nep-fmk New Economics Papers
on Financial Markets
Issue of 2023‒05‒29
seven papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Stock Price Predictability and the Business Cycle via Machine Learning By Li Rong Wang; Hsuan Fu; Xiuyi Fan
  2. Stock Market Volatility and Multi-Scale Positive and Negative Bubbles By Rangan Gupta; Jacobus Nel; Joshua Nielsen; Christian Pierdzioch
  3. Money market funds and the pricing of near-money assets By Sebastian Doerr; Sebastian Egemen Eren; Semyon Malamud
  4. Deep Stock: training and trading scheme using deep learning By Sungwoo Kang
  5. The impact of the AI revolution on asset management By Michael Kopp
  6. Identifying Trades Using Technical Analysis and ML/DL Models By Aayush Shah; Mann Doshi; Meet Parekh; Nirmit Deliwala; Prof. Pramila M. Chawan
  7. Maximally Machine-Learnable Portfolios By Philippe Goulet Coulombe; Maximilian Gobel

  1. By: Li Rong Wang; Hsuan Fu; Xiuyi Fan
    Abstract: We study the impacts of business cycles on machine learning (ML) predictions. Using the S&P 500 index, we find that ML models perform worse during most recessions, and the inclusion of recession history or the risk-free rate does not necessarily improve their performance. Investigating recessions where models perform well, we find that they exhibit lower market volatility than other recessions. This implies that the improved performance is not due to the merit of ML methods but rather factors such as effective monetary policies that stabilized the market. We recommend that ML practitioners evaluate their models during both recessions and expansions.
    Date: 2023–04
  2. By: Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Jacobus Nel (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Joshua Nielsen (Boulder Investment Technologies, LLC, 1942 Broadway Suite 314C, Boulder, CO, 80302, USA); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany)
    Abstract: We study whether booms and busts in the stock market of the United States (US) drives its volatility. Given this, first, we employ the Multi-Scale Log-Periodic Power Law Singularity Confidence Indicator (MS-LPPLS-CI) approach to identify both positive and negative bubbles in the short-, medium, and long-term. We successfully detect major crashes and rallies during the weekly period from January 1973 to December 2020. Second, we utilize a nonparametric causality-in-quantiles approach to analyze the predictive impact of our bubble indicators on daily data-based weekly realized volatility (RV). This econometric framework allows us to circumvent potential misspecification due to nonlinearity and instability, rendering the results of weak causal influence derived from a linear framework invalid. The MS-LPPLS-CIs reveal strong evidence of predictability for RV over its entire conditional distribution. We observe relatively stronger impacts for the positive bubbles indicators, with our findings being robust to an alternative metric of volatility, namely squared returns, and weekly realized volatilities derived from 5 (RV5)- and 10 (RV10)-minutes interval intraday data. Furthermore, we detect evidence of predictability for RV5 and RV10 of nine other developed and emerging stock markets. Finally, we also find strong evidence of causal feedbacks from RV5 and RV10 on to the MS-LPPLS-CIs of the 10 countries considered. Our findings have significant implications for investors and policymakers.
    Keywords: Multi-Scale Positive and Negative Bubbles, Realized Volatility, Nonparametric Causality-in-Quantiles Test, International Stock Markets
    JEL: C22 G15
    Date: 2023–05
  3. By: Sebastian Doerr; Sebastian Egemen Eren; Semyon Malamud
    Abstract: US money market funds (MMFs) play an important role in short-term markets as large investors of Treasury bills (T-bills) and repurchase agreements (repos). We build a theoretical model in which MMFs strategically interact with banks and each other. These interactions generate interdependencies between repo and T-bill markets, affecting the pricing of these near-money assets. Consistent with the model's predictions, we empirically show that when MMFs allocate more cash to the T-bill market, T-bill rates fall, and the liquidity premium on T-bills rises. To establish causality, we devise instrumental variables guided by our theory. Using a granular holding-level dataset to examine the channels, we show that MMFs internalize their price impact in the T-bill market when they set repo rates and tilt their portfolios towards repos with the Federal Reserve when Treasury market liquidity is low. Our results have implications for the transmission of monetary policy, benchmark rates, and government debt issuance.
    Keywords: T-bills, repo, money market funds, near-money assets, liquidity
    JEL: E44 G11 G12 G23
    Date: 2023–05
  4. By: Sungwoo Kang
    Abstract: Despite the efficient market hypothesis, many studies suggest the existence of inefficiencies in the stock market, leading to the development of techniques to gain above-market returns, known as alpha. Systematic trading has undergone significant advances in recent decades, with deep learning emerging as a powerful tool for analyzing and predicting market behavior. In this paper, we propose a model inspired by professional traders that look at stock prices of the previous 600 days and predicts whether the stock price rises or falls by a certain percentage within the next D days. Our model, called DeepStock, uses Resnet's skip connections and logits to increase the probability of a model in a trading scheme. We test our model on both the Korean and US stock markets and achieve a profit of N\% on Korea market, which is M\% above the market return, and profit of A\% on US market, which is B\% above the market return.
    Date: 2023–04
  5. By: Michael Kopp
    Abstract: Recent progress in deep learning, a special form of machine learning, has led to remarkable capabilities machines can now be endowed with: they can read and understand free flowing text, reason and bargain with human counterparts, translate texts between languages, learn how to take decisions to maximize certain outcomes, etc. Today, machines have revolutionized the detection of cancer, the prediction of protein structures, the design of drugs, the control of nuclear fusion reactors etc. Although these capabilities are still in their infancy, it seems clear that their continued refinement and application will result in a technological impact on nearly all social and economic areas of human activity, the likes of which we have not seen before. In this article, I will share my view as to how AI will likely impact asset management in general and I will provide a mental framework that will equip readers with a simple criterion to assess whether and to what degree a given fund really exploits deep learning and whether a large disruption risk from deep learning exist.
    Date: 2023–04
  6. By: Aayush Shah; Mann Doshi; Meet Parekh; Nirmit Deliwala; Prof. Pramila M. Chawan
    Abstract: The importance of predicting stock market prices cannot be overstated. It is a pivotal task for investors and financial institutions as it enables them to make informed investment decisions, manage risks, and ensure the stability of the financial system. Accurate stock market predictions can help investors maximize their returns and minimize their losses, while financial institutions can use this information to develop effective risk management policies. However, stock market prediction is a challenging task due to the complex nature of the stock market and the multitude of factors that can affect stock prices. As a result, advanced technologies such as deep learning are being increasingly utilized to analyze vast amounts of data and provide valuable insights into the behavior of the stock market. While deep learning has shown promise in accurately predicting stock prices, there is still much research to be done in this area.
    Date: 2023–04
  7. By: Philippe Goulet Coulombe (University of Quebec in Montreal); Maximilian Gobel (Bocconi University)
    Abstract: When it comes to stock returns, any form of predictability can bolster risk-adjusted profitability. We develop a collaborative machine learning algorithm that optimizes portfolio weights so that the resulting synthetic security is maximally predictable. Precisely, we introduce MACE, a multivariate extension of Alternating Conditional Expectations that achieves the aforementioned goal by wielding a Random Forest on one side of the equation, and a constrained Ridge Regression on the other. There are two key improvements with respect to Lo and MacKinlay’s original maximally predictable portfolio approach. First, it accommodates for any (nonlinear) forecasting algorithm and predictor set. Second, it handles large portfolios. We conduct exercises at the daily and monthly frequency and report significant increases in predictability and profitability using very little conditioning information. Interestingly, predictability is found in bad as well as good times, and MACE successfully navigates the debacle of 2022.
    Date: 2023–04

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.