nep-fmk New Economics Papers
on Financial Markets
Issue of 2022‒08‒08
ten papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Predicting Stock Price Movement after Disclosure of Corporate Annual Reports: A Case Study of 2021 China CSI 300 Stocks By Fengyu Han; Yue Wang
  2. Intermediary Balance Sheets and the Treasury Yield Curve By Wenxin Du; Benjamin Hébert; Wenhao Li
  3. Development of a hybrid method for stock trading based on TOPSIS, EMD and ELM By Elivelto Ebermam; Helder Knidel; Renato A. Krohling
  4. Fundamental, technical and external factors induced positive and negative extreme events in the stock market By Anish Rai; Salam Rabindrajit Luwang; Md Nurujjaman; Kanish Debnath
  5. Manage Risk in DeFi Portfolio By Hugo Inzirillo; Stanislas de Quenetain
  6. A Data Science Pipeline for Algorithmic Trading: A Comparative Study of Applications for Finance and Cryptoeconomics By Luyao Zhang; Tianyu Wu; Saad Lahrichi; Carlos-Gustavo Salas-Flores; Jiayi Li
  7. On the universality of the volatility formation process: when machine learning and rough volatility agree By Mathieu Rosenbaum; Jianfei Zhang
  8. The probability flow in the Stock market and Spontaneous symmetry breaking in Quantum Finance By Ivan Arraut; Joao Alexandre Lobo Marques; Sergio Gomes
  9. Crypto-Assets and Decentralized Finance through a Financial Stability Lens, a speech at Bank of England Conference, London, United Kingdom, July 8, 2022 By Lael Brainard
  10. Unique futures in China: studys on volatility spillover effects of ferrous metal futures By Tingting Cao; Weiqing Sun; Cuiping Sun; Lin Hao

  1. By: Fengyu Han; Yue Wang
    Abstract: In the current stock market, computer science and technology are more and more widely used to analyse stocks. Not same as most related machine learning stock price prediction work, this work study the predicting the tendency of the stock price on the second day right after the disclosure of the companies' annual reports. We use a variety of different models, including decision tree, logistic regression, random forest, neural network, prototypical networks. We use two sets of financial indicators (key and expanded) to conduct experiments, these financial indicators are obtained from the EastMoney website disclosed by companies, and finally we find that these models are not well behaved to predict the tendency. In addition, we also filter stocks with ROE greater than 0.15 and net cash ratio greater than 0.9. We conclude that according to the financial indicators based on the just-released annual report of the company, the predictability of the stock price movement on the second day after disclosure is weak, with maximum accuracy about 59.6% and maximum precision about 0.56 on our test set by the random forest classifier, and the stock filtering does not improve the performance. And random forests perform best in general among all these models which conforms to some work's findings.
    Date: 2022–06
  2. By: Wenxin Du; Benjamin Hébert; Wenhao Li
    Abstract: We have documented a regime change in the U.S. Treasury market post-Global Financial Crisis (GFC). We first derived bounds on Treasury yields that account for dealer balance sheet costs, which we call the net short and net long curves. We show that actual Treasury yields moved from the net short curve pre- GFC to the net long curve post-GFC, consistent with the shift in the dealers’ net position. We then use a stylized model to demonstrate that increased bond supply and tightening leverage constraints can explain this change in regime. This change, in turn, helps explain negative swap spreads and the co-movement between swap spreads, dealer positions, yield curve slope, and covered-interest-parity violations, and implies changing effects for a wide range of monetary and regulatory policy interventions.
    Keywords: yield curve; balance sheet constraints; CIP deviations
    JEL: G12 E52 F3
    Date: 2022–07–01
  3. By: Elivelto Ebermam; Helder Knidel; Renato A. Krohling
    Abstract: Deciding when to buy or sell a stock is not an easy task because the market is hard to predict, being influenced by political and economic factors. Thus, methodologies based on computational intelligence have been applied to this challenging problem. In this work, every day the stocks are ranked by technique for order preference by similarity to ideal solution (TOPSIS) using technical analysis criteria, and the most suitable stock is selected for purchase. Even so, it may occur that the market is not favorable to purchase on certain days, or even, the TOPSIS make an incorrect selection. To improve the selection, another method should be used. So, a hybrid model composed of empirical mode decomposition (EMD) and extreme learning machine (ELM) is proposed. The EMD decomposes the series into several sub-series, and thus the main omponent (trend) is extracted. This component is processed by the ELM, which performs the prediction of the next element of component. If the value predicted by the ELM is greater than the last value, then the purchase of the stock is confirmed. The method was applied in a universe of 50 stocks in the Brazilian market. The selection made by TOPSIS showed promising results when compared to the random selection and the return generated by the Bovespa index. Confirmation with the EMD-ELM hybrid model was able to increase the percentage of profit tradings.
    Date: 2022–06
  4. By: Anish Rai; Salam Rabindrajit Luwang; Md Nurujjaman; Kanish Debnath
    Abstract: Sporadic large fluctuations in stock price are seen in the stock market. Such large fluctuations occur due to three important factors: (a) the significant change in the fundamental parameters like excellent or bad results; (b) the formation of a special technical setup in the stock price like double-bottom and (c) external factors like war. These factors may lead to occasional and rare upsurge or crash of significant height in the stock price, and such upsurge or crash is termed as positive or negative extreme event (EE), respectively. In this work, we have identified EE in the stock price of selected companies from global stock markets due to the above factors in minute, daily, weekly time-scales. Augmented Dickey-Fuller and degree of nonstationarity tests show that the stock price time-series is nonstationary. Subsequently, we applied the Hilbert-Huang transformation to identify EE. The analysis shows that the instantaneous energy ($IE$) concentration in the stock price is very high during an EE with $IE>E_{\mu}+4\sigma,$ where $E_{\mu}$ and $\sigma$ are the mean energy and standard deviation of energy, respectively. The analysis shows that investor can gain or lose a significant amount of their capital due to these events. Hence, identification of the EEs in the stock market is important as it helps the investor and trader to take rational decisions during such crisis. Investors should carefully monitor the factors that lead to EEs for entry or exit strategies in the market.
    Date: 2022–06
  5. By: Hugo Inzirillo; Stanislas de Quenetain
    Abstract: Decentralized Finance (DeFi) is a new financial industry built on blockchain technologies. Decentralized financial services increased consequantly, the ability to lend, borrow and invest in decentralized investment vehicules, allowing investors to bypass third party intermediaries. DeFI promise is to reduce transactions costs, management fees while increasing the trust between agents of this financial industry 3.0. This paper provides an overview of Decentralized Finance different components as well as the risks involved in investing through these new vehicles. It also proposes an allocation methodology which integrate and quantify these risks.
    Date: 2022–05
  6. By: Luyao Zhang; Tianyu Wu; Saad Lahrichi; Carlos-Gustavo Salas-Flores; Jiayi Li
    Abstract: Recent advances in Artificial Intelligence (AI) have made algorithmic trading play a central role in finance. However, current research and applications are disconnected information islands. We propose a generally applicable pipeline for designing, programming, and evaluating the algorithmic trading of stock and crypto assets. Moreover, we demonstrate how our data science pipeline works with respect to four conventional algorithms: the moving average crossover, volume-weighted average price, sentiment analysis, and statistical arbitrage algorithms. Our study offers a systematic way to program, evaluate, and compare different trading strategies. Furthermore, we implement our algorithms through object-oriented programming in Python3, which serves as open-source software for future academic research and applications.
    Date: 2022–06
  7. By: Mathieu Rosenbaum; Jianfei Zhang
    Abstract: We train an LSTM network based on a pooled dataset made of hundreds of liquid stocks aiming to forecast the next daily realized volatility for all stocks. Showing the consistent outperformance of this universal LSTM relative to other asset-specific parametric models, we uncover nonparametric evidences of a universal volatility formation mechanism across assets relating past market realizations, including daily returns and volatilities, to current volatilities. A parsimonious parametric forecasting device combining the rough fractional stochastic volatility and quadratic rough Heston models with fixed parameters results in the same level of performance as the universal LSTM, which confirms the universality of the volatility formation process from a parametric perspective.
    Date: 2022–06
  8. By: Ivan Arraut; Joao Alexandre Lobo Marques; Sergio Gomes
    Abstract: The Spontaneous Symmetry breaking in Quantum Finance considers the martingale condition in the stock market as a vacuum state if we express the financial equations in the Hamiltonian form. The original analysis for this phenomena ignores completely the kinetic terms in the neighborhood of the minimal of the potential terms. This is correct in most of the cases. However, when we deal with the Martingale condition, it comes out that the kinetic terms can also behave as potential terms and then reproduce a shift on the effective location of the vacuum (Martingale). In this paper we analyze the effective symmetry breaking patterns and the connected vacuum degeneracy for these special circumstances. Within the same scenario, we analyze the connection between the flow of information and the multiplicity of martingale states, providing in this way powerful tools for analyzing the dynamic of the stock market.
    Date: 2022–05
  9. By: Lael Brainard
    Date: 2022–07–08
  10. By: Tingting Cao; Weiqing Sun; Cuiping Sun; Lin Hao
    Abstract: Ferrous metal futures have become unique commodity futures with Chinese characteristics. Due to the late listing time, it has received less attention from scholars. Our research focuses on the volatility spillover effects, defined as the intensity of price volatility in financial instruments. We use DCC-GARCH, BEKK-GARCH, and DY(2012) index methods to conduct empirical tests on the volatility spillover effects of the Chinese ferrous metal futures market and other parts of the Chinese commodity futures market, as well as industries related to the steel industry chain in stock markets. It can be seen that there is a close volatility spillover relationship between ferrous metal futures and nonferrous metal futures. Energy futures and chemical futures have a significant transmission effect on the fluctuations of ferrous metals. In addition, ferrous metal futures have a significant spillover effect on the stock index of the steel industry, real estate industry, building materials industry, machinery equipment industry, and household appliance industry. Studying the volatility spillover effect of the ferrous metal futures market can reveal the operating laws of this field and provide ideas and theoretical references for investors to hedge their risks. It shows that the ferrous metal futures market has an essential role as a "barometer" for the Chinese commodity futures market and the stock market.
    Date: 2022–06

This nep-fmk issue is ©2022 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.