nep-fmk New Economics Papers
on Financial Markets
Issue of 2020‒10‒26
eighteen papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Fears for COVID-19: The crash risk of stock market By Zhifeng Liu; Toan Luu Duc Huynh; Peng-Fei Dai
  2. Firm-Level Risk Exposures and Stock Returns in the Wake of COVID-19 By Steven J. Davis; Stephen Hansen; Cristhian Seminario-Amez
  3. Has the Stock Market Become Less Representative of the Economy? By Frederik P. Schlingemann; René M. Stulz
  4. Choosing News Topics to Explain Stock Market Returns By Paul Glasserman; Kriste Krstovski; Paul Laliberte; Harry Mamaysky
  5. Distillation of News Flow into Analysis of Stock Reactions By Junni L. Zhang; Wolfgang Karl H\"ardle; Cathy Y. Chen; Elisabeth Bommes
  6. Strikingly Suspicious Overnight and Intraday Returns By Bruce Knuteson
  7. Forecasting Stock Returns with Large Dimensional Factor Models By Alessandro Giovannelli; Daniele Massacci; Stefano Soccorsi
  8. Tail-risk protection: Machine Learning meets modern Econometrics By Bruno Spilak; Wolfgang Karl H\"ardle
  9. Using Machine Learning and Alternative Data to Predict Movements in Market Risk By Thomas Dierckx; Jesse Davis; Wim Schoutens
  10. A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data By Qi Zhao
  11. Machine Learning Classification of Price Extrema Based on Market Microstructure Features: A Case Study of S&P500 E-mini Futures By Artur Sokolovsky; Luca Arnaboldi
  12. Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models By Sidra Mehtab; Jaydip Sen; Abhishek Dutta
  13. Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network By Xing Wang; Yijun Wang; Bin Weng; Aleksandr Vinel
  14. Portfolio Optimization on Multivariate Regime Switching GARCH Model with Normal Tempered Stable Innovation By Cheng Peng; Young Shin Kim
  15. Sovereign bond and CDS market contagion: A story from the Eurozone crisis. By Bampinas, Georgios; Panagiotidis, Theodore; Politsidis, Panagiotis
  16. Efficient Markets Hypothesis in Canada:‎ a comparative study between Islamic and Conventional stock markets ‎ By neifar, malika
  17. Efficiency-Market Hypothesis: case of Tunisian and 6 ‎Asian stock markets ‎ By neifar, malika
  18. Granger-causal relationship between islamic stock markets and oil prices: a case study of Malaysia By Musaeva, Gulzhan; Masih, Mansur

  1. By: Zhifeng Liu; Toan Luu Duc Huynh; Peng-Fei Dai
    Abstract: This paper investigates the impact of COVID-19 epidemic on the Chinese stock market crash risk. We first estimate conditional skewness of the return distribution from the GARCH-S model as the proxy of the equity market crash risk for the Shanghai Exchange Stock Market. Then, we construct a fear index for COVID-19 using the data from Baidu Index. Our findings show that the conditional skewness reacts negatively to daily growth in total confirmed cases, indicating that the epidemic increases the crash risk of stock market. Furthermore, we find that the fear sentiment also exacerbates the crash risk. In particular, the fear sentiment plays a significant role in the impact of COVID-19 on the crash risk. When the fear sentiment among people is high, the stock market crash risk is affected by the epidemic more seriously. Evidence from the daily deaths and global cases shows the robustness.
    Date: 2020–09
  2. By: Steven J. Davis; Stephen Hansen; Cristhian Seminario-Amez
    Abstract: Firm-level stock returns differ enormously in reaction to COVID-19 news. We characterize these reactions using the Risk Factors discussions in pre-pandemic 10-K filings and two text-analytic approaches: expert-curated dictionaries and supervised machine learning (ML). Bad COVID-19 news lowers returns for firms with high exposures to travel, traditional retail, aircraft production and energy supply — directly and via downstream demand linkages — and raises them for firms with high exposures to healthcare policy, e-commerce, web services, drug trials and materials that feed into supply chains for semiconductors, cloud computing and telecommunications. Monetary and fiscal policy responses to the pandemic strongly impact firm-level returns as well, but differently than pandemic news. Despite methodological differences, dictionary and ML approaches yield remarkably congruent return predictions. Importantly though, ML operates on a vastly larger feature space, yielding richer characterizations of risk exposures and outperforming the dictionary approach in goodness-of-fit. By integrating elements of both approaches, we uncover new risk factors and sharpen our explanations for firm-level returns. To illustrate the broader utility of our methods, we also apply them to explain firm-level returns in reaction to the March 2020 Super Tuesday election results.
    Date: 2020
  3. By: Frederik P. Schlingemann; René M. Stulz
    Abstract: The firms listed on the stock market in aggregate as well as the top market capitalization firm contribute less to total non-farm employment and GDP now than in the 1970s. A major reason for this development is the decline of manufacturing and the growth of the service economy as firms providing services are less likely to be listed on exchanges. We develop quantitative measures of representativeness showing how firms’ market capitalizations differ from their contribution to employment and GDP. Representativeness is worst when the market is most highly valued and worsens over time for employment, but not for value added.
    JEL: E44 G23 G32 K22 L16
    Date: 2020–10
  4. By: Paul Glasserman; Kriste Krstovski; Paul Laliberte; Harry Mamaysky
    Abstract: We analyze methods for selecting topics in news articles to explain stock returns. We find, through empirical and theoretical results, that supervised Latent Dirichlet Allocation (sLDA) implemented through Gibbs sampling in a stochastic EM algorithm will often overfit returns to the detriment of the topic model. We obtain better out-of-sample performance through a random search of plain LDA models. A branching procedure that reinforces effective topic assignments often performs best. We test methods on an archive of over 90,000 news articles about S&P 500 firms.
    Date: 2020–10
  5. By: Junni L. Zhang; Wolfgang Karl H\"ardle; Cathy Y. Chen; Elisabeth Bommes
    Abstract: The gargantuan plethora of opinions, facts and tweets on financial business offers the opportunity to test and analyze the influence of such text sources on future directions of stocks. It also creates though the necessity to distill via statistical technology the informative elements of this prodigious and indeed colossal data source. Using mixed text sources from professional platforms, blog fora and stock message boards we distill via different lexica sentiment variables. These are employed for an analysis of stock reactions: volatility, volume and returns. An increased sentiment, especially for those with negative prospection, will influence volatility as well as volume. This influence is contingent on the lexical projection and different across Global Industry Classification Standard (GICS) sectors. Based on review articles on 100 S&P 500 constituents for the period of October 20, 2009, to October 13, 2014, we project into BL, MPQA, LM lexica and use the distilled sentiment variables to forecast individual stock indicators in a panel context. Exploiting different lexical projections to test different stock reaction indicators we aim at answering the following research questions: (i) Are the lexica consistent in their analytic ability? (ii) To which degree is there an asymmetric response given the sentiment scales (positive v.s. negative)? (iii) Are the news of high attention firms diffusing faster and result in more timely and efficient stock reaction? (iv) Is there a sector-specific reaction from the distilled sentiment measures? We find there is significant incremental information in the distilled news flow and the sentiment effect is characterized as an asymmetric, attention-specific and sector-specific response of stock reactions.
    Date: 2020–09
  6. By: Bruce Knuteson
    Abstract: The world's stock markets display a strikingly suspicious pattern of overnight and intraday returns. Overnight returns to major stock market indices over the past few decades have been wildly positive, while intraday returns have been disturbingly negative. The cause of these astonishingly consistent return patterns is unknown. We highlight the features of these extraordinary patterns that have hindered the construction of any plausible innocuous explanation. We then use those same features to deduce the only plausible explanation so far advanced for these strikingly suspicious returns.
    Date: 2020–10
  7. By: Alessandro Giovannelli; Daniele Massacci; Stefano Soccorsi
    Abstract: We study equity premium out-of-sample predictability by extracting the information contained in a high number of macroeconomic predictors via large dimensional factor models. We compare the well known factor model with a static representation of the common components with a more general model known as the Generalized Dynamic Factor Model. Using statistical and economic evaluation criteria, we empirically show that the Generalized Dynamic Factor Model helps predicting the equity premium. Exploiting the link between business cycle and return predictability, we find more accurate predictions by combining rolling and recursive forecasts in real-time, with promising results in the aftermath of the Great Financial Crisis.
    Keywords: Stock Returns Forecasting, Factor Model, Large Data Sets, Forecast Evaluation
    JEL: C38 C53 C55 G11 G17
    Date: 2020
  8. By: Bruno Spilak; Wolfgang Karl H\"ardle
    Abstract: Tail risk protection is in the focus of the financial industry and requires solid mathematical and statistical tools, especially when a trading strategy is derived. Recent hype driven by machine learning (ML) mechanisms has raised the necessity to display and understand the functionality of ML tools. In this paper, we present a dynamic tail risk protection strategy that targets a maximum predefined level of risk measured by Value-At-Risk while controlling for participation in bull market regimes. We propose different weak classifiers, parametric and non-parametric, that estimate the exceedance probability of the risk level from which we derive trading signals in order to hedge tail events. We then compare the different approaches both with statistical and trading strategy performance, finally we propose an ensemble classifier that produces a meta tail risk protection strategy improving both generalization and trading performance.
    Date: 2020–10
  9. By: Thomas Dierckx; Jesse Davis; Wim Schoutens
    Abstract: Using machine learning and alternative data for the prediction of financial markets has been a popular topic in recent years. Many financial variables such as stock price, historical volatility and trade volume have already been through extensive investigation. Remarkably, we found no existing research on the prediction of an asset's market implied volatility within this context. This forward-looking measure gauges the sentiment on the future volatility of an asset, and is deemed one of the most important parameters in the world of derivatives. The ability to predict this statistic may therefore provide a competitive edge to practitioners of market making and asset management alike. Consequently, in this paper we investigate Google News statistics and Wikipedia site traffic as alternative data sources to quantitative market data and consider Logistic Regression, Support Vector Machines and AdaBoost as machine learning models. We show that movements in market implied volatility can indeed be predicted through the help of machine learning techniques. Although the employed alternative data appears to not enhance predictive accuracy, we reveal preliminary evidence of non-linear relationships between features obtained from Wikipedia page traffic and movements in market implied volatility.
    Date: 2020–09
  10. By: Qi Zhao
    Abstract: This paper presents a deep learning framework based on Long Short-term Memory Network(LSTM) that predicts price movement of cryptocurrencies from trade-by-trade data. The main focus of this study is on predicting short-term price changes in a fixed time horizon from a looking back period. By carefully designing features and detailed searching for best hyper-parameters, the model is trained to achieve high performance on nearly a year of trade-by-trade data. The optimal model delivers stable high performance(over 60% accuracy) on out-of-sample test periods. In a realistic trading simulation setting, the prediction made by the model could be easily monetized. Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data. This study exceeds existing researches in term of the scale and precision of data used, as well as the high prediction accuracy achieved.
    Date: 2020–10
  11. By: Artur Sokolovsky; Luca Arnaboldi
    Abstract: The study introduces an automated trading system for S\&P500 E-mini futures (ES) based on state-of-the-art machine learning. Concretely: we extract a set of scenarios from the tick market data to train the model and further use the predictions to model trading. We define the scenarios from the local extrema of the price action. Price extrema is a commonly traded pattern, however, to the best of our knowledge, there is no study presenting a pipeline for automated classification and profitability evaluation. Our study is filling this gap by presenting a broad evaluation of the approach showing the resulting average Sharpe ratio of 6.32. However, we do not take into account order execution queues, which of course affect the result in the live-trading setting. The obtained performance results give us confidence that this approach is worthwhile.
    Date: 2020–09
  12. By: Sidra Mehtab; Jaydip Sen; Abhishek Dutta
    Abstract: Prediction of stock prices has been an important area of research for a long time. While supporters of the efficient market hypothesis believe that it is impossible to predict stock prices accurately, there are formal propositions demonstrating that accurate modeling and designing of appropriate variables may lead to models using which stock prices and stock price movement patterns can be very accurately predicted. In this work, we propose an approach of hybrid modeling for stock price prediction building different machine learning and deep learning-based models. For the purpose of our study, we have used NIFTY 50 index values of the National Stock Exchange (NSE) of India, during the period December 29, 2014 till July 31, 2020. We have built eight regression models using the training data that consisted of NIFTY 50 index records during December 29, 2014 till December 28, 2018. Using these regression models, we predicted the open values of NIFTY 50 for the period December 31, 2018 till July 31, 2020. We, then, augment the predictive power of our forecasting framework by building four deep learning-based regression models using long-and short-term memory (LSTM) networks with a novel approach of walk-forward validation. We exploit the power of LSTM regression models in forecasting the future NIFTY 50 open values using four different models that differ in their architecture and in the structure of their input data. Extensive results are presented on various metrics for the all the regression models. The results clearly indicate that the LSTM-based univariate model that uses one-week prior data as input for predicting the next week open value of the NIFTY 50 time series is the most accurate model.
    Date: 2020–09
  13. By: Xing Wang; Yijun Wang; Bin Weng; Aleksandr Vinel
    Abstract: We have proposed to develop a global hybrid deep learning framework to predict the daily prices in the stock market. With representation learning, we derived an embedding called Stock2Vec, which gives us insight for the relationship among different stocks, while the temporal convolutional layers are used for automatically capturing effective temporal patterns both within and across series. Evaluated on S&P 500, our hybrid framework integrates both advantages and achieves better performance on the stock price prediction task than several popular benchmarked models.
    Date: 2020–09
  14. By: Cheng Peng; Young Shin Kim
    Abstract: We propose a Markov regime switching GARCH model with multivariate normal tempered stable innovation to accommodate fat tails and other stylized facts in returns of financial assets. The model is used to simulate sample paths as input for portfolio optimization with risk measures, namely, conditional value at risk and conditional drawdown. The motivation is to have a portfolio that avoids left tail events by combining models that incorporates fat tail with optimization that focuses on tail risk. In-sample test is conducted to demonstrate goodness of fit. Out-of-sample test shows that our approach yields higher performance measured by Sharpe-like ratios than the market and equally weighted portfolio in recent years which includes some of the most volatile periods in history. We also find that suboptimal portfolios with higher return constraints tend to outperform optimal portfolios.
    Date: 2020–09
  15. By: Bampinas, Georgios; Panagiotidis, Theodore; Politsidis, Panagiotis
    Abstract: We examine the asymmetric and nonlinear nature of the cross- and intra-market linkages of eleven EMU sovereign bond and CDS markets during 2006-2018. By adopting the excess correlation concept of Bekaert et al. (2005) and the local Gaussian correlation approach of Tjøstheim and Hufthammer (2013), we find that contagion phenomena occurred during two major phases. The first, extends from late 2009 to mid 2011 and concerns the outright contagion transmission from EMU South bond markets towards all European CDS markets. The second, is during the revived fears of a Greek exit in November 2011 and is characterized by contagion from (i) CDS spreads in the EMU South towards bond yields in the same bloc and Belgium, and (ii) from Italian and Spanish CDS spreads towards all European CDS spreads. Consistent with their “too big to bail out” status, Italy and Spain emerge as pivotal for the evolution of sovereign credit risk across the Eurozone. Our examination of the relevant mechanisms, highlights the importance of credit risk over liquidity risk, and the containment effect of the naked CDS ban.
    Keywords: sovereign bond market, sovereign CDS market, nonlinear dependence, contagion, local Gaussian correlation
    JEL: C1 C58 G01 G14 G15
    Date: 2020–08–06
  16. By: neifar, malika
    Abstract: In this paper we test the weak form of the Efficient-Market Hypothesis (EMH) using monthly ‎data from 2004M08 to 2018M04 of stock prices by using linear and nonlinear (KSS 3 type, ‎Sollis and Kruse) unit root tests. The informational market efficiency is examined in the ‎Islamic and conventional markets in Canada. It aims to investigate whether Islamic market ‎would be more or less efficient than the conventional one. Findings indicate that both ‎Conventional Canadian Stock Index (CCSI) and Dow Jones Islamic Canadian Price Index ‎‎(DJICPI) show characteristics of random walk indicating that the stock markets are efficient. ‎The major policy implications is that in this country (Canada), fund managers and investors ‎cannot enjoy excess returns to their investment. ‎
    Keywords: Dow Jones Islamic Market (DJIM); Conventional Canadian Stock Index, Efficient-Market ‎Hypothesis (EMH), linear and nonlinear unit root tests, KSS, Sollis, CHLL‎
    JEL: C12 C22 G10 G14 G15
    Date: 2020–09–28
  17. By: neifar, malika
    Abstract: In this paper we test the weak form of the Efficient-Market Hypothesis (EMH) using monthly ‎data of stock prices for the period from 2010M01 to 2019M07 for seven markets (Tunindex) ‎in Tunisia and 6 Asian countries : Saudi Arabia (TSAI), Japon (Nikkei 225), China (SSEC), ‎Turkey (BIST100), India (BSE30), and Indonesia (JKSE) by using linear and nonlinear (KSS ‎and Modified KSS) unit root tests. Our empirical results indicate that the stock markets are ‎efficient [not efficient] in the weak form of EMH in Tunisia and Saudi Arabia [Japan, ‎Turkey, India, Indonesia, and China]. The major policy implications is that in these five ‎countries (Japan, Turkey, India, Indonesia, and China), fund managers and investors can ‎enjoy excess returns to their investment. ‎
    Keywords: Efficient-Market Hypothesis (EMH); BDS test; Linear Unit root test; Nonlinear Unit root test, ‎Tunisia and 6 Asian countries
    JEL: C12 C22 G10 G14
    Date: 2020–09–30
  18. By: Musaeva, Gulzhan; Masih, Mansur
    Abstract: The connection between oil price fluctuations and stock markets has gained much attention in the recent decades due to the critical importance of global oil prices. This paper aims to study the Granger-causal relationship between real prices of the Islamic stock market and real oil prices – a novel study, to the best of our knowledge. Malaysia is chosen as a case study. Using the standard time series techniques, we have discovered that Islamic stock prices and oil prices are both more or less independently leading; that is, neither of them drives the other to a large extent. These results are explained in part by Malaysia’s prevaling oil price subsidies. We thus conclude that, in all similar scenarios, investors should not use real oil price changes as a predictor of subsequent changes in the Islamic stock market, seeing that the latter seems to be strongly resilient to oil price fluctuations. The policymakers, in turn, could experiment by monitoring Islamic stock prices more closely to gauge the performance of the economy, in order to take any further action (if necessary) for affecting economic variables (through either stabilization or supply-side policies).
    Keywords: Islamic stock market, oil prices, Granger causality, Malaysia
    JEL: C22 C58 G15
    Date: 2018–10–31

This nep-fmk issue is ©2020 by Kwang Soo Cheong. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.