. In this paper, we combine the prediction and optimization tasks in a single feed-forward neural network and implement an end-to-end approach, where we learn the portfolio allocation directly from the input features. Two end-to-end portfolio constructions are included: a model-free network and a model-based network. The model-free approach is seen as a black-box, whereas in the model-based approach, we learn the optimal risk contribution on the assets and solve the allocation with an implicit optimization layer embedded in the neural network. The model-based end-to-end framework provides robust perfor- mance in the out-of-sample (2017-2021) tests when maximizing Sharpe ratio is used as the training objective function, achieving a Sharpe ratio of 1.16 when nominal risk parity yields 0.79 and equal-weight fix-mix yields 0.83. Noticing that risk-based port- folios can be sensitive to the underlying asset universe, we develop an asset selection mechanism embedded in the neural network with stochastic gates, in order to prevent the portfolio being hurt by the low-volatility assets with low returns. The gated end- to-end with filter outperforms the nominal risk-parity benchmarks with naive filtering mechanism, boosting the Sharpe ratio of the out-of-sample period (2017-2021) to 1.24 in the market data.<\/p>\n\n\n\n

#658 \u2013 Betting Against Uncertainty Beta in Australia<\/a><\/strong><\/p>\n\n\n\n

Period of rebalancing:<\/strong> Monthly
Markets traded: <\/strong>equities
Instruments used for trading:<\/strong> stocks
Complexity:<\/strong> Moderately complex strategy
Backtest period:<\/strong> 2009-2017
Indicative performance:<\/strong> 17.46%
Estimated volatility:<\/strong> 13.03%<\/p>\n\n\n\n

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

Nartea, Gilbert and Bai, Hengyu and Wu, Ji (George), Investor Sentiment and the Economic Policy Uncertainty Premium
<\/strong>https:\/\/ssrn.com\/abstract=3854203
<\/a>Abstracto:
Motivated by recent studies documenting an equity premium associated with economic policy uncertainty (EPU), we test the hypothesis that the EPU premium is stronger (weaker) following periods of low (high) investor sentiment. We estimate stock sensitivity to an economic policy uncertainty (EPU) index and show that stocks in the Australian equities market in the highest uncertainty beta quintile underperform stocks in the lowest quintile, similar to U.S. stocks. However, we find that this negative uncertainty premium remains significant only following periods of low investor sentiment as it disappears following periods of high sentiment. Our results complement the U.S. evidence in that uncertainty averse investors are willing to pay high prices for stocks with positive uncertainty beta and require extra compensation to hold stocks with the negative beta, but only in low sentiment periods. These results are consistent with strong (weak) intertemporal hedging demand for positive EPU beta stocks in low (high) sentiment periods. It is also consistent with limited (full) participation of pessimistic investors and investors with a high aversion to uncertainty in low (high) sentiment periods. Our results suggest that betting against EPU as a trading strategy would be relatively more profitable when executed during low sentiment periods.<\/p>\n\n\n\n

#659 \u2013 Robust Quality in Stocks<\/a><\/strong><\/p>\n\n\n\n

Period of rebalancing:<\/strong> Quarterly
Markets traded: <\/strong>equities
Instruments used for trading:<\/strong> stocks
Complexity:<\/strong> Complex strategy
Backtest period:<\/strong> 2003-2020
Indicative performance:<\/strong> 5%
Estimated volatility:<\/strong> 6.4%<\/p>\n\n\n\n

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

Lepetit, Frederic and Cherief, Amina and Ly, Yannick and Sekine, Takaya, Revisiting Quality Investing <\/strong>
https:\/\/ssrn.com\/abstract=3877161
<\/a>Abstracto:
In the field of factor investing, quality is undoubtedly the equity factor with the weakest consensus. This research investigates the best way to define it. In order to capture the multi-faceted reality of the factor depicted in academia, we address the quality factor through a multidimensional process by defining four self-reliant pillars: profitability, earnings quality, safety and investment. To better fit institutional investor’s’ needs, we analyze the resulting factor by focusing on the last eighteen years and on a global developed markets universe of liquid stocks (large- and mid-caps).
In a long-short framework, our quality factor delivers a statistically significant alpha that cannot be explained by loadings on conventional equity factors (market, value, size and momentum). Most regions and dimensions display positive contribution to this alpha, with the noticeable exceptions of the Eurozone region and the safety dimension. In a long-only framework, our quality factor outperforms its benchmark by 2.8% per annum over the entire analysis period, with an information ratio of 0.81. Furthermore, the outperformance has been very consistent since the 2008 Global Financial Crisis (GFC). The four dimensions are weakly correlated with each other and are therefore complementary. We show that safety is of particular importance during periods of market turmoil (GFC, Covid-19 pandemic) and that the dimension is therefore part of the quality factor in its own right. On the Eurozone side, a sector-neutral portfolio construction seems to be more suited.
We also introduce a new portfolio construction methodology by implementing a clustering approach based on the K-means algorithm to group together companies based on features that are related to both fundamentals and market characteristics. This approach allows to capture dynamic variations between fundamentals and other stock features. This fully implementable process results in better quality factor performance without impacting the associated risk measures or the portfolio\u2019s quality exposure, as measured on the unconstrained quality factor.<\/p>\n\n\n\n

#660\u2013 ESG in Currencies<\/a><\/strong><\/p>\n\n\n\n

Period of rebalancing:<\/strong> Monthly
Markets traded: <\/strong>currencies
Instruments used for trading:<\/strong> ETFs, futures, stocks
Complexity:<\/strong> Moderately complex strategy
Backtest period:<\/strong> 2001-2020
Indicative performance:<\/strong> 3.62%
Estimated volatility:<\/strong> 7.03%<\/p>\n\n\n\n

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

Ilias Filippou and Mark P. Taylor: Pricing Ethics in the Foreign Exchange Market: Environmental, Social and Governance Ratings and Currency Premia
<\/strong>https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3887760
<\/a>Abstracto:
We examine the cross-sectional predictive ability of the Refinitiv Environmental, Social and Governance (ESG) score for returns in the foreign exchange market, using ESG scores aggregated at the national level, and find that ESG is a strong negative predictor of currency returns. Intuitively, investors require a premium for financing low-ESG countries while high-ESG countries offer lower returns and provide a hedge in the bad state of the world. We show that ESG is priced in the cross-section of currency returns. We also consider the different components of ESG and show that its predictability is driven by the environmental pillar of the ESG ratings. The profitability of the ESG currency strategy is not driven by the carry trade and is robust to transaction costs.<\/p>\n\n\n\n

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

#223 \u2013 Realized Skewness Predicts Equity Returns<\/a><\/strong><\/p>\n\n\n\n

Rehman, Seema and Sharif, Saqib and Ullah, Wali: Higher Realized Moments and Stock Return Predictability
<\/strong>https:\/\/ssrn.com\/abstract=3702835
<\/a>Abstracto:
This study exploits information contained in high frequency sample data by computing higher realized moments of individual firms in the emerging stock market of Pakistan. Furthermore, the relation of higher moments with future stock returns is examined by constructing decile portfolios based on weekly realized volatility, skewness and kurtosis to predict next week return of the trading strategy that takes long position for portfolio of stocks having high realized moment and takes short position for portfolio of stocks having low realized moment. The long short spread is significant for equal weighted weekly returns based on realized volatility. The long short weekly return is positive and highly significant for realized skewness, 1.659 and 1.969 (in bps) with t-statistics of 7.92 and 14.027 for value and equal weighted portfolios respectively. The result for realized skewness is also supported by Carhart\u2019s Alphas. Similar results are obtained for realized kurtosis, 0.427 and 0.664 (in bps) of long short return, with t-statistics of 2.079 and 4.049 for value and equal weighted portfolios respectively. The evidence suggests that realized skewness and kurtosis can predict the next week\u2019s moment based cross sectional stock returns.<\/p>\n\n\n\n

#459 \u2013 Machine Learning and Currency Carry Strategy<\/a><\/strong><\/p>\n\n\n\n

Cartea, \u00c1lvaro and Jaimungal, Sebastian and S\u00e1nchez-Betancourt, Leandro: Deep Reinforcement Learning for Algorithmic Trading
<\/strong>https:\/\/ssrn.com\/abstract=3812473
<\/a>Abstracto:
We employ reinforcement learning (RL) techniques to devise statistical arbitrage strategies in electronic markets. In particular, double deep Q network learning (DDQN) and a new variant of reinforced deep Markov models (RDMMs) are used to derive the optimal strategies for an agent who trades in a foreign exchange (FX) triplet. An FX triplet consists of three currency pairs where the exchange rate of one pair is redundant because, by no-arbitrage, it is determined by the exchange rates of the other two pairs. We use simulations of a co-integrated model of exchange rates to implement the strategies and show their financial performance.<\/p>\n\n\n\n

#578 \u2013 Combining Smart Factors Momentum and Market Portfolio<\/a><\/strong><\/p>\n\n\n\n

Kadan, Ohad and Liu, Fang and Tang, Xiaoxiao: Recovering Conditional Factor Risk Premia
<\/strong>https:\/\/ssrn.com\/abstract=3803993
<\/a>Abstracto:
We offer an approach for recovering option-implied time-varying forward-looking risk premia of systematic factors—even if they do not possess actively-traded options. We apply this approach to the market, size, value, and momentum factors. We find that factor premia are highly volatile. Both the market and the value premia tend to be higher during slowdowns and recessions and during turbulent times. By contrast, the momentum premium is higher during periods of high economic growth and low volatility. We use the recovered factor premia to construct trading strategies, which mitigate market and momentum crash risk and to predict returns of individual stocks even if they do not possess traded options.<\/p>\n\n\n\n

#26 \u2013 Value (Book-to-Market) Factor<\/a><\/strong><\/p>\n\n\n\n

Shea, Yifei and Radatz, Erhard: Searching for Inner Peace with Value Factors
<\/strong>https:\/\/ssrn.com\/abstract=3737895
<\/a>Abstracto:
Value factors have always been an essential part of quantitative investing processes. We show that the deterioration in performance of value stocks, as defined by high book-to-price (B\/P) ratios, comes as no surprise given their relatively poor fundamentals as well as slower mean reversion of profitability. The opposite has been observed for low B\/P \u201cglamour\u201d stocks. Value defined by high earnings yield (E\/P) has also suffered from deteriorating performance despite being fundamentally different from value characterized by a high B\/P.<\/p>\n\n\n\n

#26 \u2013 Value (Book-to-Market) Factor<\/a><\/strong><\/p>\n\n\n\n

Dugar, Amitabh and Pozharny, Jacob: Equity Investing in the Age of Intangibles
<\/strong>https:\/\/ssrn.com\/abstract=3770088
<\/a>Abstracto:
Expenditures on creation of intangible capital have increased but accounting standards have not kept pace. We investigate whether this has affected the value relevance of book value and earnings. We construct a composite measure of intangible intensity based on intangible assets capitalized on the balance sheet, research and development expenditures, and sales, general & administrative expenditures to classify industries by intangible intensity. We show that the value relevance of book value and earnings has declined for high intangible intensity companies in USA and abroad, but for the low intangible intensity group it has remained stable in USA and increased internationally.<\/p>\n\n\n\n

And several interesting free blog posts have been published during last 2 weeks:<\/strong><\/h4>\n\n\n\n

Modelling the Impact of Climate Change and Policies on GDP<\/a><\/strong><\/p>\n\n\n\n

Climate change is becoming a central topic among economists, investors<\/a>, politicians and the general public as well. Scientists warn us that we have to act immediately, but it is not that simple because becoming environmentally friendly<\/a> is not cheap, and we are somewhat reluctant even though we have only one Earth. Moreover, while fighting climate change might be seen as a cost for developed economies, less developed economies frequently do not have many alternatives to fossil fuels.<\/p>\n\n\n\n

A captivating insight to this topic offers a paper by Alestra et al. (2020) since the research provides a model to examine climate change scenarios for GDP forecasting, considering both GDP damage caused by the climate change itself and the impact of measures aimed to mitigate the climate change. It is crucial to emphasise that climate change endangers the economy. Therefore, even though fighting climate change can negatively affect the GDP, not acting might be even worse in the long run.<\/p>\n\n\n\n

<\/a>The Best Systematic Trading Strategies in 2021: Part 2<\/a><\/strong>

In the first part of our article<\/a>, we talked about quantitative strategies which achieved even better results in 2021 than passive US equity investors. Then, we focused more on tendencies and trends among the best quantitative investment strategies. Today we will talk more deeply about specific trading strategies and shortly describe number #10 to number #6 of the best quantitative strategies of 2021.<\/p>\n\n\n\n

<\/a>Impact of US Inflation on Global Asset Returns<\/a><\/strong><\/p>\n\n\n\n

A lot of attention is centred around inflation in the academic literature. If the inflation is low and oscillates around central banks\u2019 targets, there is not a big fuss around it. However, when inflation gets high, it becomes a hot topic among investors.<\/p>\n\n\n\n

The sharp recovery is also accompanied by high inflation, and recent coronavirus crisis recovery<\/a> has become a hot topic among practitioners. But is the current period of higher inflation truly that bad? Dai and Medhat (2021) show that inflation is not as big a problem as it may seem in the long term. The authors have examined the relationship between US inflation and the performance of global assets such as stocks, bonds, commodities, REITs, factors or industry portfolios. Based on an analysis of both long-term and the most recent sample periods, the results suggest that most assets had positive real returns during high-inflation periods (and low-inflation as well).<\/p>\n\n\n\n

How to Use Exotic Assets to Improve Your Trading Strategy<\/a><\/strong><\/p>\n\n\n\n

As we have mentioned several times, the best course of action for a quant analyst who wants to develop a new trading strategy<\/a> is to understand a well-known investment anomaly\/factor fundamentally<\/a> and then improve it. Quantpedia is a big fan of transferring ideas derived from academic research from one asset class to another<\/a>. But that\u2019s not the only possibility of improvement \u2013 we can try to embrace Roger Ibbotson\u2019s theory of popularity<\/a>, which states that popular assets\/securities are usually overpriced compared to less-known (exotic) assets\/securities. Additionally, more professional investors usually follow popular assets, and this market segment is probably significantly more efficient.<\/p>\n\n\n\n

So, we went in this direction. We took a well-known commodity momentum factor strategy<\/a> and investigated its performance among commodity futures that were part of the S&P GSCI respectively BCOM commodity indexes and then compared the strategy\u2019s performance with a variant that traded only non-indexed commodity futures. As we had expected, the trading strategy using exotic assets performed significantly better.<\/p>\n\n\n\n

Community Alpha of QuantConnect \u2013 Part 2: Social Trading Factor Strategies<\/strong><\/a><\/p>\n\n\n\n

This blog post is the continuation of series about Quantconnect\u2019s Alpha market strategies.\u00a0\u00a0Part 1 can be found here.<\/a>\u00a0This part is related to the\u00a0factor strategies<\/a>\u00a0notoriously known from the majority of asset classes.
Overall, the factors on alpha strategies provide insightful results that could be utilized. The results particularly point to excluding the most extreme strategies based on various past distribution\u2019s characteristics.
Stay tuned for the 3rd and 4th part of this series, where we will explore factor meta-strategies built on top of the QuantConnect\u2019s Alpha Market<\/a>.<\/p>\n\n\n\n

The Best Systematic Trading Strategies in 2021: Part 3<\/a><\/strong><\/p>\n\n\n\n

In part 1 of our article<\/a>, we analyzed tendencies and trends among the Top 10 quantitative strategies of 2021. Thanks to Quantpedia Pro\u2019s screener<\/a>, we published several interesting insights about them.<\/p>\n\n\n\n

In part 2 of our article<\/a>, we got deeper into the first five specific strategies, which are significantly outperforming the rest in 2021. <\/p>\n\n\n\n

Today, without any further thoughts, let\u2019s proceed to the five single best performing strategies of 2021 as of August 2021.<\/p>\n\n\n\n

Factor Exposures of Thematic Indices<\/strong><\/a>

Numerous new businesses are emerging related to autonomous traffic, clean energy, biotechnology, etc. Without any doubt, these new companies are promising and at least the technology behind them seems to be the future. Moreover, this novel trend is also supported by the most prominent index creators S&P and MSCI. Both providers have created numerous thematic indexes connected to these hot industries. The popularity has caused that ETFs are nowhere behind, and as a result, these thematic indexes could be easily tracked. However, popularity itself does not guarantee the best investment, and we should be interested in these indexes in greater detail. A vital insight provides the novel research paper of Blitz (2021). The findings are interesting \u2013 the thematic investors bet against  <\/strong>quantitative<\/a> <\/strong><\/a><\/strong>investors<\/a> or, more precisely, against the most common factors<\/a> that are well-known from the asset pricing models.<\/p>\n\n\n\n

Plus, the following five trading strategies have been backtested in\u00a0QuantConnect<\/a>\u00a0in the previous two weeks:<\/strong><\/h4>\n\n\n\n

#64 – Statistical Arbitrage with ETFs<\/a>
#72 – Combined Mean Reversion and Momentum in Foreign Exchange Markets<\/a>
#123 – Options Skewness Predicts Consecutive Stocks Returns<\/a>
#653 – Similar Stock Short-term Momentum<\/a>
#654 – Momentum without the Crash Component<\/a><\/p>\n\n\n\n

\n\n\n\n

\u00bfBuscas m\u00e1s estrategias para leer? Suscr\u00edbete a nuestro bolet\u00edn informativo<\/a> o visite nuestra Blog<\/a> o Evaluador<\/a><\/strong>.<\/p>\n\n\n\n

\u00bfQuieres saber m\u00e1s sobre el servicio Quantpedia Premium? Consulta C\u00f3mo funciona Quantpedia<\/a>, nuestra misi\u00f3n<\/a> y Oferta de precios premium<\/a>.<\/strong><\/p>\n\n\n\n

\u00bfQuieres saber m\u00e1s sobre el servicio Quantpedia Pro? Compru\u00e9balo descripci\u00f3n<\/a>, mirar videos<\/a>, revisar capacidades de generaci\u00f3n de informes<\/a> y visite nuestro oferta de precios<\/a>.<\/strong><\/p>\n\n\n\n

\u00bfBuscas datos hist\u00f3ricos o plataformas de backtesting? Consulta nuestra lista de Descuentos en Algo Trading<\/a><\/strong>.<\/p>\n\n\n\n

\u00bfTe gustar\u00eda tener acceso gratuito a? nuestros servicios<\/a>? Entonces, Abre una cuenta con Lightspeed.<\/a> y disfrute de un a\u00f1o de Quantpedia Premium sin costo alguno.<\/strong><\/p>\n\n\n\n

\n\n\n\n

O s\u00edguenos en:<\/strong><\/p>\n\n\n\n

Facebook Grupo<\/a>, Facebook P\u00e1gina<\/a>, Gorjeo<\/a>, LinkedIn<\/a>, Medio<\/a> o YouTube<\/a><\/strong><\/p>","protected":false},"excerpt":{"rendered":"

Five new strategies have been added.<\/p>\n

Five new related research papers have been included into existing strategy reviews and seven short free blog posts<\/strong><\/a> have been published during last few weeks. Plus, five trading strategies have been backtested in QuantConnect<\/strong><\/a> in the previous two weeks.<\/strong><\/p>","protected":false},"author":21001,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-14964","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/posts\/14964","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\/21001"}],"replies":[{"embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/comments?post=14964"}],"version-history":[{"count":0,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/posts\/14964\/revisions"}],"wp:attachment":[{"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/media?parent=14964"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/categories?post=14964"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vvv.quantpedia.com\/es\/wp-json\/wp\/v2\/tags?post=14964"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}