nep-fmk New Economics Papers
on Financial Markets
Issue of 2022‒11‒07
twelve papers chosen by

  1. Do consumption-based asset pricing models explain own-history predictability in stock market returns? By Ashby, M.; Linton, O. B.
  2. Determinants of Stock Market Correlation. Accounting for Model Uncertainty and Reverse Causality in a Large Panel Setting By António Afonso; Krzysztof Beck; Karen Jackson
  3. Multiclass Sentiment Prediction for Stock Trading By Marshall R. McCraw
  4. Inattentive Price Discovery in ETFs By Mariia Kosar; Sergei Mikhalishchev
  5. It’s not time to make a change: sovereign fragility and the corporate credit risk By Fornari, Fabio; Zaghini, Andrea
  6. Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning By Naseh Majidi; Mahdi Shamsi; Farokh Marvasti
  7. Stock Volatility Prediction using Time Series and Deep Learning Approach By Ananda Chatterjee; Hrisav Bhowmick; Jaydip Sen
  8. DNN-ForwardTesting: A New Trading Strategy Validation using Statistical Timeseries Analysis and Deep Neural Networks By Ivan Letteri; Giuseppe Della Penna; Giovanni De Gasperis; Abeer Dyoub
  9. MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization By Hui Niu; Siyuan Li; Jian Li
  10. Sudden Yield Reversals and Financial Intermediation in Emerging Markets By Miguel Sarmiento
  11. "Energy Firms in Emerging Markets: Systemic Risk and Diversification Opportunities". By Helena Chuliá; Jorge A. Muñoz-Mendoza; Jorge M. Uribe
  12. Decentralised finance and cryptocurrency activity in Africa By Ozili, Peterson K

  1. By: Ashby, M.; Linton, O. B.
    Abstract: We show that three prominent consumption-based asset pricing models - the Bansal-Yaron, Campbell-Cochrane and Cecchetti-Lam-Mark models - cannot explain the own-history predictability properties of stock market returns. We show this by estimating these models with GMM, deriving ex-ante expected returns from them and then testing whether the difference between realised and expected returns is a martingale difference sequence, which it is not. Furthermore, semi-parametric tests of whether the models' state variables are consistent with the degree of own-history predictability in stock returns suggest that only the Campbell-Cochrane habit variable may be able to explain return predictability, although the evidence on this is mixed.
    Keywords: consumption-based asset pricing models, martingale difference sequence, MIDAS, power spectrum, predictability, quantilogram, rescaled range, serial correlation, variance ratio
    JEL: C52 C58 G12
    Date: 2022–10–20
  2. By: António Afonso; Krzysztof Beck; Karen Jackson
    Abstract: We examine 22 determinants of stock market correlations in a panel setting with 651 country pairs of developed economies over the 2001-2018 period, while accounting for model uncertainty and reverse causality. On the one hand, we find, that a number of determinants, well established in the literature, e.g. trade, institutional distance, and exchange rate volatility fail the robustness test. On the other hand, we find strong evidence supporting several others: (1) inertia, with current correlation being the best single predictor of the future stock market correlation (2) positive impact of the market size (3) imperative role of the interconnected financial factors: capital mobility, financial development, and portfolio equity flows. With the expected future growth of economies and their capital markets as well as deepening financial liberalization, this paper brings strong support to the hypothesis of diminishing international diversification potential.
    Keywords: stock market correlations, stock market comovement, financial development, Bayesian model averaging, OECD countries
    JEL: G10 G11 G15 F62
    Date: 2022
  3. By: Marshall R. McCraw
    Abstract: Python was used to download and format NewsAPI article data relating to 400 publicly traded, low cap. Biotech companies. Crowd-sourcing was used to label a subset of this data to then train and evaluate a variety of models to classify the public sentiment of each company. The best performing models were then used to show that trading entirely off public sentiment could provide market beating returns.
    Date: 2022–09
  4. By: Mariia Kosar; Sergei Mikhalishchev
    Abstract: This paper studies the information choice of exchange-traded funds (ETF) investors, and its impact on the price efficiency of underlying stocks. First, we show that the learning of stock-specific information can occur at the ETF level. Our results suggest that ETF investors respond endogenously to changes in the fundamental value of underlying stocks, in line with the rational inattention theory. Second, we provide evidence that ETFs facilitate propagation of idiosyncratic shocks across its constituents.
    Keywords: Exchange-Traded Fund; ETF; Price Efficiency; Rational Inattention; Information Acquisition; Comovement;
    JEL: G12 G14 D82
    Date: 2022–09
  5. By: Fornari, Fabio; Zaghini, Andrea
    Abstract: Relying on a perspective borrowed from monetary policy announcements and introducing an econometric twist in the traditional event study analysis, we document the existence of an "event risk transfer", namely a significant credit risk transmission from the sovereign to the corporate sector after a sovereign rating downgrade. We find that after the delivery of the downgrade, corporate CDS spreads rise by 36% per annum and there is a widespread contagion across countries, in particular among those which were most exposed to the sovereign debt crisis. This effect exists on top of the standard relation between sovereign and corporate credit risk. JEL Classification: C21, G12, G14
    Keywords: credit default swaps, credit rating, sovereign risk spillover
    Date: 2022–10
  6. By: Naseh Majidi; Mahdi Shamsi; Farokh Marvasti
    Abstract: Price movement prediction has always been one of the traders' concerns in financial market trading. In order to increase their profit, they can analyze the historical data and predict the price movement. The large size of the data and complex relations between them lead us to use algorithmic trading and artificial intelligence. This paper aims to offer an approach using Twin-Delayed DDPG (TD3) and the daily close price in order to achieve a trading strategy in the stock and cryptocurrency markets. Unlike previous studies using a discrete action space reinforcement learning algorithm, the TD3 is continuous, offering both position and the number of trading shares. Both the stock (Amazon) and cryptocurrency (Bitcoin) markets are addressed in this research to evaluate the performance of the proposed algorithm. The achieved strategy using the TD3 is compared with some algorithms using technical analysis, reinforcement learning, stochastic, and deterministic strategies through two standard metrics, Return and Sharpe ratio. The results indicate that employing both position and the number of trading shares can improve the performance of a trading system based on the mentioned metrics.
    Date: 2022–10
  7. By: Ananda Chatterjee; Hrisav Bhowmick; Jaydip Sen
    Abstract: Volatility clustering is a crucial property that has a substantial impact on stock market patterns. Nonetheless, developing robust models for accurately predicting future stock price volatility is a difficult research topic. For predicting the volatility of three equities listed on India's national stock market (NSE), we propose multiple volatility models depending on the generalized autoregressive conditional heteroscedasticity (GARCH), Glosten-Jagannathan-GARCH (GJR-GARCH), Exponential general autoregressive conditional heteroskedastic (EGARCH), and LSTM framework. Sector-wise stocks have been chosen in our study. The sectors which have been considered are banking, information technology (IT), and pharma. yahoo finance has been used to obtain stock price data from Jan 2017 to Dec 2021. Among the pulled-out records, the data from Jan 2017 to Dec 2020 have been taken for training, and data from 2021 have been chosen for testing our models. The performance of predicting the volatility of stocks of three sectors has been evaluated by implementing three different types of GARCH models as well as by the LSTM model are compared. It has been observed the LSTM performed better in predicting volatility in pharma over banking and IT sectors. In tandem, it was also observed that E-GARCH performed better in the case of the banking sector and for IT and pharma, GJR-GARCH performed better.
    Date: 2022–10
  8. By: Ivan Letteri; Giuseppe Della Penna; Giovanni De Gasperis; Abeer Dyoub
    Abstract: In general, traders test their trading strategies by applying them on the historical market data (backtesting), and then apply to the future trades the strategy that achieved the maximum profit on such past data. In this paper, we propose a new trading strategy, called DNN-forwardtesting, that determines the strategy to apply by testing it on the possible future predicted by a deep neural network that has been designed to perform stock price forecasts and trained with the market historical data. In order to generate such an historical dataset, we first perform an exploratory data analysis on a set of ten securities and, in particular, analize their volatility through a novel k-means-based procedure. Then, we restrict the dataset to a small number of assets with the same volatility coefficient and use such data to train a deep feed-forward neural network that forecasts the prices for the next 30 days of open stocks market. Finally, our trading system calculates the most effective technical indicator by applying it to the DNNs predictions and uses such indicator to guide its trades. The results confirm that neural networks outperform classical statistical techniques when performing such forecasts, and their predictions allow to select a trading strategy that, when applied to the real future, increases Expectancy, Sharpe, Sortino, and Calmar ratios with respect to the strategy selected through traditional backtesting.
    Date: 2022–10
  9. By: Hui Niu; Siyuan Li; Jian Li
    Abstract: Portfolio management is a fundamental problem in finance. It involves periodic reallocations of assets to maximize the expected returns within an appropriate level of risk exposure. Deep reinforcement learning (RL) has been considered a promising approach to solving this problem owing to its strong capability in sequential decision making. However, due to the non-stationary nature of financial markets, applying RL techniques to portfolio optimization remains a challenging problem. Extracting trading knowledge from various expert strategies could be helpful for agents to accommodate the changing markets. In this paper, we propose MetaTrader, a novel two-stage RL-based approach for portfolio management, which learns to integrate diverse trading policies to adapt to various market conditions. In the first stage, MetaTrader incorporates an imitation learning objective into the reinforcement learning framework. Through imitating different expert demonstrations, MetaTrader acquires a set of trading policies with great diversity. In the second stage, MetaTrader learns a meta-policy to recognize the market conditions and decide on the most proper learned policy to follow. We evaluate the proposed approach on three real-world index datasets and compare it to state-of-the-art baselines. The empirical results demonstrate that MetaTrader significantly outperforms those baselines in balancing profits and risks. Furthermore, thorough ablation studies validate the effectiveness of the components in the proposed approach.
    Date: 2022–09
  10. By: Miguel Sarmiento
    Abstract: Banks in emerging market economies rely on cross-border interbank lending to financing firms in the real sector. By matching cross-border bank-to-bank loan level data with domestic bank-to-firm loan level data, and firm-level data, this paper shows that sudden yield reversal observed during the 2013 Fed taper tantrum resulted in a substantial contraction of cross-border interbank lending in emerging markets that significantly reduced the supply of domestic corporate credit and increased the corporate loan rates. Results show that firms with an ex-ante high concentration of credit granted by exposed banks in the cross-border interbank market exhibited low bank credit and substantial real effects, including a decline in imports and exports. The results further indicate that cross-border intra-group lending and domestic unsecured interbank funding contribute to smoothing the effects of sudden yield reversals on the financial intermediation. Overall, the results are consistent with the notion that banks’ exposition in international credit markets contributes to global financial conditions’ transmission to the economy. ****RESUMEN: Los bancos en las economías de mercados emergentes dependen de los préstamos interbancarios transfronterizos para financiar empresas en el sector real. Usando datos a nivel de préstamos transfronterizos entre bancos, datos a nivel de préstamos domésticos de bancos a firmas y datos a nivel de firma, este documento muestra que la reversión repentina de rendimientos observadas durante el Fed Taper Tantrum de 2013 generó una contracción sustancial del crédito interbancario transfronterizo en los mercados emergentes que resultó en una significativa reducción de la oferta doméstica de crédito corporativo y en mayores tasas de los préstamos. Los resultados muestran que las firmas con una alta concentración de crédito otorgado por los bancos más expuestos en el mercado de préstamos interbancarios transfronterizos exhibieron bajo crédito bancario y efectos reales sustanciales, incluyendo una disminución de las importaciones y exportaciones. Los resultados indican además que los préstamos transfronterizos intra-grupo y el fondeo interbancario doméstico contribuyen a suavizar los efectos de las reversiones repentinas de rendimientos sobre la intermediación financiera. En general, estos resultados son consistentes con la noción de que la exposición de los bancos en los mercados internacionales de crédito contribuye a la transmisión de las condiciones financieras globales en la economía.
    Keywords: Sudden Yield Reversals, Cross-Border Interbank Lending, Financial Intermediation, Lending Relationships, Emerging Markets, Reversiones repentinas de rendimientos, Intermediación financiera, Mercados Emergentes, Crédito interbancario transfronterizo, Relaciones bancarias
    JEL: E43 E58 L14 G12 G21
    Date: 2022–10
  11. By: Helena Chuliá (RISKcenter, Institut de Recerca en Economia Aplicada (IREA). Departament d’Econometria, Estadística i Economia Aplicada, Universitat de Barcelona (UB).); Jorge A. Muñoz-Mendoza (Department of Business Management, University of Concepcion, Chile. School of Economics, University of Barcelona, Spain.); Jorge M. Uribe (Faculty of Economics and Business, Universitat Oberta de Catalunya, Spain.)
    Abstract: Previous studies in energy stock markets have analyzed market connectedness using aggregate indexes and focusing on developed markets. We depart from the extant literature and we focus our attention on companies listed on emerging stock markets and examine connectedness from the firm’s perspective. Using a two-step approach, we remove the common global factors from energy stock returns and estimate the network of global energy stocks in emerging markets. We show that idiosyncratic components are highly relevant for our understanding of risk transmission in energy markets. Moreover, we offer precise diversification alternatives and identify the most systemically important firms and countries.
    Keywords: Energy firms, Spillovers, Connectedness, Network. JEL classification: G15, Q43, Q48.
    Date: 2022–10
  12. By: Ozili, Peterson K
    Abstract: This paper presents a discussion of decentralized finance in Africa. It presents some statistics and data on decentralized finance in Africa. Thereafter, the potential benefits, challenges and regulatory issues associated with decentralized finance in Africa are discussed. Recently, there has been an increase in the use of cryptocurrency, decentralized finance applications (dApps) and decentralized financial services (DeFi) in several countries. These innovations facilitate the delivery of financial services using smart contracts. Decentralized finance (DeFi) encompasses all financial services that are built on public blockchains, based on open protocols and removes intermediaries from the financial intermediation process. There is significant cryptocurrency activity in Africa while decentralized finance (DeFi) is relatively new and unpopular in the African continent. There is low interest in decentralized finance in Africa. The benefit of DeFi to African countries include increased liquidity for small and medium scale enterprises (SMEs), new opportunities to raise additional capital to fund capital-intensive activities, it will usher in an era of smart contracts that are negotiated bilaterally without needing an intermediary, it will encourage peer-to-peer trade between economic agents in several African countries, it will enhance the efficiency of the Pan-African Payment Settlement System (PAPSS), and encourage more trade between individuals and corporations under the African Continental Free Trade Agreement (AfCFTA), amongst others.
    Keywords: Decentralized finance, Cryptocurrencies, DeFi, dApps, AfCFTA, Bitcoin, blockchain, central bank digital currency crypto technologies, Africa, smart contracts.
    JEL: G21 G23 O31
    Date: 2022–09

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.