TY - JOUR
T1 - Google search keywords that best predict energy price volatility
AU - Afkhami, Mohamad
AU - Cormack, Lindsey
AU - Ghoddusi, Hamed
N1 - Publisher Copyright:
© 2017
PY - 2017/9
Y1 - 2017/9
N2 - Internet search activity data has been widely used as an instrument to approximate trader attention in different markets. This method has proven effective in predicting market indices in the short-term. However, little attention has been paid to demonstrating search activity for keywords that best grab investor attention in different markets. This study attempts to build the best practically possible proxy for attention in the market for energy commodities using Google search data. Specifically, we confirm the utility of Google search activity for energy related keywords are significant predictors of volatility by showing they have incremental predictive power beyond the conventional GARCH models in predicting volatility for energy commodities' prices. Starting with a set of ninety terms used in the energy sector, the study uses a multistage filtering process to create combinations of keywords that best predict the volatility of crude oil (Brent and West Texas Intermediate), conventional gasoline (New York Harbor and US Gulf Coast), heating oil (New York Harbor), and natural gas prices. For each commodity, combinations that enhance GARCH most effectively are established as proxies of attention. The results indicate investor attention is widely reflected in Internet search activities and demonstrate search data for what keywords best reveal the direction of concern and attention in energy markets.
AB - Internet search activity data has been widely used as an instrument to approximate trader attention in different markets. This method has proven effective in predicting market indices in the short-term. However, little attention has been paid to demonstrating search activity for keywords that best grab investor attention in different markets. This study attempts to build the best practically possible proxy for attention in the market for energy commodities using Google search data. Specifically, we confirm the utility of Google search activity for energy related keywords are significant predictors of volatility by showing they have incremental predictive power beyond the conventional GARCH models in predicting volatility for energy commodities' prices. Starting with a set of ninety terms used in the energy sector, the study uses a multistage filtering process to create combinations of keywords that best predict the volatility of crude oil (Brent and West Texas Intermediate), conventional gasoline (New York Harbor and US Gulf Coast), heating oil (New York Harbor), and natural gas prices. For each commodity, combinations that enhance GARCH most effectively are established as proxies of attention. The results indicate investor attention is widely reflected in Internet search activities and demonstrate search data for what keywords best reveal the direction of concern and attention in energy markets.
KW - Energy market
KW - Energy price volatility
KW - Google search activity
KW - Volatility prediction
UR - http://www.scopus.com/inward/record.url?scp=85027565539&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027565539&partnerID=8YFLogxK
U2 - 10.1016/j.eneco.2017.07.014
DO - 10.1016/j.eneco.2017.07.014
M3 - Article
AN - SCOPUS:85027565539
SN - 0140-9883
VL - 67
SP - 17
EP - 27
JO - Energy Economics
JF - Energy Economics
ER -