nep-fmk New Economics Papers
on Financial Markets
Issue of 2021‒04‒05
fourteen papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Rising Stocks during Lockdown Economic Recessions: Explaining the Phenomenon By Vasconcelos Costa, André
  2. What cured the TSX Equity index after COVID-19? By Guillaume Ouellet Leblanc; Jean-Sébastien Fontaine; Ryan Shotlander
  3. Modeling of crisis periods in stock markets By Apostolos Chalkis; Emmanouil Christoforou; Theodore Dalamagkas; Ioannis Z. Emiris
  4. Text Mining of Stocktwits Data for Predicting Stock Prices By Mukul Jaggi; Priyanka Mandal; Shreya Narang; Usman Naseem; Matloob Khushi
  5. Can Machine Learning Help to Select Portfolios of Mutual Funds? By Victor DeMiguel; Javier Gil-Bazo; Francisco J. Nogales; André A. P. Santos
  6. A Deep Deterministic Policy Gradient-based Strategy for Stocks Portfolio Management By Huanming Zhang; Zhengyong Jiang; Jionglong Su
  7. Portfolio Optimization with Sparse Multivariate Modelling By Pier Francesco Procacci; Tomaso Aste
  8. Revisiting the Expected Utility Theory and the Consumption CAPM By Sapre, Nikhil
  9. Deep Hedging of Derivatives Using Reinforcement Learning By Jay Cao; Jacky Chen; John Hull; Zissis Poulos
  10. Machine Learning and Central Banks: Ready for Prime Time? By Hans Genberg; Özer Karagedikli
  11. Asymmetric Information and Corporate Lending: Evidence from SMEs Bond Markets By Alessandra Iannamorelli; Stefano Nobili; Antonio Scalia; Luana Zaccaria
  12. Valuing Exotic Options and Estimating Model Risk By Jay Cao; Jacky Chen; John Hull; Zissis Poulos
  13. Suisse stock return, Macro Factors, and Efficient Market ‎Hypothesis: evidence from ARDL model By NEIFAR, MALIKA
  14. Multivariate Causality between Stock price index and Macro variables: ‎evidence from Canadian stock market By NEIFAR, MALIKA

  1. By: Vasconcelos Costa, André
    Abstract: Whilst facing an economic recession, stock prices have been rising consistently since late March of 2020, which has been viewed by many as paradoxical and has led some to consider that the stock market does not represent the real economy. The aim of this paper is to offer a simple, coherent explanation which is capable of showing why this is actually a phenomenon to be expected during the implementation of lockdown measures. The theoretical tool through which this is accomplished is the Life Cycle/Permanent Income Hypothesis and its consumption smoothing implications. I show that the exceptional inability to smooth consumption under current circumstances has been the cause of unprecedented increases in savings which find the stock market as one of their natural destinations.
    Keywords: Stocks, Consumption Smoothing, Permanent Income, COVID-19, Lockdown, Recession.
    JEL: E21 E3 G1
    Date: 2021–03–18
  2. By: Guillaume Ouellet Leblanc; Jean-Sébastien Fontaine; Ryan Shotlander
    Abstract: The TSX index rose by 9.5 percent in November 2020, adding large gains to an already sharp V-shaped recovery. The economic outlook improved at that time as well. We ask whether the stock market gains since last autumn are due to improving forecasts of firms’ earnings.
    Keywords: Asset pricing; Coronavirus disease (COVID-19); Financial markets
    JEL: G12 G14
    Date: 2021–03
  3. By: Apostolos Chalkis; Emmanouil Christoforou; Theodore Dalamagkas; Ioannis Z. Emiris
    Abstract: We exploit a recent computational framework to model and detect financial crises in stock markets, as well as shock events in cryptocurrency markets, which are characterized by a sudden or severe drop in prices. Our method manages to detect all past crises in the French industrial stock market starting with the crash of 1929, including financial crises after 1990 (e.g. dot-com bubble burst of 2000, stock market downturn of 2002), and all past crashes in the cryptocurrency market, namely in 2018, and also in 2020 due to covid-19. We leverage copulae clustering, based on the distance between probability distributions, in order to validate the reliability of the framework; we show that clusters contain copulae from similar market states such as normal states, or crises. Moreover, we propose a novel regression model that can detect successfully all past events using less than 10% of the information that the previous framework requires. We train our model by historical data on the industry assets, and we are able to detect all past shock events in the cryptocurrency market. Our tools provide the essential components of our software framework that offers fast and reliable detection, or even prediction, of shock events in stock and cryptocurrency markets of hundreds of assets.
    Date: 2021–03
  4. By: Mukul Jaggi; Priyanka Mandal; Shreya Narang; Usman Naseem; Matloob Khushi
    Abstract: Stock price prediction can be made more efficient by considering the price fluctuations and understanding the sentiments of people. A limited number of models understand financial jargon or have labelled datasets concerning stock price change. To overcome this challenge, we introduced FinALBERT, an ALBERT based model trained to handle financial domain text classification tasks by labelling Stocktwits text data based on stock price change. We collected Stocktwits data for over ten years for 25 different companies, including the major five FAANG (Facebook, Amazon, Apple, Netflix, Google). These datasets were labelled with three labelling techniques based on stock price changes. Our proposed model FinALBERT is fine-tuned with these labels to achieve optimal results. We experimented with the labelled dataset by training it on traditional machine learning, BERT, and FinBERT models, which helped us understand how these labels behaved with different model architectures. Our labelling method competitive advantage is that it can help analyse the historical data effectively, and the mathematical function can be easily customised to predict stock movement.
    Date: 2021–03
  5. By: Victor DeMiguel; Javier Gil-Bazo; Francisco J. Nogales; André A. P. Santos
    Abstract: Identifying outperforming mutual funds ex-ante is a notoriously difficult task. We use machine learning methods to exploit the predictive ability of a large set of mutual fund characteristics that are readily available to investors. Using data on US equity funds in the 1980-2018 period, the methods allow us to construct portfolios of funds that earn positive and significant out-of-sample risk-adjusted after-fee returns as high as 4.2% per year. We further show that such outstanding performance is the joint outcome of both exploiting the information contained in multiple fund characteristics and allowing for flexibility in the relationship between predictors and fund performance. Our results confirm that even retail investors can benefit from investing in actively managed funds. However, we also find that the performance of all our portfolios has declined over time, consistent with increased competition in the asset market and diseconomies of scale at the industry level.
    Keywords: mutual fund performance, performance predictability, active management, machine learning, elastic net, random forests, gradient boosting
    Date: 2021–03
  6. By: Huanming Zhang; Zhengyong Jiang; Jionglong Su
    Abstract: With the improvement of computer performance and the development of GPU-accelerated technology, trading with machine learning algorithms has attracted the attention of many researchers and practitioners. In this research, we propose a novel portfolio management strategy based on the framework of Deep Deterministic Policy Gradient, a policy-based reinforcement learning framework, and compare its performance to that of other trading strategies. In our framework, two Long Short-Term Memory neural networks and two fully connected neural networks are constructed. We also investigate the performance of our strategy with and without transaction costs. Experimentally, we choose eight US stocks consisting of four low-volatility stocks and four high-volatility stocks. We compare the compound annual return rate of our strategy against seven other strategies, e.g., Uniform Buy and Hold, Exponential Gradient and Universal Portfolios. In our case, the compound annual return rate is 14.12%, outperforming all other strategies. Furthermore, in terms of Sharpe Ratio (0.5988), our strategy is nearly 33% higher than that of the second-best performing strategy.
    Date: 2021–03
  7. By: Pier Francesco Procacci; Tomaso Aste
    Abstract: Portfolio optimization approaches inevitably rely on multivariate modeling of markets and the economy. In this paper, we address three sources of error related to the modeling of these complex systems: 1. oversimplifying hypothesis; 2. uncertainties resulting from parameters' sampling error; 3. intrinsic non-stationarity of these systems. For what concerns point 1. we propose a L0-norm sparse elliptical modeling and show that sparsification is effective. The effects of points 2. and 3. are quantifified by studying the models' likelihood in- and out-of-sample for parameters estimated over train sets of different lengths. We show that models with larger off-sample likelihoods lead to better performing portfolios up to when two to three years of daily observations are included in the train set. For larger train sets, we found that portfolio performances deteriorate and detach from the models' likelihood, highlighting the role of non-stationarity. We further investigate this phenomenon by studying the out-of-sample likelihood of individual observations showing that the system changes significantly through time. Larger estimation windows lead to stable likelihood in the long run, but at the cost of lower likelihood in the short-term: the `optimal' fit in finance needs to be defined in terms of the holding period. Lastly, we show that sparse models outperform full-models in that they deliver higher out of sample likelihood, lower realized portfolio volatility and improved portfolios' stability, avoiding typical pitfalls of the Mean-Variance optimization.
    Date: 2021–03
  8. By: Sapre, Nikhil
    Abstract: The concept of utility is the core component of many foundational theories in social sciences. It has evolved from a philosophical belief that people seek happiness and satisfaction to a mathematically derived theory in economics and finance. Beginning with a brief review of the developments in the Expected Utility Theory (EUT) and its applicability in equity pricing, this paper includes a critical appraisal of relevant theoretical and empirical studies from the fields of financial economics and behavioural studies, with a particular focus on the the Consumption Capital Asset Pricing Model (CCAPM).
    Keywords: Expected Utility, Choice Behaviour, Equity Pricing, CCAPM
    JEL: G10 G11 G12
    Date: 2021–02–18
  9. By: Jay Cao; Jacky Chen; John Hull; Zissis Poulos
    Abstract: This paper shows how reinforcement learning can be used to derive optimal hedging strategies for derivatives when there are transaction costs. The paper illustrates the approach by showing the difference between using delta hedging and optimal hedging for a short position in a call option when the objective is to minimize a function equal to the mean hedging cost plus a constant times the standard deviation of the hedging cost. Two situations are considered. In the first, the asset price follows a geometric Brownian motion. In the second, the asset price follows a stochastic volatility process. The paper extends the basic reinforcement learning approach in a number of ways. First, it uses two different Q-functions so that both the expected value of the cost and the expected value of the square of the cost are tracked for different state/action combinations. This approach increases the range of objective functions that can be used. Second, it uses a learning algorithm that allows for continuous state and action space. Third, it compares the accounting P&L approach (where the hedged position is valued at each step) and the cash flow approach (where cash inflows and outflows are used). We find that a hybrid approach involving the use of an accounting P&L approach that incorporates a relatively simple valuation model works well. The valuation model does not have to correspond to the process assumed for the underlying asset price.
    Date: 2021–03
  10. By: Hans Genberg (Asia School of Business); Özer Karagedikli (South East Asian Central Banks (SEACEN) Research and Training Centre and Centre for Applied Macroeconomic Analysis (CAMA))
    Abstract: In this article we review what machine learning might have to offer central banks as an analytical approach to support monetary policy decisions. After describing the central bank’s “problem†and providing a brief introduction to machine learning, we propose to use the gradual adoption of Vector Auto Regression (VAR) methods in central banks to speculate how machine learning models must (will?) evolve to become influential analytical tools supporting central banks’ monetary policy decisions. We argue that VAR methods achieved that status only after they incorporated elements that allowed users to interpret them in terms of structural economic theories. We believe that the same has to be the case for machine learning model.
    Date: 2021–03
  11. By: Alessandra Iannamorelli (Bank of Italy); Stefano Nobili (Bank of Italy); Antonio Scalia (Bank of Italy); Luana Zaccaria (EIEF)
    Abstract: Using a comprehensive dataset of Italian SMEs, we find that differences between private and public information on firm creditworthiness affect the decision to issue traded debt securities. Specifically, holding public information constant, firms with better private fundamentals are more likely to access bond markets. Additionally, credit conditions improve for issuers following the bond placement, compared with a matched sample of non-issuers. Thus, our evidence supports 'positive' (rather than adverse) selection in corporate bond markets. This is consistent with a model where banks offer more flexibility than markets during financial distress and firms use market lending to signal credit quality to outside stakeholders.
    Date: 2021
  12. By: Jay Cao; Jacky Chen; John Hull; Zissis Poulos
    Abstract: A common approach to valuing exotic options involves choosing a model and then determining its parameters to fit the volatility surface as closely as possible. We refer to this as the model calibration approach (MCA). This paper considers an alternative approach where the points on the volatility surface are features input to a neural network. We refer to this as the volatility feature approach (VFA). We conduct experiments showing that VFA can be expected to outperform MCA for the volatility surfaces encountered in practice. Once the upfront computational time has been invested in developing the neural network, the valuation of exotic options using VFA is very fast. VFA is a useful tool for the estimation of model risk. We illustrate this using S&P 500 data for the 2001 to 2019 period.
    Date: 2021–03
    Abstract: This study investigates the short run and the long run equilibrium ‎relationship between Suisse stock market (SSM) prices and a set of ‎macroeconomic variables (inflation, interest rate, and exchange rate) using ‎Monthly data for the period 1999:1 to 2018:4. Different specifications and ‎tests will be carried out, namely unit root tests (ADF and PP), Vector Auto ‎Regression (VAR) to select the optimal lag length and for Granger causality ‎and Toda and Yamamoto (TY) Wald non causality testing, VEC Model and ‎‎(Johansen, 1988)’ test for no cointegration, and ARDL framework and FPSS ‎test of no cointegration hypothesis. ECM representation of the ARDL ‎model confirm temporal causality between (inflation, interest rate, exchange ‎rate) and the stock price. There is dynamic short run adjustment and long ‎run stable equilibrium relationship between macroeconomic variables ‎‎(except exchange rate) and stock prices in the SSM. This imply that the ‎SSM is informationally inefficient because publicly available information on ‎macroeconomic variables (inflation and interest rate) can be potentially used ‎in predicting Suisse stock prices.‎
    Keywords: Suisse Stock market efficiency; Macroeconomic variables; Causality; cointegration; ARDL ‎model‎
    JEL: C32 E44 G14
    Date: 2021–01–30
    Abstract: Currently, the investor considers monetary indicators a vital factor when ‎making any investment in equity prices. This research aim to find the long-‎run relationship between stock returns (DLSP) of Canada and monetary ‎indicators as the exchange rate (LEXC), the interest rate (LINT), and ‎inflation rate (INF). We consider T=232 observations for each variable from ‎January 1999 to April 2018. From the Johansen cointegration approaches, ‎there is no long-run association between stock prices and monetary ‎indicators. Results of the Granger causality tests have demonstrated the ‎unidirectional causation from the stock return to Inflation rate and to ‎Exchange rate growth. While Results of Toda and Yamamoto Wald tests ‎have demonstrated a bidirectional causal relation between stock price and ‎consumer price index and a unidirectional causation from stock price to the ‎interest rate and to the exchange rate growth. Based on IRFs, Inflation rate ‎is shown to be inversely related to stock returns. Thus, it is concluded that ‎the predictability of Canadian stock return relies only on the variations of ‎inflation rate.‎
    Keywords: Canadian stock price index; macroeconomic variables; Granger non causality; Johansen ‎cointegration; Toda and Yamamoto non causality wald test, Impulse–response functions ‎‎(IRFs).‎
    JEL: C32 E44 G14
    Date: 2021–01–30

This nep-fmk issue is ©2021 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.