nep-fmk New Economics Papers
on Financial Markets
Issue of 2021‒02‒22
fifteen papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Stock marketsas a network: from description to inference By Marcello Esposito
  2. When it Rains, it Pours: Multifactor Asset Management in Good and Bad Times By Marie Briere; Ariane Szafarz
  3. Multi-Horizon Equity Returns Predictability via Machine Learning By Lenka Nechvatalova
  4. Deep Reinforcement Learning for Portfolio Optimization using Latent Feature State Space (LFSS) Module By Kumar Yashaswi
  5. Deep Learning for Market by Order Data By Zihao Zhang; Bryan Lim; Stefan Zohren
  6. Detecting and Quantifying Wash Trading on Decentralized Cryptocurrency Exchanges By Friedhelm Victor; Andrea Marie Weintraud
  7. Power-Law Return-Volatility Cross Correlations of Bitcoin By T. Takaishi
  8. Stealth Trading in FX Markets By Alexis Stenfor; Masayuki Susai
  9. Hedging of Financial Derivative Contracts via Monte Carlo Tree Search By Oleg Szehr
  10. Stock Market Returns and Oil Price Shocks: A CoVaR Analysis based on Dynamic Vine Copula Models By Julia Kielmann; Hans Manner; Aleksey Min
  11. Spillover Effects of the European Central Bank's Expanded Asset Purchase Program to Non-eurozone Countries in Central and Eastern Europe By Lorant Kaszab; Mark Antal
  12. Does diversification protect European banks' market valuation in a pandemic? By Mathieu Simoens; Rudi Vander Vennet
  13. Financial Vulnerability and Volatility in Emerging Stock Markets: Evidence from GARCH-MIDAS Models By Riza Demirer; Rangan Gupta; He Li; Yu You
  14. The Impact of the Bank of Japan’s Exchange Traded Fund and Corporate Bond Purchases on Firms’ Capital Structure By Linh, Nguyen Thuy
  15. The Impact of Oil Price Shocks on Turkish Sovereign Yield Curve By Oguzhan Cepni; Selcuk Gul; Muhammed Hasan Yilmaz; Brian Lucey

  1. By: Marcello Esposito
    Abstract: Among the statistical techniques used to describe the behaviour of the financial markets, one of the most promising is based on the network analysis of the stock market. In this framework, the stock market is represented as a graph with nodes (the single stocks), edges (connections between stocks), and attributes (industry classification, volumes ...). The application of network analysis to the stock market is not new, but in previous contributions the market graph has been mainly derived from the correlationmatrix of the stock prices. This is a limitation, and the risks are to express in different words what traditional financial econometrics has already said about the returns’ distribution. Moreover, if we want to use network analysis not only as a descriptive tool but also as an inference instrument, we need other data than the correlation matrix itself. For this reason, we integrated the analysis and built the market graph with new type of data taken from the observation of the information gathering activity performed by retail investors through the Google’s search engine. We focussed the attention on financial crises, when a shock hits the economy in such a profound way that almost all the parameters entering the pricing equation of stocks must be reassessed. Those periods are relatively rare and short. They are characterised by extremely high levels of volatility and correlation. In these moments, searching for new information becomes of paramount importance. And then it is in these moments that we expect to observe more neatly the working of the underlying network.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:liu:liucec:2021-10&r=all
  2. By: Marie Briere; Ariane Szafarz
    Abstract: We examine the profitability of multifactor portfolios on the U.S. stock market. Using passive sector investing as the benchmark, we assess the performances of factor-based asset management strategies in good and bad times. When short selling is unrestricted, factor investing outperforms sector investing in all respects. For long-only portfolios, our results reveal a trade-off between the risk premia associated with factors and the diversification potential of sectors. Multifactor investing tends to be more profitable than the benchmark during good times but less attractive during bad times, when diversification is needed the most.
    Keywords: Portfolio management; asset allocation; factor; industry; sector; crisis
    JEL: G11 C61 E44 G01
    Date: 2021–02–10
    URL: http://d.repec.org/n?u=RePEc:sol:wpaper:2013/319463&r=all
  3. By: Lenka Nechvatalova (Institute of Economic Studies, Charles University and Institute of Information Theory and Automation, Czech Academy of Sciences Prague, Czech Republic)
    Abstract: We examine the predictability of expected stock returns across horizons using machine learning. We use neural networks, and gradient boosted regression trees on the U.S. and international equity datasets. We find that predictability of returns using neural networks models decreases with longer forecasting horizon. We also document the profitability of long-short portfolios, which were created using predictions of cumulative returns at various horizons, before and after accounting for transaction costs. There is a trade-off between higher transaction costs connected to frequent rebalancing and greater returns on shorter horizons. However, we show that increasing the forecasting horizon while matching the rebalancing period increases risk-adjusted returns after transaction cost for the U.S. We combine predictions of expected returns at multiple horizons using double-sorting and buy/hold spread, a turnover reducing strategy. Using double sorts significantly increases profitability on the U.S. sample. Buy/hold spread portfolios have better risk-adjusted profitability in the U.S.
    Keywords: Machine learning, asset pricing, horizon predictability, anomalies
    JEL: G11 G12 G15 C55
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:fau:wpaper:wp2021_02&r=all
  4. By: Kumar Yashaswi
    Abstract: Dynamic Portfolio optimization is the process of distribution and rebalancing of a fund into different financial assets such as stocks, cryptocurrencies, etc, in consecutive trading periods to maximize accumulated profits or minimize risks over a time horizon. This field saw huge developments in recent years, because of the increased computational power and increased research in sequential decision making through control theory. Recently Reinforcement Learning(RL) has been an important tool in the development of sequential and dynamic portfolio optimization theory. In this paper, we design a Deep Reinforcement Learning(DRL) framework as an autonomous portfolio optimization agent consisting of a Latent Feature State Space(LFSS) Module for filtering and feature extraction of financial data which is used as a state space for deep RL model. We develop an extensive RL agent with high efficiency and performance advantages over several benchmarks and model-free RL agents used in prior work. The noisy and non-stationary behaviour of daily asset prices in the financial market is addressed through Kalman Filter. Autoencoders, ZoomSVD, and restricted Boltzmann machines were the models used and compared in the module to extract relevant time series features as state space. We simulate weekly data, with practical constraints and transaction costs, on a portfolio of S&P 500 stocks. We introduce a new benchmark based on technical indicator Kd-Index and Mean-Variance Model as compared to equal weighted portfolio used in most of the prior work. The study confirms that the proposed RL portfolio agent with state space function in the form of LFSS module gives robust results with an attractive performance profile over baseline RL agents and given benchmarks.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2102.06233&r=all
  5. By: Zihao Zhang; Bryan Lim; Stefan Zohren
    Abstract: Market by order (MBO) data - a detailed feed of individual trade instructions for a given stock on an exchange - is arguably one of the most granular sources of microstructure information. While limit order books (LOBs) are implicitly derived from it, MBO data is largely neglected by current academic literature which focuses primarily on LOB modelling. In this paper, we demonstrate the utility of MBO data for forecasting high-frequency price movements, providing an orthogonal source of information to LOB snapshots. We provide the first predictive analysis on MBO data by carefully introducing the data structure and presenting a specific normalisation scheme to consider level information in order books and to allow model training with multiple instruments. Through forecasting experiments using deep neural networks, we show that while MBO-driven and LOB-driven models individually provide similar performance, ensembles of the two can lead to improvements in forecasting accuracy -- indicating that MBO data is additive to LOB-based features.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2102.08811&r=all
  6. By: Friedhelm Victor; Andrea Marie Weintraud
    Abstract: Cryptoassets such as cryptocurrencies and tokens are increasingly traded on decentralized exchanges. The advantage for users is that the funds are not in custody of a centralized external entity. However, these exchanges are prone to manipulative behavior. In this paper, we illustrate how wash trading activity can be identified on two of the first popular limit order book-based decentralized exchanges on the Ethereum blockchain, IDEX and EtherDelta. We identify a lower bound of accounts and trading structures that meet the legal definitions of wash trading, discovering that they are responsible for a wash trading volume in equivalent of 159 million U.S. Dollars. While self-trades and two-account structures are predominant, complex forms also occur. We quantify these activities, finding that on both exchanges, more than 30\% of all traded tokens have been subject to wash trading activity. On EtherDelta, 10% of the tokens have almost exclusively been wash traded. All data is made available for future research. Our findings underpin the need for countermeasures that are applicable in decentralized systems.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2102.07001&r=all
  7. By: T. Takaishi
    Abstract: This paper investigates the return-volatility asymmetry of Bitcoin. We find that the cross correlations between return and volatility (squared return) are mostly insignificant on a daily level. In the high-frequency region, we find thata power-law appears in negative cross correlation between returns and future volatilities, which suggests that the cross correlation is \revision{long ranged}. We also calculate a cross correlation between returns and the power of absolute returns, and we find that the strength of \revision{the cross correlations} depends on the value of the power.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2102.08187&r=all
  8. By: Alexis Stenfor (University of Portsmouth); Masayuki Susai (Nagasaki University)
    Abstract: We investigate if and how other traders react to algorithmic order-splitting tactics. Studying over 1.4 million limit orders in the EUR/USD foreign exchange (FX) spot market, we find that stealth-trading strategies adopted by algorithmic traders seem to go detected and are perceived as more market-moving than orders of the corresponding size typically submitted by human traders. We also document that algorithmic traders appear to be more sensitive to limit orders submitted from the opposite side (free-option risk) than to the same side of the order book (non-execution risk). Once human traders have had time to react, however, the pattern reverses.
    Keywords: algorithmic trading, foreign exchange, limit order book, market microstructure, order splitting, stealth trading
    JEL: D4 F3
    Date: 2021–02–12
    URL: http://d.repec.org/n?u=RePEc:pbs:ecofin:2021-02&r=all
  9. By: Oleg Szehr
    Abstract: The construction of approximate replication strategies for derivative contracts in incomplete markets is a key problem of financial engineering. Recently Reinforcement Learning algorithms for pricing and hedging under realistic market conditions have attracted significant interest. While financial research mostly focused on variations of $Q$-learning, in Artificial Intelligence Monte Carlo Tree Search is the recognized state-of-the-art method for various planning problems, such as the games of Hex, Chess, Go,... This article introduces Monte Carlo Tree Search for the hedging of financial derivatives in realistic markets and shows that there are good reasons, both on the theoretical and practical side, to favor it over other Reinforcement Learning methods.
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2102.06274&r=all
  10. By: Julia Kielmann (Technical University of Munich, Germany); Hans Manner (University of Graz, Austria); Aleksey Min (Technical University of Munich, Germany)
    Abstract: Crude oil plays a significant role in economic developments in the world. Understanding the relationship between oil price changes and stock market returns helps to improve portfolio strategies and risk positions. Kilian (2009) proposes to decompose the oil price into three types of oil price shocks by using a structural vector autoregression (SVAR) model. This paper investigates the dynamic, non-linear dependence and risk spillover effects between BRICS stock returns and the different types of oil price shocks using an appropriate multivariate and dynamic copula model. Risk is measured using the conditional Value-at-Risk, conditioning on one or more simultaneous oil and stock market shocks. For this purpose, a D-vine based quantile regression model and the GAS copula model are combined. Our results show, inter alia, that the early stages of the Covid-19 crisis leads to increasing risk levels in the BRICS stock markets except for the Chinese one, which has recovered quickly and therefore shows no changes in the risk level.
    Keywords: Oil prices; risk management; time-varying copula; D-vine copula; CoVaR.
    JEL: C12 C32 C52 C53
    Date: 2021–01
    URL: http://d.repec.org/n?u=RePEc:grz:wpaper:2021-01&r=all
  11. By: Lorant Kaszab (Magyar Nemzeti Bank (Central Bank of Hungary)); Mark Antal (European Central Bank)
    Abstract: For a panel of six Central and Eastern European countries outside the eurozone (Bulgaria, Croatia, Czechia, Hungary, Poland and Romania) we estimate the spillover effects of the European Central Bank's Expanded Asset Purchase Program (APP) on exchange rates, equity prices, government bond yields of various maturities, and CDS spreads. We find that the most pronounced spillovers induced sovereign bond yields to drop by around 1-6 basis points in a two-day time window in response to the Public Sector Purchase Program (PSPP) announcements.
    Keywords: ordinary least squares estimation, panel data, unconventional monetary policy
    JEL: E51 E32 E44 F45 F47
    Date: 2021
    URL: http://d.repec.org/n?u=RePEc:mnb:opaper:2021/140&r=all
  12. By: Mathieu Simoens; Rudi Vander Vennet (-)
    Abstract: We use the Covid-19 pandemic to assess whether diversification in various dimensions can protect European banks from substantial negative valuation shocks. Our results demonstrate that functional diversification acts as an economically significant shock absorber: it mitigates banks' stock market decline by approximately 10 percentage points. Loan portfolio diversification also contributes to dampening the valuation shock, but with a much lower impact (4.4 percentage points). Geographical diversification fails to act as a shock absorber. Banks with lower pre-Covid systematic risk, higher liquidity buyers, higher cost eficiency and active in countries with better post-Covid growth prospects weathered the storm better.
    Keywords: European banks, Covid-19, valuation, functional diversification, geographical diversification
    JEL: G21 G28 G01
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:rug:rugwps:21/1009&r=all
  13. By: Riza Demirer (Department of Economics & Finance, Southern Illinois University Edwardsville, Alumni Hall 3145, Edwardsville IL, 62026-1102, USA); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield, 0028, South Africa); He Li (School of International Economics and Politics, Liaoning University, Shenyang, Liaoning, China); Yu You (Li Anmin Advanced Institute of Finance and Economics, Liaoning University, Shenyang, Liaoning, China)
    Abstract: This paper establishes a predictive relationship between financial vulnerability and volatility in emerging stock markets. Focusing on China and India and utilizing GARCH-MIDAS models, we show that incorporating financial vulnerability can substantially improve the forecasting power of standard macroeconomic fundamentals (output growth, inflation and monetary policy interest rate) for stock market volatility. The findings have significant implications for investors to improve the accuracy of volatility forecasts.
    Keywords: Stock Market Volatility, Financial Vulnerability, GARCH-MIDAS, Emerging Markets
    JEL: C32 C53 G15 G17
    Date: 2021–02
    URL: http://d.repec.org/n?u=RePEc:pre:wpaper:202112&r=all
  14. By: Linh, Nguyen Thuy
    Abstract: This study examines the effects of the Bank of Japan’s (BOJ’s) exchange traded fund (ETF) and corporate bond (CB) purchases on the capital structure of Japanese listed firms. The results suggest that following the expansion of ETF purchases, treatment firms actively issued more stocks and became less dependent on bond debt and bank loans than control firms, resulting in a lower level of leverage. In contrast, following the introduction of CB purchases, firms whose bonds were eligible for CB purchases issued more corporate bonds, while reducing long-term bank debt by a smaller extent, thus they have a higher leverage ratio than ineligible firms. Moreover, evidence further suggests the existence of an interaction between these two purchasing programs. These results indicate that the BOJ’s ETF and CB purchases have had a considerable impact, implying that the supply of capital plays an important role in determining firms’ capital structure.
    Keywords: Unconventional monetary policy, Risk asset purchases, Difference in differences, Capital structure, Supply-side effects
    JEL: E52 E58 G32
    Date: 2021–01
    URL: http://d.repec.org/n?u=RePEc:hit:rcesrs:dp21-1&r=all
  15. By: Oguzhan Cepni; Selcuk Gul; Muhammed Hasan Yilmaz; Brian Lucey
    Abstract: This paper investigates the impact of oil price shocks on Turkish sovereign yield curve factors. The recent oil shock identification scheme of Ready (2018) is modified by using geopolitical oil price risk index in order to capture the changes in the risk perceptions of oil markets driven by geopolitical tensions such as terrorism, conflicts and sanctions. The modified identification scheme attributes more power to demand shocks in explaining the variation of the oil price. Furthermore, our findings demonstrate that the various oil price shocks influence the yield curve factors quite differently. A supply shock leads to a statistically significant increase in the level factor. This result shows that elevated oil prices due to supply disruptions are interpreted as a signal of surge in inflation expectations since the cost channel prevails. Moreover, unanticipated demand shocks have a positive impact on the slope factor as a result of the central bank policy response for offsetting the elevated inflation expectations. Overall, our results provide new insights to understand the driven forces of yield curve movements that are induced by various oil shocks in order to formulate appropriate policy responses.
    Keywords: Emerging markets, Local projections, Oil price, Supply and demand shocks, Yield curve factors, Geopolitical oil price risks
    JEL: E43 E44 G12 G15 Q43
    Date: 2021
    URL: http://d.repec.org/n?u=RePEc:tcb:wpaper:2104&r=all

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 http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. 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.