Quantpedia Premium Update – 5th March

New strategies:

#835 – Reversal After Voluntary Disclosures

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1990-2017
Indicative performance: 12.20%
Estimated volatility: 68.77%

Source paper:

Hyun Jung Rim, Jenny Zha Giedt: Mistaking Bad News for Good News: Mispricing of a Voluntary Disclosure
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4322045
Abstract:
We challenge the prevailing belief among investors that a company’s evaluation of strategic alternatives is good news and show that this news is mispriced. We propose that investors succumb to a cognitive bias known as the ‘availability heuristic’ (Tversky and Kahneman, 1973). We find corroborating evidence in that: (i) mispricing is exacerbated by expectations of a potential takeover; (ii) investors and analyst do not fully incorporate the signal about the firm’s declining fundamentals, and future earnings reports correct their overly optimistic expectations; and (iii) inducing the availability heuristic in experiment participants causes over-optimism. Moreover, we document the role of investor sophistication and investor learning.

#836 – Relative Sentiment and Machine Learning for Tactical Asset Allocation

Period of rebalancing: Monthly
Markets traded: stocks
Instruments used for trading: equities
Complexity: Very complex strategy
Backtest period: 2002-2019
Indicative performance: 15.9%
Estimated volatility: 11.04%

Source paper:

Micaletti, C. Raymond: Relative Sentiment and Machine Learning for Tactical Asset Allocation
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3475258
Abstract
We examine Sentix sentiment indices for use in tactical asset allocation. In particular, we construct monthly relative sentiment factors for the U.S., Europe, Japan, and Asia ex-Japan by taking the difference in 6-month economic expectations between each region’s institutional and individual investors. These factors (along with one-month forward equity returns) then serve as inputs to a wide array of machine learning algorithms. Employing combinatorial cross-validation and adjusting for data snooping, we find relative sentiment factors have robust and significant predictive power in all four regions; that they surpass both standalone sentiment and time-series momentum in terms of informational content; and that they demonstrate the ability to identify the subsequent best- and worst-performing global equity markets from along a cross-section. The results are consistent with previous findings on relative sentiment, discovered using unrelated datasets.

#837 – Patent Innovation Factor in Stocks

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1981-2019
Indicative performance: 5.54%
Estimated volatility: 11.83%

Source paper:

Kim, Jinyoung: New Technologies and Stock Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4299577
Abstract
Investments in emerging technologies, such as quantum computing, are risky. This paper examines whether investing in stocks of companies with high exposure to new technologies leads to potentially high returns. I collect all U.S. patent publications publicized between 1976 and 2021 and their first-and second-hop neighbor patents in their citation network. I use textual information and the information on the citation network to detect tech clusters experiencing high growth of new patents. A size-adjusted value-weighted portfolio is created by buying firms with high exposure to new technology and selling firms with low exposure (new-minus-old factor, NMO). The portfolio generates 7.4% annual returns and 5.7% to 14.7% annualized alphas depending on different factor models. In the Fama and MacBeth (1973) regressions of monthly excess returns, the exposure to new technology has a positive, statistically significant loading. I further show that the results are driven by risk-return trade-off.

#838 – Overnight Reversal and the Asymmetric Reaction to News

Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 1996-2020
Indicative performance: 47.52%
Estimated volatility: 36.27%

Source paper:

Dangl, Thomas and Salbrechter, Stefan: Overnight Reversal and the Asymmetric Reaction to News
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4307675
Abstract
News released overnight has a significant directional impact on individual shares’ opening prices, i.e., the market tends to open higher (lower) when news with positive (negative) sentiment is published. However, the market opening is not fully efficient due to over- or underreactions of market participants to the news, resulting in a predictable pattern of returns on the following trading day. In particular, we find that large daytime returns followed by overnight news with strong sentiment lead to a predictable return reversal during the subsequent trading day. This predictable reversal is present independent of the polarity of the news sentiment. Without overnight news, large previous-day returns only have marginal predictive power.

#839 – Factor Allocation with Reinforcement Learning

Period of rebalancing: Yearly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very complex strategy
Backtest period: 2005-2020
Indicative performance: 7.37%
Estimated volatility: 2.73%

Source paper:

Goyenko, Ruslan and Zhang, Chengyu: Multi-(Horizon) Factor Investing with AI
https://ssrn.com/abstract=4187056
Abstract:
We provide a novel approach for multi-factor investing with big data by a multi-horizon investor who takes into consideration long-term versus short-term volatility, liquidity and trading costs trade offs while maximizing expected portfolio returns. Reinforcement learning (RL), which is generally used to solve problems with long- versus short-term reward trade-offs, allows explicitly incorporating long, ten-year investment horizon considerations during training. In out-of-sample, testing period we are the first to show the importance of investment horizon effect for portfolio performance. First, RL portfolio of long term investors with annual rebalancing performs competitively vis-à-vis their short-term peers with monthly rebalancing, and outperforms the latter due to lower portfolio rebalancing needs, turnover and trading costs. Second, when both, short and long-term investors are allowed to rebalance monthly, long-horizon portfolio outperforms by being more patient, with more strategic factor timing and turnover strategies spread over multiple months. Short horizon portfolio is less patient, has higher volatility and almost twice higher monthly turnover. Importantly, we identify different fundamental economic signals determining success of long vs. short-term strategies.

New research papers related to existing strategies:

#823 – Machine Learning and the Cross-Section of Cryptocurrency Returns
#381 – Blended Factors in Cryptocurrencies

Han, Newton, Platanakis, Wu, Xiao: The Diversification Benefits of Cryptocurrency Factor Portfolios: Are They There?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4319598
Abstract:
We investigate the out-of-sample diversification benefits of cryptocurrencies from a generalised perspective, a cryptocurrency-factor level, with traditional and machine-learning-enhanced asset-allocation strategies. The cryptocurrency factor portfolios are formed in an analogous way to equity anomalies by using more than 2,000 cryptocurrencies. The findings indicate that a stock-bond portfolio incorporating size- and momentum-based cryptocurrency factors can achieve statistically significant out-of-sample diversification benefits for investors with different risk preferences. Additionally, machine-learning-enhanced asset-allocation strategies can boost the traditional approaches by enriching (shrinking) the distributions of weights allocated to potentially effective cryptocurrency factors. Our findings are robust to i) the inclusion of transaction costs, ii) an alternative benchmark portfolio, and iii) a rolling-window estimation scheme.

#461 – ESG Factor Momentum Strategy
#460 – ESG Level Factor Investing Strategy

Cesarone, Martino, Carleo: Does ESG Impact Really Enhance Portfolio Profitability?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4007413
Abstract:
Over the last few decades, a growing attention to the Social Responsibility topic has affected financial markets and institutional authorities. Indeed, recent environmental, social and financial crises have inevitably led regulators and investors to take into account the sustainable investing issue. However, the question of how Environmental, Social and Governance (ESG) criteria impact financial portfolio performances, is still open.

In this work, we examine a multi-objective optimization model for portfolio selection, where we add to the classical Mean-Variance analysis, a third non-financial goal represented by the ESG scores. The resulting optimization problem, formulated as a convex Quadratic Programming, consists in minimizing the portfolio variance with parametric lower bounds on the levels of the portfolio expected return and ESG.

We provide here an extensive empirical analysis on five datasets involving real-world capital market indices from major stock markets. Our empirical findings typically reveal the presence of two behavioral patterns for the 16 Mean-Variance-ESG portfolios analyzed. Indeed, over the last fifteen years we can distinguish two non-overlapping time windows on which the inclusion of portfolio ESG targets leads to different regimes in terms of portfolio profitability.

Furthermore, on the most recent time window we observe that, for the US markets, imposing a high ESG target tends to select portfolios that show better financial performances than the other strategies, whereas for the European markets the ESG constraint does not seem to improve the portfolio profitability.

#461 – ESG Factor Momentum Strategy
#460 – ESG Level Factor Investing Strategy

Hoang, Wee, Yang, Yu: Institutional Trading Around Firms’ Negative ESG Incidents
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4059541
Abstract:
This paper provides evidence that institutional investors’ concern for firms’ environment, social and governance (ESG) is reflected in their trading activity around firms’ negative ESG incidents. We show that institutional investors reduce net purchases around these incidents, and the higher the CSR index of the institutional investor, the lower the net purchase. We further show that the pre-incident institutional trading is associated with abnormal profits, suggesting institutional investors seem to be informed and trade in anticipation of ESG incidents. We then find that such information advantage is moderated by firm-level information asymmetry, shareholder breadth, and long-term CSR reputation.

#33 – Post-Earnings Announcement Effect

Hansen, Siggaard: Double Machine Learning: Explaining the Post-Earnings Announcement Drift
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4017917
Abstract:
We demonstrate the benefits of merging traditional hypothesis-driven research with new methods from machine learning that enable high-dimensional inference. Because the literature on post-earnings announcement drift (PEAD) is characterized by a “zoo” of explanations, limited academic consensus on model design, and reliance on massive data, it will serve as a leading example to demonstrate the challenges of high-dimensional analysis. We identify a small set of variables associated with momentum, liquidity, and limited arbitrage that explain PEAD directly and consistently, and the framework can be applied broadly in finance.

#257 – Cloning Hedge Fund Indexes

Antoniadis, Skouras: Hedge Fund Factor Exposures with Daily Data
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4287028
Abstract:
We find that performance evaluation of hedge funds at daily resolution suggests exposures to more factors and consequently less alpha than identical analyses at monthly resolution, due to the higher statistical precision of daily estimates. Additionally, using a comprehensive set of daily factors and predictors of factor exposures, we report several new findings for hedge fund returns, including exposure to commodity puts and daily variation in exposures as a function of market liquidity. Since hedge fund returns have been analyzed almost exclusively with monthly returns and a limited set of static factors, our findings suggest that much outstanding research on hedge fund alpha and risk exposures should be interpreted with caution.

#454 – Time Series Momentum Strategies Using Deep Neural Networks
#581 – Equity Index and Risk-free Asset Allocation Using Neural Networks

Khan: Return Predictability and Market Sentiment: Evidence from Deep Learning
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4314543
Abstract:
This study finds that mispricing is a vital source of the cross-sectional return predictability in equity returns. Using a novel Artificial Neural Network (ANN) regression model, I obtain firm-level predictions conditional on 54 firm-level characteristics and an encoded representation of the macro-economic state. These predictions provide important insights into the sources of overall cross-sectional return predictability. First, the future negative returns are predictable out-of-sample which implies negative expected returns. Such predictability is hard to reconcile with a risk-based explanation. Secondly, the predictability in negative returns is higher following periods of high sentiment and vice versa. This evidence is consistent with the existence of a market-level investor sentiment that drives misvaluations. Third, a long-short strategy based on ANN prediction deciles is more profitable following periods of high sentiment. This disparity in pro fitability points to arbitrage asymmetry implied by short-sale constraints. Fourth, the predictability in losses and high pro fitability of the ANN top decile vanishes in estimation horizons longer than a month. This suggests that mispricing is short-lived and that predictability is realized due to corrections to such misvaluations. These corrections are preceded by high put-to-call(PCR) trading volumes and high implied volatility(VIX). Finally, the short-term and long-term predictions load on different conditioning variables indicating varying sources of predictability across return horizons. Overall, these findings are consistent with the existence of sentiment-driven short-lived mispricing that corrects in longer horizons.

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

How to Deal With Missing Financial Data

The problem of missing financial data is widespread yet often overlooked. An interesting insight into the structure of missing financial data provides a novel research paper by authors Bryzgalova et al. (2022). Firstly, examining the dataset of the 45 most popular characteristics in asset pricing, the authors found that missing data is frequent among almost any characteristic and affects all kinds of firms – small, large, young, mature, profitable, or in financial distress. The requirement of multiple characteristics simultaneously makes the problem even worse. Moreover, the data is not missing randomly; missing values clusters both cross-sectionally and over time. This may lead to a selection bias, making most famous ad-hoc approaches like the median invalid. Considering the abovementioned findings, the authors propose a novel imputation method based on Principal Component Analysis (PCA).

Time Series Variation in the Factor Zoo

Factor investing and detailed allocation according to different sets of factors are lively researched topics with many unanswered and open questions. Many views are often conflicting and from both radical sides — on one, that only a few factors should be necessary to explain the cross-section of mean returns, which is attractive, especially because of its simplicity; on the other, that you can use complex (authors examine the 161 “clear predictors” and 44 “likely predictors”) combinations of factors from less known and unorthodox models, but falling into dangerous and often unexamined “factor zoo” with many undesirable, unexamined and non-controllable outcomes. A huge gap is often seen in finance between the theory of academia and practical applications (by PMs [portfolio managers]), and so is especially present in this one. Let’s take a look at what the complexity of factors does for various equities pricing models.