Predicting Stock Price Falls Using News Data: Evidence from the Brazilian Market
- PDF / 1,356,447 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 37 Downloads / 217 Views
Predicting Stock Price Falls Using News Data: Evidence from the Brazilian Market Juvenal José Duarte1 · Sahudy Montenegro González1 · José César Cruz Jr1 Accepted: 15 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Market participants use a wide set of information before they decide to invest in risk assets, such as stocks. Investors often follow the news to collect the information that will help them decide which strategy to follow. In this study, we analyze how public news and historical prices can be used together to anticipate and prevent financial losses on the Brazilian stock market. We include an extensive set of 64 securities in our analysis, which represent various sectors of the Brazilian economy. Our analysis compares the traditional Buy & Hold and the moving average strategies to several experiments designed with 11 machine learning algorithms. We explore daily, weekly and monthly time horizons for both publication and return windows. With this approach we were able to assess the most relevant set of news for investor’s decision, and to determine for how long the information remains relevant to the market. We found a strong relationship between news publications and stock price changes in Brazil, suggesting even short-term arbitrage opportunities. The study shows that it is possible to predict stock price falls using a set of news in Portuguese, and that text mining-based approaches can overcome traditional strategies when forecasting losses. Keywords Text mining · Brazilian Portuguese news · Brazilian stock market · Price forecasting · Machine learning algorithms
* Sahudy Montenegro González [email protected] Juvenal José Duarte [email protected] José César Cruz Jr [email protected] 1
School of Management and Technology, Federal University of São Carlos - UFSCar Sorocaba, São Paulo 18052‑780, Brazil
13
Vol.:(0123456789)
J. J. Duarte et al.
1 Introduction After the 2008 global financial crisis, international interest rates reached historical low levels, especially in developed countries such as the United States, the U.K., and Japan (Del Negro et al. 2019). Even though interest rates in developing countries are still relatively high, several countries tried to use monetary policy to reduce their interest rate levels during the same period. For instance, according to Fund (2019), the Brazilian monetary policy-related interest rate was cut by roughly 84% since 2008, from 13.75 to 2.25% APR, in 2020. Interest rate cuts directly impact the levels of national debts and indirectly impact firms’ and individuals’ decisions to invest in real and financial assets. The study developed by Bernanke and Reinhart (2004) highlights that economic decisions are affected by prices and yields of financial assets, which are influenced by changes in interest rates promoted by monetary policy. As an example, we can assume that, when low-risk asset yields decrease, investors become more likely to face more risk to increase their portfolio returns. Therefore, we can
Data Loading...