nep-fmk New Economics Papers
on Financial Markets
Issue of 2022‒08‒22
eleven papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Learning Mutual Fund Categorization using Natural Language Processing By Dimitrios Vamvourellis; Mate Attila Toth; Dhruv Desai; Dhagash Mehta; Stefano Pasquali
  2. AlphaMLDigger: A Novel Machine Learning Solution to Explore Excess Return on Investment By Jimei Shen; Zhehu Yuan; Yifan Jin
  3. Balancing Profit, Risk, and Sustainability for Portfolio Management By Charl Maree; Christian W. Omlin
  4. Reinforcement Learning Portfolio Manager Framework with Monte Carlo Simulation By Jungyu Ahn; Sungwoo Park; Jiwoon Kim; Ju-hong Lee
  5. Market Making with Scaled Beta Policies By Joseph Jerome; Gregory Palmer; Rahul Savani
  6. Clustering of Excursion Sets in Financial Market By M. Shadmangohar; S. M. S. Movahed
  7. A global monetary policy factor in sovereign bond yields By Dimitris Malliaropulos; Petros Migiakis
  8. Option characteristics as cross-sectional predictors By Neuhierl, Andreas; Tang, Xiaoxiao; Varneskov, Rasmus Tangsgaard; Zhou, Guofu
  9. Trading Volume and Liquidity Provision in Cryptocurrency Markets By Daniele Bianchi; Mykola Babiak; Alexander Dickerson
  10. Modeling S&P500 returns with GARCH models By Rodrigo Alfaro; Alejandra Inzunza
  11. The dynamics of the prices of the companies of the STOXX Europe 600 Index through the logit model and neural network By Federico Mecchia; Marcellino Gaudenzi

  1. By: Dimitrios Vamvourellis; Mate Attila Toth; Dhruv Desai; Dhagash Mehta; Stefano Pasquali
    Abstract: Categorization of mutual funds or Exchange-Traded-funds (ETFs) have long served the financial analysts to perform peer analysis for various purposes starting from competitor analysis, to quantifying portfolio diversification. The categorization methodology usually relies on fund composition data in the structured format extracted from the Form N-1A. Here, we initiate a study to learn the categorization system directly from the unstructured data as depicted in the forms using natural language processing (NLP). Positing as a multi-class classification problem with the input data being only the investment strategy description as reported in the form and the target variable being the Lipper Global categories, and using various NLP models, we show that the categorization system can indeed be learned with high accuracy. We discuss implications and applications of our findings as well as limitations of existing pre-trained architectures in applying them to learn fund categorization.
    Date: 2022–07
  2. By: Jimei Shen; Zhehu Yuan; Yifan Jin
    Abstract: How to quickly and automatically mine effective information and serve investment decisions has attracted more and more attention from academia and industry. And new challenges have been raised with the global pandemic. This paper proposes a two-phase AlphaMLDigger that effectively finds excessive returns in the highly fluctuated market. In phase 1, a deep sequential NLP model is proposed to transfer blogs on Sina Microblog to market sentiment. In phase 2, the predicted market sentiment is combined with social network indicator features and stock market history features to predict the stock movements with different Machine Learning models and optimizers. The results show that our AlphaMLDigger achieves higher accuracy in the test set than previous works and is robust to the negative impact of COVID-19 to some extent.
    Date: 2022–06
  3. By: Charl Maree; Christian W. Omlin
    Abstract: Stock portfolio optimization is the process of continuous reallocation of funds to a selection of stocks. This is a particularly well-suited problem for reinforcement learning, as daily rewards are compounding and objective functions may include more than just profit, e.g., risk and sustainability. We developed a novel utility function with the Sharpe ratio representing risk and the environmental, social, and governance score (ESG) representing sustainability. We show that a state-of-the-art policy gradient method - multi-agent deep deterministic policy gradients (MADDPG) - fails to find the optimum policy due to flat policy gradients and we therefore replaced gradient descent with a genetic algorithm for parameter optimization. We show that our system outperforms MADDPG while improving on deep Q-learning approaches by allowing for continuous action spaces. Crucially, by incorporating risk and sustainability criteria in the utility function, we improve on the state-of-the-art in reinforcement learning for portfolio optimization; risk and sustainability are essential in any modern trading strategy and we propose a system that does not merely report these metrics, but that actively optimizes the portfolio to improve on them.
    Date: 2022–06
  4. By: Jungyu Ahn; Sungwoo Park; Jiwoon Kim; Ju-hong Lee
    Abstract: Asset allocation using reinforcement learning has advantages such as flexibility in goal setting and utilization of various information. However, existing asset allocation methods do not consider the following viewpoints in solving the asset allocation problem. First, State design without considering portfolio management and financial market characteristics. Second, Model Overfitting. Third, Model training design without considering the statistical structure of financial time series data. To solve the problem of the existing asset allocation method using reinforcement learning, we propose a new reinforcement learning asset allocation method. First, the state of the portfolio managed by the model is considered as the state of the reinforcement learning agent. Second, Monte Carlo simulation data are used to increase training data complexity to prevent model overfitting. These data can have different patterns, which can increase the complexity of the data. Third, Monte Carlo simulation data are created considering various statistical structures of financial markets. We define the statistical structure of the financial market as the correlation matrix of the assets constituting the financial market. We show experimentally that our method outperforms the benchmark at several test intervals.
    Date: 2022–07
  5. By: Joseph Jerome; Gregory Palmer; Rahul Savani
    Abstract: This paper introduces a new representation for the actions of a market maker in an order-driven market. This representation uses scaled beta distributions, and generalises three approaches taken in the artificial intelligence for market making literature: single price-level selection, ladder strategies and "market making at the touch". Ladder strategies place uniform volume across an interval of contiguous prices. Scaled beta distribution based policies generalise these, allowing volume to be skewed across the price interval. We demonstrate that this flexibility is useful for inventory management, one of the key challenges faced by a market maker. In this paper, we conduct three main experiments: first, we compare our more flexible beta-based actions with the special case of ladder strategies; then, we investigate the performance of simple fixed distributions; and finally, we devise and evaluate a simple and intuitive dynamic control policy that adjusts actions in a continuous manner depending on the signed inventory that the market maker has acquired. All empirical evaluations use a high-fidelity limit order book simulator based on historical data with 50 levels on each side.
    Date: 2022–07
  6. By: M. Shadmangohar; S. M. S. Movahed
    Abstract: Relying on the excursion set theory, we compute the number density of local extrema and crossing statistics versus the threshold for the stock market indices. Comparing the number density of excursion sets calculated numerically with the theoretical prediction for the Gaussian process confirmed that all data sets used in this paper have a surplus (almost lack) value of local extrema (up-crossing) density at low (high) thresholds almost around the mean value implying universal properties for stock indices. We estimate the clustering of geometrical measures based on the excess probability of finding the pairs of excursion sets, which clarify well statistical coherency between markets located in the same geographical region. The cross-correlation of excursion sets between various markets is also considered to construct the matrix of agglomerative hierarchical clustering. Our results demonstrate that the peak statistics is more capable of capturing blocks. Incorporating the partitioning approach, we implement the Singular Value Decomposition on the matrix containing the maximum value of unweighted Two-Point Correlation Function of peaks and up-crossing to compute the similarity measure. Our results support that excursion sets are more sensitive than standard measures to elucidate the existence of {\it a priori} crisis.
    Date: 2022–07
  7. By: Dimitris Malliaropulos (Bank of Greece); Petros Migiakis
    Abstract: We document the existence of a global monetary policy factor in sovereign bond yields, related to the size of the aggregate balance sheet of nine major central banks of developed economies that have implemented programs of large-scale asset purchases. Balance sheet policies of these central banks reduced the net supply of safe assets in the global economy, triggering a decline in global yields as investors rebalanced their portfolios towards more risky assets. We find that central banks’ large-scale asset purchases have contributed to significant and permanent declines in long-term yields globally, ranging from around 330 bps for AAA-rated sovereigns to 800 bps for non-investment grade sovereigns. The stronger decline in yields of high-risk sovereigns can be partly attributed to the decline in the foreign exchange risk premium as their currencies appreciated. Global central bank asset purchases during the Covid-19 crisis have more than counterbalanced the effects of expanding fiscal deficits on global bond yields, driving them to even lower levels. Our findings have important policy implications: normalizing monetary policy by scaling down central bank balance sheets to pre-crisis levels may lead to sharp increases in sovereign bond yields globally, widening spreads and currency depreciations of vulnerable sovereigns with severe consequences for financial stability and the global economy.
    Keywords: quantitative easing; central bank balance sheet policies; sovereign risk; interest rates; panel cointegration.
    JEL: E42 E43 G12 G15
    Date: 2022–07
  8. By: Neuhierl, Andreas; Tang, Xiaoxiao; Varneskov, Rasmus Tangsgaard; Zhou, Guofu
    Abstract: We provide the first comprehensive analysis of option information for pricing the cross-section of stock returns by jointly examining extensive sets of firm and option characteristics. Using portfolio sorts and high-dimensional methods, we show that certain option measures have significant predictive power, even after controlling for firm characteristics, earning a Fama-French three-factor alpha in excess of 20% per annum. Our analysis further reveals that the strongest option characteristics are associated with information about asset mispricing and future tail return realizations. Our findings are consistent with models of informed trading and limits to arbitrage.
    Keywords: Asset Pricing,Factor Models,High-dimensional Methods,Option Characteristics
    JEL: C13 C14 G11 G12 G14
    Date: 2022
  9. By: Daniele Bianchi; Mykola Babiak; Alexander Dickerson
    Abstract: We provide empirical evidence within the context of cryptocurrency markets that the returns from liquidity provision, proxied by the returns of a short-term reversal strategy, are primarily concentrated in trading pairs with lower levels of market activity. Empirically, we focus on a moderately large cross section of cryptocurrency pairs traded against the U.S. Dollar from March 1, 2017 to March 1, 2022 on multiple centralised exchanges. Our findings suggest that expected returns from liquidity provision are amplified in smaller, more volatile, and less liquid cryptocurrency pairs, where fear of adverse selection might be higher. A panel regression analysis confirms that the interaction between lagged returns and trading volume contains significant predictive information about the dynamics of cryptocurrency returns. This is consistent with theories that highlight the roles of inventory risk and adverse selection for liquidity provision.
    Keywords: liquidity provision; short-term reversal; trading volume; empirical asset pricing; adverse selection;
    JEL: G12 G17 E44 C58
    Date: 2022–06
  10. By: Rodrigo Alfaro; Alejandra Inzunza
    Abstract: This paper provides several estimates of the parameters of a GARCH model for the S&P500 index, based on: (i) returns, (ii) returns and CBOE VIX, and (iii) returns, CBOE VIX, and other option-based indexes reported by the Federal Reserve of Minneapolis. We conclude that by including option-based indexes alternative calibrations are obtained, which can be used to compute improved tail-risk statistics under the risk neutral measure, providing a better assessment of the occurrence of extreme events.
    Date: 2022–05
  11. By: Federico Mecchia; Marcellino Gaudenzi
    Abstract: The aim of the present work is analysing and understanding the dynamics of the prices of companies, depending on whether they are included or excluded from the STOXX Europe 600 Index. For this reason, data regarding the companies of the Index in question was collected and analysed also through the use of logit models and neural networks in order to find the independent variables that affect the changes in prices and thus determine the dynamics over time.
    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.