Stock‐induced Google trends and the predictability of sectoral stock returns

Abstract

In this paper, we consider Google trends (G-trends) as a measure of investors' attention in the predictability of stock returns across eleven major US sectors. The theoretical motivation for our paper is clear. In seeking information to guide investment decisions, investors' sentiments are shaped by news such as G-trends that could induce changes in the prices of stocks. Thus, we construct a predictive model that incorporates G-trends series as a predictor of stock returns and thereafter we account for evident asymmetry in G-trends to analyze the signficance of positive-and negative-worded news in the predictability of stock returns. We also compare single-and multi-factor predictive models augmented with distinctive statistical effects against the baseline time series model. We highlight three key findings: (1) G-trends record consistent negative correlations with stock returns across sectors. ( 2) The proposed predictive model with G-trends outperforms the baseline (random walk) model. (3) The inclusion of asymmetry and macroeconomic variables improves the outperformance of G-trends over the baseline model.

An information‐based index of uncertainty and the predictability of energy prices

“…Second, we employ the index to examine the vulnerability of energy pricing for different energy proxies (Brent oil, diesel, gasoline, heating oil, kerosene, natural gas, propane, and WTI oil) to COVID‐19 pandemic. This aligns with extant researches that have shown the relevance of the Google Trends data to facilitate predictability of financial and economic series (see 24,25 ; among others). Third, we account for salient data features, such as structural breaks, persistence, conditional heteroscedasticity, and autocorrelation, as well as day‐of‐the‐week effect following, 26,27 within a single predictive model, following Westerlund and Narayan 28,29 .…”

“…The model is used, also with partially decomposed sums in a bid to examine the asymmetric effect. The COVID‐19 induced uncertainty ( ciu t ) is decomposed into positive and negative partial sums, which are defined as and respectively (see 24,25,30,32 ; among others).…”

Pandemics and the emerging stock markets

“…The economic consequences revealed by the novel coronavirus (COVID-19) pandemic have brought to the fore the need to better understand pandemics and how they affect economic activities including the stock market. The theoretical basis for studying the pandemics–stocks nexus lies in the argument that stock prices, returns and volatility respond to news and macroeconomic conditions that shape investors’ sentiments about the level of uncertainty in financial markets (see Haroon & Rizvi, 2020a , 2020b ; Narayan, 2019 , 2020 ; Salisu, Ogbonna, & Adediran, 2020 , among others). During pandemics, like during wars, natural disasters and financial crises, the level of uncertainty in the markets is exceptionally high, and so is the level of risk aversion among investors (see Eichenbaum et al., 2020 ; Haroon & Rizvi, 2020b ; Ma et al., 2020 ; Qadan, 2019 ; Salisu & Akanni, 2020 ).…”

OPEC News and Exchange Rate Forecasting Using Dynamic Bayesian Learning

“…In this paper, we analyse the ability of the information content of a newspaper articles count index related to OPEC meetings and events connected with its production levels to forecast 9 To make our results based on the GOPEC1 and GOPEC2 perfectly comparable with those obtained by Beckmann et al, (2020) with the alternative predictors and the RW model they use, we use the same exchange rate returns as these authors, derived from a different source (DataStream). 10 A number of studies suggest using Google search volume for constructing news-based indexes for return predictability (see Salisu et al, (2020b) for a review).…”