nep-fmk New Economics Papers
on Financial Markets
Issue of 2019‒09‒09
eleven papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Predicting Returns With Text Data By Zheng Tracy Ke; Bryan T. Kelly; Dacheng Xiu
  2. HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction By Raehyun Kim; Chan Ho So; Minbyul Jeong; Sanghoon Lee; Jinkyu Kim; Jaewoo Kang
  3. Stock Price Forecasting and Hypothesis Testing Using Neural Networks By Kerda Varaku
  4. Becker Meets Kyle: Inside Insider Trading By Kacperczyk, Marcin; Pagnotta, Emiliano
  5. Christmas Jump in LIBOR By Vikenty Mikheev; Serge E. Miheev
  6. Interdependency between the Stock Market and Financial News By EunJeong Hwang; Yong-Hyuk Kim
  7. Are Bitcoins price predictable? Evidence from machine learning techniques using technical indicators By Samuel Asante Gyamerah
  8. Momentum and Disposition Effect in the stock market of USA By Ranjeeta Sadhwani; Mujeeb U Rehman Bhayo
  9. The relationship between announcements of complete mergers and acquisitions and acquirers' abnormal CDS spread changes By Benjamin Hippert
  10. On the stability of Stock-bond comovements across market conditions in the Eurozone periphery By Thomas J.Flavin; Dolores Lagoa-Varela
  11. Determinants of CDS trading on major banks By Benjamin Hippert; André Uhde; Sascha Tobias Wengerek

  1. By: Zheng Tracy Ke; Bryan T. Kelly; Dacheng Xiu
    Abstract: We introduce a new text-mining methodology that extracts sentiment information from news articles to predict asset returns. Unlike more common sentiment scores used for stock return prediction (e.g., those sold by commercial vendors or built with dictionary-based methods), our supervised learning framework constructs a sentiment score that is specifically adapted to the problem of return prediction. Our method proceeds in three steps: 1) isolating a list of sentiment terms via predictive screening, 2) assigning sentiment weights to these words via topic modeling, and 3) aggregating terms into an article-level sentiment score via penalized likelihood. We derive theoretical guarantees on the accuracy of estimates from our model with minimal assumptions. In our empirical analysis, we text-mine one of the most actively monitored streams of news articles in the financial system—the Dow Jones Newswires—and show that our supervised sentiment model excels at extracting return-predictive signals in this context.
    JEL: C53 C58 G10 G11 G12 G14 G17
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:nbr:nberwo:26186&r=all
  2. By: Raehyun Kim; Chan Ho So; Minbyul Jeong; Sanghoon Lee; Jinkyu Kim; Jaewoo Kang
    Abstract: Many researchers both in academia and industry have long been interested in the stock market. Numerous approaches were developed to accurately predict future trends in stock prices. Recently, there has been a growing interest in utilizing graph-structured data in computer science research communities. Methods that use relational data for stock market prediction have been recently proposed, but they are still in their infancy. First, the quality of collected information from different types of relations can vary considerably. No existing work has focused on the effect of using different types of relations on stock market prediction or finding an effective way to selectively aggregate information on different relation types. Furthermore, existing works have focused on only individual stock prediction which is similar to the node classification task. To address this, we propose a hierarchical attention network for stock prediction (HATS) which uses relational data for stock market prediction. Our HATS method selectively aggregates information on different relation types and adds the information to the representations of each company. Specifically, node representations are initialized with features extracted from a feature extraction module. HATS is used as a relational modeling module with initialized node representations. Then, node representations with the added information are fed into a task-specific layer. Our method is used for predicting not only individual stock prices but also market index movements, which is similar to the graph classification task. The experimental results show that performance can change depending on the relational data used. HATS which can automatically select information outperformed all the existing methods.
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1908.07999&r=all
  3. By: Kerda Varaku
    Abstract: In this work we use Recurrent Neural Networks and Multilayer Perceptrons to predict NYSE, NASDAQ and AMEX stock prices from historical data. We experiment with different architectures and compare data normalization techniques. Then, we leverage those findings to question the efficient-market hypothesis through a formal statistical test.
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1908.11212&r=all
  4. By: Kacperczyk, Marcin; Pagnotta, Emiliano
    Abstract: How do illegal insiders trade on private information? Do they internalize legal risk? Using hand-collected data on insiders prosecuted by the SEC, we find that, consistent with Kyle (1985), insiders manage trade size and timing according to market conditions and the value of information. Gender, age, and profession play a lesser role. Various shocks to penalties and likelihood of prosecution show that insiders internalize legal risk by moderating aggressiveness, providing support to regulators' deterrence ability. Consistent with Becker (1968), following positive shocks to expected penalties, insiders concentrate on fewer signals of higher value. Thus, enforcement actions could hamper price informativeness.
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:cpr:ceprdp:13928&r=all
  5. By: Vikenty Mikheev; Serge E. Miheev
    Abstract: A short-term pattern in LIBOR dynamics was discovered. Namely, 2-month LIBOR experiences a jump after Xmas. The sign and size of the jump depend on the data trend on 21 days before Xmas.
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1908.10014&r=all
  6. By: EunJeong Hwang; Yong-Hyuk Kim
    Abstract: Stock prices are driven by various factors. In particular, many individual investors who have relatively little financial knowledge rely heavily on the information from news stories when making investment decisions in the stock market. However, these stories may not reflect future stock prices because of the subjectivity in the news; stock prices may instead affect the news contents. This study aims to discover whether it is news or stock prices that have a greater impact on the other. To achieve this, we analyze the relationship between news sentiment and stock prices based on time series analysis using five different classification models. Our experimental results show that stock prices have a bigger impact on the news contents than news does on stock prices.
    Date: 2019–09
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1909.00344&r=all
  7. By: Samuel Asante Gyamerah
    Abstract: The uncertainties in future Bitcoin price make it difficult to accurately predict the price of Bitcoin. Accurately predicting the price for Bitcoin is therefore important for decision-making process of investors and market players in the cryptocurrency market. Using historical data from 01/01/2012 to 16/08/2019, machine learning techniques (Generalized linear model via penalized maximum likelihood, random forest, support vector regression with linear kernel, and stacking ensemble) were used to forecast the price of Bitcoin. The prediction models employed key and high dimensional technical indicators as the predictors. The performance of these techniques were evaluated using mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R-squared). The performance metrics revealed that the stacking ensemble model with two base learner (random forest and generalized linear model via penalized maximum likelihood) and support vector regression with linear kernel as meta-learner was the optimal model for forecasting Bitcoin price. The MAPE, RMSE, MAE, and R-squared values for the stacking ensemble model were 0.0191%, 15.5331 USD, 124.5508 USD, and 0.9967 respectively. These values show a high degree of reliability in predicting the price of Bitcoin using the stacking ensemble model. Accurately predicting the future price of Bitcoin will yield significant returns for investors and market players in the cryptocurrency market.
    Date: 2019–09
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1909.01268&r=all
  8. By: Ranjeeta Sadhwani (Sukkur IBA University, Sindh); Mujeeb U Rehman Bhayo (Sukkur IBA University, Sindh)
    Abstract: This paper analyze whether momentum effect drives disposition effect and vice versa during the period of January 1963 to 2017 in the stock market of USA. To examine the relationship, Fama and Macbeth (1973) cross sectional regressions are performed in the study. The results show that disposition effect drives momentum but not the other way around. Furthermore, this relationship is also examined for three sub-samples, and we find that relationship between momentum and disposition effect varies over the time and one possible reason could be crisis as sample is divided on the basis of the dot-com bubble and global financial crisis. Another finding of the study is that along with the disposition effect, size also has an impact on the momentum effect. To further analyze the impact of size on momentum and disposition effect, we test the relationship between momentum and disposition effect on the basis of size deciles. The results demonstrate that relationship does not vary significantly over the size of stocks but it does have an impact on momentum and disposition effect as past cumulative returns, and capital gain varies monotonically with the increase in the size of stocks.
    Keywords: Momentum, Disposition effect, Fama-Macbeth regression, Behavioral Finance, Size effect
    JEL: M20 D89 C01
    Date: 2019–07
    URL: http://d.repec.org/n?u=RePEc:sek:iefpro:8911340&r=all
  9. By: Benjamin Hippert (University of Paderborn)
    Abstract: Employing a sample of 492 merger and acquisition (M&A) announcements from 284 acquirers across North America and Europe between 2005 and 2018, this study analyzes the impact of M&A announcements on an acquirers abnormal CDS spread changes. We find that spreads from CDS which are written on acquirers increase by 310 bps during a symmetric five-day event window suggesting that investors expect an increase in the acquirers credit risk exposure due to M&As. Next to this baseline finding, we conduct a large variety of sensitivity analyses to gain more insight into the driving factors of the rising risk perception of CDS investors due to M&A announcements.
    Keywords: credit default swaps, risk perception of CDS investors, mergers and acquisitions, event study
    JEL: G14 G34
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:pdn:dispap:52&r=all
  10. By: Thomas J.Flavin (Economics, National University of Ireland, Maynooth); Dolores Lagoa-Varela (Universidade da Coruña, Spain)
    Abstract: We analyze the relationship between returns on equity and long-term government bonds in the crisis-hit Eurozone peripheral economies. In particular, we are interested in the stability of the relationship across differing market conditions and if long-term bonds act as a safe haven for equity investors during periods of financial distress. Employing a Markov-switching vector autoregression model with three regimes, we find that the stock-bond relationship varies across market conditions and across countries. Overall we observe increased comovement during the crisis regimes at the market level, with the relationship between the financial sectors and the domestic sovereign bond being its most important driver across countries.
    Keywords: : Stock-bond relationship; Eurozone peripheral countries; financial crisis; safe haven.
    JEL: G01 G11 C32
    Date: 2019
    URL: http://d.repec.org/n?u=RePEc:may:mayecw:n295-19.pdf&r=all
  11. By: Benjamin Hippert (University of Paderborn); André Uhde (University of Paderborn); Sascha Tobias Wengerek (University of Paderborn)
    Abstract: Employing credit default swap (CDS) data for a sample of 52 major banks across 18 countries from 2008 to 2016, this paper investigates determinants of the outstanding net notional amount of CDS which are written on banks. We extend the current literature dealing with CDS trading by analyzing further CDS trading-specific, fundamental bank-specific as well as macroeconomic and institutional determinants with a focus on bank CDS trading. We find that, next to well-discussed determinants for corporate firms in the literature, especially a bank's tail risk, capital adequacy, loan portfolio and business model affect a bank's outstanding CDS net notional. This finding indicates that investors in the bank CDS market partly have a recourse to a fundamental analysis for their investment decision. Our study fills an important gap since empirical studies have solely focused on sovereign and corporate CDS yet. In addition, the analysis at hand provides important implications for both academics and practitioners since understanding the trading motives of bank CDS investors gives deeper insights into the still opaque CDS market.
    Keywords: banking, outstanding CDS net notional, determinants of bank CDS trading
    JEL: G10 G12 G21
    Date: 2019–08
    URL: http://d.repec.org/n?u=RePEc:pdn:dispap:51&r=all

This nep-fmk issue is ©2019 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 http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. 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.