nep-fmk New Economics Papers
on Financial Markets
Issue of 2020‒03‒09
ten papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. The Hedge Fund Industry is Bigger (and has Performed Better) Than You Think By Daniel Barth; Juha Joenvaara; Mikko Kauppila; Russ Wermers
  2. Leverage and Risk in Hedge Funds By Daniel Barth; Laurel Hammond; Phillip Monin
  3. An Empirical Study of the Sentiment Capital Asset Pricing Model By Soroush Ghazi; Mark Schneider
  4. Deep Learning for Asset Bubbles Detection By Oksana Bashchenko; Alexis Marchal
  5. Cross-sectional Stock Price Prediction using Deep Learning for Actual Investment Management By Masaya Abe; Kei Nakagawa
  6. Using Reinforcement Learning in the Algorithmic Trading Problem By Evgeny Ponomarev; Ivan Oseledets; Andrzej Cichocki
  7. AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment By Tianping Zhang; Yuanqi Li; Yifei Jin; Jian Li
  8. Firms Default Prediction with Machine Learning By Tesi Aliaj; Aris Anagnostopoulos; Stefano Piersanti
  9. Trimming the Sail: A Second-order Learning Paradigm for Stock Prediction By Chi Chen; Li Zhao; Wei Cao; Jiang Bian; Chunxiao Xing
  10. Central Clearing and Systemic Liquidity Risk By G. Thomas Kingsley; Anna L. Paulson; Todd Prono; Travis D. Nesmith

  1. By: Daniel Barth (Office of Financial Research); Juha Joenvaara (School of Business, Aalto University); Mikko Kauppila (Oulu Business School, University of Oulu); Russ Wermers (Smith School of Business, University of Maryland at College Park)
    Abstract: Of first-order importance to the study of potential systemic risks in hedge funds is the aggregate size of the industry. The worldwide hedge fund industry has been estimated by regulators and industry experts as having total net assets under management of $2.3 - 3.7 trillion as of the end of 2016. Using a newly combined database of several hedge fund information vendors, augmented by the first detailed, systematic regulatory collection of data on large hedge funds in the United States, we estimate that the worldwide net assets under management were at least $5.2 trillion in 2016, over 40% larger than the most generous estimate. Gross assets, which represent the balance sheet value of hedge fund assets, exceeds $8.5 trillion. We further decompose hedge fund assets by their self-reported strategy and by fund domicile. We also show that the total returns earned by funds that report to the public databases are significantly lower than the returns of funds that report only on regulatory filings, both in aggregate and within nearly every fund strategy. This difference appears to be driven entirely by alpha, rather than by differences in exposures to systemic risk factors. However, net investor flows are considerably higher for funds reporting publicly, suggesting previous estimates of the flow-performance relationship are likely biased. Our new, and much larger, estimates of the size of the hedge fund industry should help regulators and prudential authorities to better gauge the systemic risks posed by the industry, and to better evaluate potential data gaps in private funds. Our results aslo suggest that systemic risk is roughly similar in publicly and non-publicly reporting funds.
    Keywords: hedge funds, net assets, gross assets, strategy, domicile, returns, flows
    Date: 2020–02–25
  2. By: Daniel Barth (Office of Financial Research); Laurel Hammond (Office of Financial Research); Phillip Monin (Office of Financial Research)
    Abstract: The use of leverage is often considered a key potential systemic risk in hedge funds. Yet, data limitations have made empirical analyses of hedge fund leverage difficult. Traditional theories predict leverage and portfolio risk are positively linearly related. Alternatively, an emerging wave of theories of leverage constraints predict leverage and asset risk are negatively correlated, and therefore leverage and portfolio risk may be unrelated or even negatively related. Consistent with theories of leverage constraints, we find that hedge fund leverage and portfolio risk are weakly negatively correlated. This arises from a strong negative association between leverage and asset risk - in particular, market beta. The average market beta on funds' assets explains 20% of the cross-sectional variation in hedge fund leverage, and 47% for the subsample of equity-style funds. Also consistent with these theories, leverage and portfolio alpha are strongly positively related, but this relationship is entirely explained by market beta. Our findings suggest that the association between leverage and risk in hedge funds is nuanced, and that leverage is in part used to scale the payoffs of low-beta, high-alpha securities, resulting in an essentially flat relationship between leverage and portfolio risk.
    Keywords: hedge funds, leverage, systemic risk, financial stability, low beta anomaly
    Date: 2020–02–25
  3. By: Soroush Ghazi (Culverhouse College of Business, University of Alabama); Mark Schneider (Culberhouse College of Business, University of Alabama and Economic Science Institute, Chapman University)
    Abstract: What is market sentiment? This paper takes a new approach to this question and derives a formula for market sentiment as a function of the risk-free rate, the price/dividend ratio, and the conditional stock market volatility. The formula is derived from a representative agent with a prospect theory probability weighting function. We estimate the model and nd that our sentiment measure correlates positively with the leading sentiment indexes. The model matches the equity premium while generating a low and stable risk-free rate with low risk aversion. We also apply the model to explain other anomalies for the aggregate stock market.
    Keywords: Sentiment; Prospect Theory; Equity Premium Puzzle; Pricing Kernel Puzzle; Sentiment Indexes
    Date: 2020
  4. By: Oksana Bashchenko; Alexis Marchal
    Abstract: We develop a methodology for detecting asset bubbles using a neural network. We rely on the theory of local martingales in continuous-time and use a deep network to estimate the diffusion coefficient of the price process more accurately than the current estimator, obtaining an improved detection of bubbles. We show the outperformance of our algorithm over the existing statistical method in a laboratory created with simulated data. We then apply the network classification to real data and build a zero net exposure trading strategy that exploits the risky arbitrage emanating from the presence of bubbles in the US equity market from 2006 to 2008. The profitability of the strategy provides an estimation of the economical magnitude of bubbles as well as support for the theoretical assumptions relied on.
    Date: 2020–02
  5. By: Masaya Abe; Kei Nakagawa
    Abstract: Stock price prediction has been an important research theme both academically and practically. Various methods to predict stock prices have been studied until now. The feature that explains the stock price by a cross-section analysis is called a "factor" in the field of finance. Many empirical studies in finance have identified which stocks having features in the cross-section relatively increase and which decrease in terms of price. Recently, stock price prediction methods using machine learning, especially deep learning, have been proposed since the relationship between these factors and stock prices is complex and non-linear. However, there are no practical examples for actual investment management. In this paper, therefore, we present a cross-sectional daily stock price prediction framework using deep learning for actual investment management. For example, we build a portfolio with information available at the time of market closing and invest at the time of market opening the next day. We perform empirical analysis in the Japanese stock market and confirm the profitability of our framework.
    Date: 2020–02
  6. By: Evgeny Ponomarev; Ivan Oseledets; Andrzej Cichocki
    Abstract: The development of reinforced learning methods has extended application to many areas including algorithmic trading. In this paper trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards. A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures. The application of recurrent layers in this approach is investigated. The experiments were performed on real anonymized data. The best architecture demonstrated a trading strategy for the RTS Index futures (MOEX:RTSI) with a profitability of 66% per annum accounting for commission. The project source code is available via the following link:
    Date: 2020–02
  7. By: Tianping Zhang; Yuanqi Li; Yifei Jin; Jian Li
    Abstract: The multi-factor model is a widely used model in quantitative investment. The success of a multi-factor model is largely determined by the effectiveness of the alpha factors used in the model. This paper proposes a new evolutionary algorithm called AutoAlpha to automatically generate effective formulaic alphas from massive stock datasets. Specifically, first we discover an inherent pattern of the formulaic alphas and propose a hierarchical structure to quickly locate the promising part of space for search. Then we propose a new Quality Diversity search based on the Principal Component Analysis (PCA-QD) to guide the search away from the well-explored space for more desirable results. Next, we utilize the warm start method and the replacement method to prevent the premature convergence problem. Based on the formulaic alphas we discover, we propose an ensemble learning-to-rank model for generating the portfolio. The backtests in the Chinese stock market and the comparisons with several baselines further demonstrate the effectiveness of AutoAlpha in mining formulaic alphas for quantitative trading.
    Date: 2020–02
  8. By: Tesi Aliaj; Aris Anagnostopoulos; Stefano Piersanti
    Abstract: Academics and practitioners have studied over the years models for predicting firms bankruptcy, using statistical and machine-learning approaches. An earlier sign that a company has financial difficulties and may eventually bankrupt is going in \emph{default}, which, loosely speaking means that the company has been having difficulties in repaying its loans towards the banking system. Firms default status is not technically a failure but is very relevant for bank lending policies and often anticipates the failure of the company. Our study uses, for the first time according to our knowledge, a very large database of granular credit data from the Italian Central Credit Register of Bank of Italy that contain information on all Italian companies' past behavior towards the entire Italian banking system to predict their default using machine-learning techniques. Furthermore, we combine these data with other information regarding companies' public balance sheet data. We find that ensemble techniques and random forest provide the best results, corroborating the findings of Barboza et al. (Expert Syst. Appl., 2017).
    Date: 2020–02
  9. By: Chi Chen; Li Zhao; Wei Cao; Jiang Bian; Chunxiao Xing
    Abstract: Nowadays, machine learning methods have been widely used in stock prediction. Traditional approaches assume an identical data distribution, under which a learned model on the training data is fixed and applied directly in the test data. Although such assumption has made traditional machine learning techniques succeed in many real-world tasks, the highly dynamic nature of the stock market invalidates the strict assumption in stock prediction. To address this challenge, we propose the second-order identical distribution assumption, where the data distribution is assumed to be fluctuating over time with certain patterns. Based on such assumption, we develop a second-order learning paradigm with multi-scale patterns. Extensive experiments on real-world Chinese stock data demonstrate the effectiveness of our second-order learning paradigm in stock prediction.
    Date: 2020–02
  10. By: G. Thomas Kingsley; Anna L. Paulson (Federal Reserve Bank of Chicago); Todd Prono; Travis D. Nesmith
    Abstract: By stepping between bilateral counterparties, a central counterparty (CCP) transforms credit exposure. CCPs generally improve financial stability. Nevertheless, large CCPs are by nature concentrated and interconnected with major global banks. Moreover, although they mitigate credit risk, CCPs create liquidity risks, because they rely on participants to provide cash. Such requirements increase with both market volatility and default; consequently, CCP liquidity needs are inherently procyclical. This procyclicality makes it more challenging to assess CCP resilience in the rare event that one or more large financial institutions default. Liquidity-focused macroprudential stress tests could help to assess and manage this systemic liquidity risk.
    Keywords: margin; financial systems; Central Counterparties (CCPs); procyclicality; liquidity risk; financial stability
    JEL: G28 E58 N22 G21 G23
    Date: 2019–12–01

This nep-fmk issue is ©2020 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.