nep-fmk New Economics Papers
on Financial Markets
Issue of 2021‒12‒06
eight papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. ESG Screening in the Fixed-Income Universe By Fabio Alessandrini; David Baptista Balula; Eric Jondeau
  2. Herding and Anti-Herding Across ESG Funds By Rocco Ciciretti; Ambrogio Dalò; Giovanni Ferri
  3. The Price of Money: How Collateral Policy Affects the Yield Curve By Kjell G. Nyborg; Jiri Woschitz
  4. Forecasting the Variability of Stock Index Returns with the Multifractal Random Walk Model for Realized Volatilities By Sattarhoff, Cristina; Lux, Thomas
  5. Stock Portfolio Optimization Using a Deep Learning LSTM Model By Jaydip Sen; Abhishek Dutta; Sidra Mehtab
  6. Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach By Mao Guan; Xiao-Yang Liu
  8. Analysis of Sectoral Profitability of the Indian Stock Market Using an LSTM Regression Model By Jaydip Sen; Saikat Mondal; Sidra Mehtab

  1. By: Fabio Alessandrini (University of Lausanne; Banque Cantonale Vaudoise); David Baptista Balula (University of Lausanne); Eric Jondeau (University of Lausanne - Faculty of Business and Economics (HEC Lausanne); affiliation not provided to SSRN; Swiss Finance Institute)
    Abstract: This paper evaluates the impact of a screening process based on Environment, Social, and Governance (ESG) scores for an otherwise passive portfolio of investment-grade corporate bonds. The main result is that this filtering leads to a substantial improvement of the targeted ESG score without reducing the risk-adjusted performance but with significant biases in regional, sectoral, and risk factor exposures. We find that screening is very often associated with a substantial improvement in the risk profile. In particular, ESG-tilted portfolios lead to large negative exposure (i.e., protection) to credit risk. Screening based on the Environment score is where most of the reduction in risk takes place, making this criterion particularly relevant in moving the portfolio toward a more defensive composition. We demonstrate that screening at the regional and sectoral levels allows investors to eliminate undesirable regional and sectoral exposures while delivering similar ESG scores and risk-adjusted performances.
    Keywords: Corporate bonds, ESG investing, Portfolio construction, Bond risk factors
    JEL: G11 G24 M14 Q01
    Date: 2021–11
  2. By: Rocco Ciciretti (DEF and CEIS, Università di Roma "Tor Vergata"); Ambrogio Dalò (University of Groningen); Giovanni Ferri (LUMSA University)
    Abstract: We investigate to what extent ESG funds present an herding/anti-herding behavior, and the consequences of their investment strategies in terms of both systematic risk exposure and risk-adjusted returns. Our findings document that ESG funds pursue an anti-herding strategy that leads to higher risk-adjusted returns. Specifically, a one standard deviation increase in ESG score at the fund-level is associated with an increase in fund performance of about 3.74 basis points per year. Moreover, we document that such an enhanced performance does not come at the cost of higher systematic risk exposure but instead reduces it. A possible explanation behind our findings is that after the catching-up phase previously documented by the literature, ESG funds are now able to put to good use enhanced stock-picking skills built over the years.
    Keywords: ESG investing, Equity Funds, Herding, Anti-Herding, Risk-Adjusted Returns
    JEL: G11 C58
    Date: 2021–11–05
  3. By: Kjell G. Nyborg (University of Zurich - Department of Banking and Finance; Centre for Economic Policy Research (CEPR); Swiss Finance Institute); Jiri Woschitz (University of Zurich)
    Abstract: Central-bank collateral policy governs the convertibility of assets into central-bank money provided directly by the central bank. Focusing on government bonds, we develop clean identification of variation in such convertibility by exploiting differential treatment of same-country government bonds in the euro area. Combining difference-in-differences analysis with yield-curve modeling on four separate events, we show that reduced convertibility lifts yields, but with the effect tapering off at longer maturities. Our findings imply that central-bank money is priced in the market and that a central bank can move and shape the yield curve through collateral policy.
    Keywords: Yield curve, central bank, collateral policy, monetary policy, haircuts, repo, asset prices, liquidity, central-bank money, government bonds
    JEL: G12 E43 E52
    Date: 2021–11
  4. By: Sattarhoff, Cristina; Lux, Thomas
    Abstract: We adapt the multifractal random walk model by Bacry et al. (2001) to realized volatilities (denoted RV-MRW) and take stock of recent theoretical insights on this model in Duchon et al. (2012) to derive forecasts of financial volatility. Moreover, we propose a new extension of the binomial Markov-switching multifractal (BMSM) model by Calvet and Fisher (2001) to the RV framework. We compare the predictive ability of the two against seven classical and multifractal volatility models. Forecasting performance is evaluated out-of-sample based on the empirical MSE and MAE as well as using model confidence sets following the methodology of Hansen et al. (2011). Overall, our empirical study for 14 international stock market indices has a clear message: The RV-MRW is throughout the best model for all forecast horizons under the MAE criterium as well as for large forecast horizons h=50 and 100 days under the MSE criterion. Moreover, the RV-MRW provides most accurate 20-day ahead forecasts in terms of MSE for the great majority of indices, followed by RV-ARFIMA, the latter dominating the competition at the 5-day-horizon. These results are very promising if we consider that this is the first empirical application of the RV-MRW. Moreover, whereas RV-ARFIMA forecasts are often a time consuming task, the RV-MRW stands out due to its fast execution and straightforward implementation. The new RV-BMSM appears to be specialized in short term forecasting, the model providing most accurate one-day ahead forecasts in terms of MSE for the same number of cases as RV-ARFIMA.
    Keywords: Realized volatility,multiplicative volatility models,multifractal random walk,longmemory,international volatility forecasting
    JEL: C20 G12
    Date: 2021
  5. By: Jaydip Sen; Abhishek Dutta; Sidra Mehtab
    Abstract: Predicting future stock prices and their movement patterns is a complex problem. Hence, building a portfolio of capital assets using the predicted prices to achieve the optimization between its return and risk is an even more difficult task. This work has carried out an analysis of the time series of the historical prices of the top five stocks from the nine different sectors of the Indian stock market from January 1, 2016, to December 31, 2020. Optimum portfolios are built for each of these sectors. For predicting future stock prices, a long-and-short-term memory (LSTM) model is also designed and fine-tuned. After five months of the portfolio construction, the actual and the predicted returns and risks of each portfolio are computed. The predicted and the actual returns of each portfolio are found to be high, indicating the high precision of the LSTM model.
    Date: 2021–11
  6. By: Mao Guan; Xiao-Yang Liu
    Abstract: Deep reinforcement learning (DRL) has been widely studied in the portfolio management task. However, it is challenging to understand a DRL-based trading strategy because of the black-box nature of deep neural networks. In this paper, we propose an empirical approach to explain the strategies of DRL agents for the portfolio management task. First, we use a linear model in hindsight as the reference model, which finds the best portfolio weights by assuming knowing actual stock returns in foresight. In particular, we use the coefficients of a linear model in hindsight as the reference feature weights. Secondly, for DRL agents, we use integrated gradients to define the feature weights, which are the coefficients between reward and features under a linear regression model. Thirdly, we study the prediction power in two cases, single-step prediction and multi-step prediction. In particular, we quantify the prediction power by calculating the linear correlations between the feature weights of a DRL agent and the reference feature weights, and similarly for machine learning methods. Finally, we evaluate a portfolio management task on Dow Jones 30 constituent stocks during 01/01/2009 to 09/01/2021. Our approach empirically reveals that a DRL agent exhibits a stronger multi-step prediction power than machine learning methods.
    Date: 2021–11
  7. By: Anders Nõu; Darya Lapitskaya; Mustafa Hakan Eratalay; Rajesh Sharma
    Abstract: For stock market predictions, the essence of the problem is usually predicting the magnitude and direction of the stock price movement as accurately as possible. There are different approaches (e.g., econometrics and machine learning) for predicting stock returns. However, it is non-trivial to find an approach which works the best. In this paper, we make a thorough analysis of the predictive accuracy of different machine learning and econometric approaches for predicting the returns and volatilities on the OMX Baltic Benchmark price index, which is a relatively less researched stock market. Our results show that the machine learning methods, namely the support vector regression and k-nearest neighbours, predict the returns better than autoregressive moving average models for most of the metrics, while for the other approaches, the results were not conclusive. Our analysis also highlighted that training and testing sample size plays an important role on the outcome of machine learning approaches.
    Keywords: machine learning, neural networks, autoregressive moving average, generalized autore- gressive conditional heteroskedasticity
    Date: 2021
  8. By: Jaydip Sen; Saikat Mondal; Sidra Mehtab
    Abstract: Predictive model design for accurately predicting future stock prices has always been considered an interesting and challenging research problem. The task becomes complex due to the volatile and stochastic nature of the stock prices in the real world which is affected by numerous controllable and uncontrollable variables. This paper presents an optimized predictive model built on long-and-short-term memory (LSTM) architecture for automatically extracting past stock prices from the web over a specified time interval and predicting their future prices for a specified forecast horizon, and forecasts the future stock prices. The model is deployed for making buy and sell transactions based on its predicted results for 70 important stocks from seven different sectors listed in the National Stock Exchange (NSE) of India. The profitability of each sector is derived based on the total profit yielded by the stocks in that sector over a period from Jan 1, 2010 to Aug 26, 2021. The sectors are compared based on their profitability values. The prediction accuracy of the model is also evaluated for each sector. The results indicate that the model is highly accurate in predicting future stock prices.
    Date: 2021–11

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.