nep-fmk New Economics Papers
on Financial Markets
Issue of 2023‒07‒31
thirteen papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Are there Dragon Kings in the Stock Market? By Jiong Liu; M. Dashti Moghaddam; R. A. Serota
  2. Social Media Emotions and IPO Returns By Domonkos F. Vamossy
  3. An Analytic Solution for Valuing Guaranteed Equity Securities By Lee, David
  4. Time-Varying Risk Aversion and International Stock Returns By Massimo Guidolin; Erwin Hansen; Gabriel Cabrera
  5. Do Municipal Bond Investors Pay a Convenience Premium to Avoid Taxes? By Matthias Fleckenstein; Francis A. Longstaff
  6. Principal Component Analysis and Hidden Markov Model for Forecasting Stock Returns By Eugene W. Park
  7. Higher-order Graph Attention Network for Stock Selection with Joint Analysis By Yang Qiao; Yiping Xia; Xiang Li; Zheng Li; Yan Ge
  8. Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management By Marc Velay; Bich-Li\^en Doan; Arpad Rimmel; Fabrice Popineau; Fabrice Daniel
  9. Abnormal Trading Detection in the NFT Market By Mingxiao Song; Yunsong Liu; Agam Shah; Sudheer Chava
  10. Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning By Joel Ong; Dorien Herremans
  11. Stock Price Prediction using Dynamic Neural Networks By David Noel
  12. Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements? By Haohan Zhang; Fengrui Hua; Chengjin Xu; Jian Guo; Hao Kong; Ruiting Zuo
  13. Russian financial market in 2022 By Abramov Alexander; Radygin Alexander; Chernova Maria

  1. By: Jiong Liu; M. Dashti Moghaddam; R. A. Serota
    Abstract: We undertake a systematic study of historic market volatility spanning roughly five preceding decades. We focus specifically on the time series of realized volatility (RV) of the S&P500 index and its distribution function. As expected, the largest values of RV coincide with the largest economic upheavals of the period: Savings and Loan Crisis, Tech Bubble, Financial Crisis and Covid Pandemic. We address the question of whether these values belong to one of the three categories: Black Swans (BS), that is they lie on scale-free, power-law tails of the distribution; Dragon Kings (DK), defined as statistically significant upward deviations from BS; or Negative Dragons Kings (nDK), defined as statistically significant downward deviations from BS. In analyzing the tails of the distribution with RV > 40, we observe the appearance of "potential" DK which eventually terminate in an abrupt plunge to nDK. This phenomenon becomes more pronounced with the increase of the number of days over which the average RV is calculated -- here from daily, n=1, to "monthly, " n=21. We fit the entire distribution with a modified Generalized Beta (mGB) distribution function, which terminates at a finite value of the variable but exhibits a long power-law stretch prior to that, as well as Generalized Beta Prime (GB2) distribution function, which has a power-law tail. We also fit the tails directly with a straight line on a log-log scale. In order to ascertain BS, DK or nDK behavior, all fits include their confidence intervals and p-values are evaluated for the data points to check if they can come from the respective distributions.
    Date: 2023–07
  2. By: Domonkos F. Vamossy
    Abstract: I examine potential mechanisms behind two stylized facts of initial public offerings (IPOs) returns. By analyzing investor sentiment expressed on StockTwits and Twitter, I find that emotions conveyed through these social media platforms can help explain the mispricing of IPO stocks. The abundance of information and opinions shared on social media can generate hype around certain stocks, leading to investors' irrational buying and selling decisions. This can result in an overvaluation of the stock in the short term but often leads to a correction in the long term as the stock's performance fails to meet the inflated expectations. In particular, I find that IPOs with high levels of pre-IPO investor enthusiasm tend to have a significantly higher first-day return of 29.54%, compared to IPOs with lower levels of pre-IPO investor enthusiasm, which have an average first-day return of 16.91%. However, this initial enthusiasm may be misplaced, as IPOs with high pre-IPO investor enthusiasm demonstrate a much lower average long-run industry-adjusted return of -8.53%, compared to IPOs with lower pre-IPO investor enthusiasm, which have an average long-run industry-adjusted return of -1.1%.
    Date: 2023–06
  3. By: Lee, David
    Abstract: Equity-linked securities with a guaranteed amount have some specific interesting features for investors, like downside protection and capital appreciation. The contract has a guaranteed return plus a payment linked to the performance of a basket of equities or indices averaged over a certain period. This article presents an analytical model for valuing equity-linked notes and computing the corresponding hedge ratios. The model appears to be accurate over a wide range of valuation parameters based on numerical studies. Finally, we use the model to value a segregated fund with a guarantee amount at maturity.
    Keywords: Equity-linked securities, segregated fund, asset pricing, derivative valuation, hedge ratio.
    JEL: C58 D46 G12
    Date: 2023–06–27
  4. By: Massimo Guidolin; Erwin Hansen; Gabriel Cabrera
    Abstract: We estimate an aggregate time-varying risk aversion function using option, stock return and macroeconomic data for a sample of 8 countries. We document that, in most of the countries, the degree of risk aversion is countercyclical. Moreover, we show that the estimated risk aversion function forecasts monthly stock index returns up to 12 months ahead. This effect is statistically significant in panel regressions, and it survives the inclusion of additional control variables. Finally, we show that the estimated time-varying risk aversion function provides useful information to an investor who aims at timing the market. An investment strategy that uses the estimated time-varying risk aversion measure to solve a mean-variance asset allocation problem, delivers significant returns.
    Keywords: Implied risk aversion, forecast stock return, market timing, mean-variance asset allocation.
    JEL: G10 G11 G15
    Date: 2023
  5. By: Matthias Fleckenstein; Francis A. Longstaff
    Abstract: We study the valuation of state-issued tax-exempt municipal bonds and find that there are significant convenience premia in their prices. These premia parallel those identified in Treasury markets. We find evidence that these premia are tax related. Specifically, the premia are related to measures of tax and fiscal uncertainty, forecast flows into state municipal bond funds, and are directly linked to outmigration from high-tax to low-tax states and to other measures of tax aversion such as IRA and retirement plan contributions. These results suggest that investors are willing to pay a substantial premium to avoid taxes.
    JEL: G12
    Date: 2023–06
  6. By: Eugene W. Park
    Abstract: This paper presents a method for predicting stock returns using principal component analysis (PCA) and the hidden Markov model (HMM) and tests the results of trading stocks based on this approach. Principal component analysis is applied to the covariance matrix of stock returns for companies listed in the S&P 500 index, and interpreting principal components as factor returns, we apply the HMM model on them. Then we use the transition probability matrix and state conditional means to forecast the factors returns. Reverting the factor returns forecasts to stock returns using eigenvectors, we obtain forecasts for the stock returns. We find that, with the right hyperparameters, our model yields a strategy that outperforms the buy-and-hold strategy in terms of the annualized Sharpe ratio.
    Date: 2023–07
  7. By: Yang Qiao; Yiping Xia; Xiang Li; Zheng Li; Yan Ge
    Abstract: Stock selection is important for investors to construct profitable portfolios. Graph neural networks (GNNs) are increasingly attracting researchers for stock prediction due to their strong ability of relation modelling and generalisation. However, the existing GNN methods only focus on simple pairwise stock relation and do not capture complex higher-order structures modelling relations more than two nodes. In addition, they only consider factors of technical analysis and overlook factors of fundamental analysis that can affect the stock trend significantly. Motivated by them, we propose higher-order graph attention network with joint analysis (H-GAT). H-GAT is able to capture higher-order structures and jointly incorporate factors of fundamental analysis with factors of technical analysis. Specifically, the sequential layer of H-GAT take both types of factors as the input of a long-short term memory model. The relation embedding layer of H-GAT constructs a higher-order graph and learn node embedding with GAT. We then predict the ranks of stock return. Extensive experiments demonstrate the superiority of our H-GAT method on the profitability test and Sharp ratio over both NSDAQ and NYSE datasets
    Date: 2023–06
  8. By: Marc Velay; Bich-Li\^en Doan; Arpad Rimmel; Fabrice Popineau; Fabrice Daniel
    Abstract: Deep Reinforcement Learning approaches to Online Portfolio Selection have grown in popularity in recent years. The sensitive nature of training Reinforcement Learning agents implies a need for extensive efforts in market representation, behavior objectives, and training processes, which have often been lacking in previous works. We propose a training and evaluation process to assess the performance of classical DRL algorithms for portfolio management. We found that most Deep Reinforcement Learning algorithms were not robust, with strategies generalizing poorly and degrading quickly during backtesting.
    Date: 2023–06
  9. By: Mingxiao Song; Yunsong Liu; Agam Shah; Sudheer Chava
    Abstract: The Non-Fungible-Token (NFT) market has experienced explosive growth in recent years. According to DappRadar, the total transaction volume on OpenSea, the largest NFT marketplace, reached 34.7 billion dollars in February 2023. However, the NFT market is mostly unregulated and there are significant concerns about money laundering, fraud and wash trading. Amateur traders and retail investors comprise a significant fraction of the NFT market. Hence it is important that researchers highlight the relevant risks involved in NFT trading. In this paper, we attempt to uncover common fraudulent behaviors such as wash trading that could mislead other traders. Using market data, we design quantitative features from the network, monetary, and temporal perspectives that are fed into K-means clustering unsupervised learning algorithm to sort traders into groups. Lastly, we discuss the clustering results' significance and how regulations can reduce undesired behaviors. Our work can potentially help regulators narrow down their search space for bad actors in the market as well as provide insights for amateur traders to protect themselves from unforeseen frauds.
    Date: 2023–05
  10. By: Joel Ong; Dorien Herremans
    Abstract: A diversified risk-adjusted time-series momentum (TSMOM) portfolio can deliver substantial abnormal returns and offer some degree of tail risk protection during extreme market events. The performance of existing TSMOM strategies, however, relies not only on the quality of the momentum signal but also on the efficacy of the volatility estimator. Yet many of the existing studies have always considered these two factors to be independent. Inspired by recent progress in Multi-Task Learning (MTL), we present a new approach using MTL in a deep neural network architecture that jointly learns portfolio construction and various auxiliary tasks related to volatility, such as forecasting realized volatility as measured by different volatility estimators. Through backtesting from January 2000 to December 2020 on a diversified portfolio of continuous futures contracts, we demonstrate that even after accounting for transaction costs of up to 3 basis points, our approach outperforms existing TSMOM strategies. Moreover, experiments confirm that adding auxiliary tasks indeed boosts the portfolio's performance. These findings demonstrate that MTL can be a powerful tool in finance.
    Date: 2023–06
  11. By: David Noel
    Abstract: This paper will analyze and implement a time series dynamic neural network to predict daily closing stock prices. Neural networks possess unsurpassed abilities in identifying underlying patterns in chaotic, non-linear, and seemingly random data, thus providing a mechanism to predict stock price movements much more precisely than many current techniques. Contemporary methods for stock analysis, including fundamental, technical, and regression techniques, are conversed and paralleled with the performance of neural networks. Also, the Efficient Market Hypothesis (EMH) is presented and contrasted with Chaos theory using neural networks. This paper will refute the EMH and support Chaos theory. Finally, recommendations for using neural networks in stock price prediction will be presented.
    Date: 2023–06
  12. By: Haohan Zhang; Fengrui Hua; Chengjin Xu; Jian Guo; Hao Kong; Ruiting Zuo
    Abstract: The rapid advancement of Large Language Models (LLMs) has led to extensive discourse regarding their potential to boost the return of quantitative stock trading strategies. This discourse primarily revolves around harnessing the remarkable comprehension capabilities of LLMs to extract sentiment factors which facilitate informed and high-frequency investment portfolio adjustments. To ensure successful implementations of these LLMs into the analysis of Chinese financial texts and the subsequent trading strategy development within the Chinese stock market, we provide a rigorous and encompassing benchmark as well as a standardized back-testing framework aiming at objectively assessing the efficacy of various types of LLMs in the specialized domain of sentiment factor extraction from Chinese news text data. To illustrate how our benchmark works, we reference three distinctive models: 1) the generative LLM (ChatGPT), 2) the Chinese language-specific pre-trained LLM (Erlangshen-RoBERTa), and 3) the financial domain-specific fine-tuned LLM classifier(Chinese FinBERT). We apply them directly to the task of sentiment factor extraction from large volumes of Chinese news summary texts. We then proceed to building quantitative trading strategies and running back-tests under realistic trading scenarios based on the derived sentiment factors and evaluate their performances with our benchmark. By constructing such a comparative analysis, we invoke the question of what constitutes the most important element for improving a LLM's performance on extracting sentiment factors. And by ensuring that the LLMs are evaluated on the same benchmark, following the same standardized experimental procedures that are designed with sufficient expertise in quantitative trading, we make the first stride toward answering such a question.
    Date: 2023–06
  13. By: Abramov Alexander (RANEPA); Radygin Alexander (Gaidar Institute for Economic Policy); Chernova Maria (RANEPA)
    Abstract: The year 2022 was one of the most difficult periods for the global financial market in many years. Due to a unique combination of adverse economic and geopolitical factors, investments in almost all assets, with few exceptions, had negative returns in 2022. Even investment assets such as government securities, precious metals, real estate and cryptocurrency failed to perform their functions of hedging investor returns against losses. In January-February 2023, many financial assets began to show positive returns again, however, this trend gradually slowed down under the influence of the same factors that negatively affected the financial market in 2022.
    Keywords: Russian economy, stock market, bond market, corporate bond market, derivatives market, private investors
    JEL: G01 G12 G18 G21 G24 G28 G32 G33
    Date: 2023

This nep-fmk issue is ©2023 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.