Quantpedia Premium Update – 21st March

New strategies:

#840 – Investment Factor in Indian Stocks

Period of rebalancing: Yearly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 2006-2021
Indicative performance: 3.61%
Estimated volatility: 8.89%

Source paper:

Raju: Four and Five-Factor Models in the Indian Equities Market
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4054146
Abstract:
We compute the Fama-French three- and five-factor and momentum factor returns for Indian equities between October 2006 and February 2022 using data from Refinitiv Datastream following two breakpoint schemes. We show a high correlation between our factor return estimates and those reported in the Data Library using the breakpoint scheme that closely follows the Indian Institute of Management, Ahmedabad (IIMA) Data Library for the Indian Market. In addition, we report four- and five-factor return estimates using the current breakpoint methodology of Fama-French and other international replication studies. We show the differences in the factor return estimates due to the methodology, thereby bridging the method adopted in the seminal work by IIMA and current international practice. We differ from international studies by building portfolios in September of each year to reflect the Indian fiscal reporting period, thereby providing factors that reflect the Indian circumstance. We use factor spanning tests to show that all five Fama-French and Momentum factors explain average returns in the Indian equity markets.

#841 – Profitability Factor in Indian Stocks

Period of rebalancing: Yearly
Markets traded: stocks
Instruments used for trading: equities
Complexity: Complex strategy
Backtest period: 2006-2021
Indicative performance: 5.14%
Estimated volatility: 11.54%

Source paper:

#842 – Cross-Sectional Mood Beta Strategy in Equities

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1963-2016
Indicative performance: 11.42%
Estimated volatility: 15.71%

Source paper:

Hirshleifer, David A. and Jiang, Danling and Meng DiGiovanni, Yuting: Mood Beta and Seasonalities in Stock Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2880257
Abstract:
Existing research has documented cross-sectional seasonality of stock returns—the periodic outperformance of certain stocks during the same calendar months or weekdays. We hypothesize that assets’ different sensitivities to investor mood explain these effects and imply other seasonalities. Consistent with our hypotheses, relative performance across individual stocks or stock portfolios during past high or low mood months and weekdays tends to recur in periods with congruent mood and reverse in periods with noncongruent mood. Furthermore, assets with higher sensitivities to aggregate mood—higher mood betas—subsequently earn higher returns during ascending mood periods and lower returns during descending mood periods.

#843 – Cross-Sectional Mood Reversal Strategy in Equities

Source paper:

#844 – Firm-Level Investor Sentiment Factor in US

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 1971-2020
Indicative performance: 6.17%
Estimated volatility: 10.46%

Source paper:

Tang, Guohao and Wu, Yiyong and Jiang, Fuwei: A New Firm-level Investor Sentiment
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4222541
Abstract:
We propose a novel measure of firm-level investor sentiment based on the divergence of stock market beta from that of its industry peers. We show that this measure coincides with investor sentiment. In the cross-section, stocks with high investor sentiment significantly underperform those with low investor sentiment in the following month. The negative sentiment-return relationship is robust to different risk adjustment models, controls for related return predictors and market-level sentiment effects. We find that stocks with high investor sentiment experience more speculative demand, resulting in concurrent overpricing and subsequent lower stock returns. We further show that the predictability of firm-level sentiment is stronger among stocks with lower institutional ownership and during periods of recession, consistent with the theoretical prediction of mispricing driven by noise traders.

#845 – Modified volatility predicts DJI returns

Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: CFDs, ETFs, funds, futures
Complexity: Moderately complex strategy
Backtest period: 2000-2019
Indicative performance: 3.23%
Estimated volatility: –

Source paper:

Qiu, Rui and Liu, Jing and Li, Yan: Adjusted Long-Term Volatility and Stock Return Predictability
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4215686
Abstract:
We design an adjusted long-term volatility (ADJ_LV) indicator by removing the interference information of short-term volatility from the simple long-term volatility indicator to investigate the level of predictive ability that ADJ_LV has for stock returns. In a sample spanning 2000 to 2019 and models considering 19 popular predictors, ADJ_LV positively predicts the next-month returns of the S&P 500 index, with the corresponding univariate model displaying the best forecasting performance with an adjusted in-sample R-squared of 3.825%, out-of-sample R-squared of 3.356%, return gains of 5.976%, certainty equivalent return (CER) gains of 4.708 and Sharpe ratio gains of 0.394. Adding ADJ_LV as an additional predictor to the other 19 univariate models generates significantly better forecasting performance in both the in-sample and the out-of-sample results. Furthermore, we find that ADJ_LV also has predictive power for long-term (1-12 month) stock returns and can forecast returns of industry portfolios and portfolios formed by size, book-to-market ratio, operating risk and investment risk. The predictive ability of ADJ_LV for equity returns is robust in forecasts of the return of the DJI index and to the use of an alternative estimated ADJ_LV.

New research papers related to existing strategies:

#646 – Post-Earnings-Annoucement Drift Using NLP on Earnings Calls

Ewertz, Jonas and Knickrehm, Charlotte and Nienhaus, Martin and Reichmann, Doron: Listen Closely: Using Vocal Cues to Predict Future Earnings
https://ssrn.com/abstract=4307178
Abstract:
In this study, we aim to advance the prediction of firm earnings – an important task for many business applications. While existing earnings prediction models only rely on numerical financial data, we hypothesize and find that vocal cues from manager speech yield substantial predictive power: the area under the receiver operating characteristics curve ranges from 61.20% to 63.44%, significantly higher compared to models based on detailed financial data and textual inputs. We further analyze the models’ economic value to investment practitioners. We find that investors can use the models’ earnings forecasts to implement trading strategies that beat the market by 8.8% on average per year. Moreover, financial analysts can use vocal cues to improve their earnings forecast accuracy by more than 40%. Collectively, our results imply that managers’ vocal cues are important information signals for future earnings that investment practitioners currently overlook.

#842 – Cross-Sectional Mood Beta Strategy in Equities
#843 – Cross-Sectional Mood Reversal Strategy in Equities

Atilgan, Yigit and Demirtas, K. Ozgur and Gunaydin, A. Doruk and KIRLI, Imra: Mood Seasonality Around the Globe
https://ssrn.com/abstract=4225766
Abstract:
This paper examines the existence of mood seasonality, documented by Hirshleifer et al. (2020, JFE) for the cross-section of US equity returns, in an international setting. First, we confirm the results of the original study. Next, we extend these findings to non-US markets and show that they are not sample-specific. A stock’s relative historical seasonal returns are positively correlated with its relative future seasonal returns during similar or congruent mood periods and negatively related with its relative future seasonal returns during dissimilar or non-congruent mood periods. Moreover, both regression and portfolio analyses indicate that mood beta, the sensitivity of equity returns to aggregate investor mood, helps explain these mood seasonality effects.

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

Çepni, Oğuzhan and Demirer, Riza and Pham, Linh and Rognone, Lavinia: Climate Uncertainty and Information Transmissions Across the Conventional and ESG Assets
https://ssrn.com/abstract=4181940
Abstract:
We examine the effect of climate uncertainty on the spillover effects across the European conventional and ESG financial markets via novel measures of physical and transitional climate risk proxies obtained from textual analysis. While the conventional stock market index serves as the net shock transmitter to ESG assets, we find that shock transmissions between the two asset classes are significantly lower during periods of high climate uncertainty, suggesting that ESG investments can offer conventional investors diversification benefits against climate-driven shocks. Indeed, by comparing a forward-looking investment strategy conditional on the level of climate risk to the passive investment strategy, we show that investors who are worried about physical climate risks could utilize ESG equity sector portfolios as a diversification tool during periods of high physical climate uncertainty. In contrast, ESG bonds are found to be particularly useful in managing transition risk exposures that are associated with policy uncertainty and/or business transitions with respect to environmental policies. The findings have important implications for investors and policymakers regarding the role of climate uncertainty as a driver of informational spillovers across the conventional and ESG assets with important insights to manage climate risk exposures.

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

Chasiotis, Ioannis and Gounopoulos, Dimitrios and Konstantios, Dimitrios and Patsika, Victoria: ESG Reputational Risk, Corporate Payouts and Firm Value
https://ssrn.com/abstract=4180523
Abstract:
This study identifies and empirically assesses the relationship between ESG reputational risk and corporate payouts. We provide robust evidence that ESG reputational risk stimulates higher payouts and that the presence of strong (weak) monitoring mechanisms amplifies (attenuates) this relationship. Turning to payout composition we show that ESG reputational risk steers firms towards a more flexible payout mix comprising a higher analogy of share repurchases versus dividends, an effect that intensifies under financial constraints. Moreover, we document that the market places a premium on distributions from high ESG reputational risk firms. Collectively, our findings indicate that ESG reputational risk raise financial risk thus firms respond by disgorging cash via a more flexible payout regime.

#480 – Machine Learning-Based Financial Statement Analysis
#536 – Machine Learning Stock Picking

Noguer i Alonso, Miquel and Zoonekynd, Vincent: Equity Machine Factor Models
https://ssrn.com/abstract=4310924
Abstract:
We examine in this paper the training and test set performance of several equity factor models with a dataset of 20 years of data, 1,200 stocks and 100 factors. First, we examine several models to forecast expected returns, which can be used as baselines for more complex models: linear regression, linear regression with an L1 penalty (lasso), constrained linear regression, xgboost and artificial neural networks. Second, we present a unified framework for portfolio construction, leveraging machine learning for the whole pipeline, from the factor data to the portfolio weights, which scales to a large number of assets and predictors. The results we obtain are interesting and non trivial to interpret; non linear models models offer a more balanced outcome considering test set Sharpe ratio and turnover but linear unconstrained models show a good performance in the test set. We introduce a model-free reinforcement learning model, which uses factors to find the portfolio weights maximizing the information ratio.

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

Which Factors Drive the Hedge Fund Returns: A Machine Learning Approach

Arbitrage is a central concept in finance. It is defined as simultaneous long and short positions in similar assets to exploit mispricing. Hedge funds experienced fast growth over the past three decades, as real-world arbitrageurs as a group. As they increasingly influence the financial market, it is important to understand the economic drivers of hedge fund returns. Therefore we would like to present a paper dealing with the development of a parsimonious factor model, based on anomalies, to explain hedge fund returns.

Avoid Equity Bear Markets with a Market Timing Strategy – Part 1

In this series of three articles, our goal is to construct a market timing strategy that would reliably sidestep the equity market during bear markets, thereby reducing market volatility and boosting risk-adjusted returns. We will build trading signals based on price-based indicators, macroeconomic indicators, and a leading indicator, a yield curve, that would try to predict recessions and bear markets in advance. All three articles would be published in a span of the next few days. We start with the first part – a short intro into the market timing strategies using price-based rules.

Avoid Equity Bear Markets with a Market Timing Strategy – Part 2

In this second installment in a series of three articles, we will continue with our goal to construct a market timing strategy that would sidestep the equity market during bear markets. A few days ago, we started with price-based market timing strategies. Today, we will focus on macroeconomic indicators and predictors derived from the movements in the commodity markets.

Avoid Equity Bear Markets with a Market Timing Strategy – Part 3

In the last third installment, we will finish exploring the world of market timing strategies (see parts 1 & 2). We will focus on yield curve predictors and incorporate all three ideas (price-based, macro-economic, and yield curve predictors) into one final trading strategy that yields an annual return above that of the stock market while doubling its Sharpe ratio and reducing maximal drawdown by two thirds.