Apr 26, 2013
#Google searches can predict stock markets
Using the keyword "debt"... the strategy netted a whopping cyber-profit of 326pc over seven years
Google searches can predict stock markets, study finds - Telegraph
Researchers led by Tobias Preis at Warwick Business School analysed data from Google Trends from 2004 to 2011.
They looked at the volume of searches for 98 terms, such as "metals", "stock", "finance", "forex", "house", "unemployment" and "health" as well as non-specific or neutral words, such as "ring", "train", kitchen" and "fun".
They then constructed a virtual portfolio of investment in the Dow Jones Industrial Average (DJIA), with a strategy based on search volumes that occurred on Sundays.
If the search volume that day was high compared with a week earlier, the DJIA investment was systematically sold at the closing price the following day, and then repurchased at the end of the first day of trading in the week after.
Conversely, if the search volume on Sunday was low compared with the previous week, the researchers "bought" the following day.
Using the keyword "debt" - the term that saw the most fluctuation during the study period - the strategy netted a whopping cyber-profit of 326pc over seven years.
By comparison, a strategy of buy-and-hold - purchasing in 2004 and selling in 2011 - would have yielded only 16pc profit, equal to the rise in the DJIA during this time.
A third strategy, of buying or selling on the basis of movements in the Dow itself, would have netted a gain of 33pc.
The paper, published in the journal Scientific Reports, suggests that search requests are a potential indicator of intent about investment decisions.
When a mass of people seek information about a particular subject on a Sunday, this is a sign of worry and boosts the likelihood that they will ditch stock when the market opens on the Monday, it argues.
"Notable drops in the financial market are preceded by periods of investor concern," according to the research.
"In such periods, investors may search for more information about the market, before eventually deciding to buy or sell.
"Our results suggest that, following this logic, during the period 2004 to 2011, Google Trends search query volumes for certain terms could have been used in the construction of profitable trading strategies."
In a phone interview with AFP, Mr Preis said that the online world was a goldmine of data for behavioural experts.
"All these new data resources from online activities, which are an essential part of our everyday life these days - we are tweeting on Twitter, we are using Wikipedia, we are using search engines like Google and upload photos to Flickr and share information on Facebook - all of this leaves indicators of behaviour," he said.
"From a scientific point of view, our interest is to link this to behaviour in the real world... it's extremely exciting."
(Edited by Andrew Trotman)
Google searches can predict stock markets, study finds - Telegraph
Subscribe to:
Post Comments (Atom)
ShareThis
MasterSearch
Categories
MasterFeeds
News
Finance
china
USA
money
stocks
debt
Commodities
United States
Gold
Venezuela
Dollars
bonds
Markets
economics
trading
Banks
FED
Hedge funds
Asia
LatAm
Oil
default
Israel
credit
metals
Mining
international relations
russia
central_banks
CapitalMarkets
HFT
democracy
zerohedge
Euro
Silver
elections
India
Iran
Japan
Middle East
SEC
bailout
Africa
Europe
Liberalism
insider trading
Agriculture
FX
Tech
Trade
UN
VC
bitcoin
copper
corruption
real estate
Brazil
CoronaVirus
ForEx
Gold Silver
NYSE
WeWork
chavez
food
Abu Dhabi
Arabs
EU
Facebook
France
Hamas
IPO
Maduro
SWF
TARP
Trump
Turkey
canada
goldman
government
recession
revolution
war
Cannabis
Capitalism
Citigroup
Democrats
EIA
Hezbollah
Jobs
Lebanon
NASDAQ
NYC
PDVSA
Palestinians
Saudi Arabia
Softbank
Stats
Syria
Ukraine
demographics
ponzi
socialism
13F
AIG
Advertising
Berkshire Hathaway
CBO
Cargill
Colombia
Cryptocurrency
ETF
Ecuador
Emerging Markets
Eton Park
Google
Housing
IMF
LME
Mindich
Mongolia
OPEC
PIIGS
Pakistan
Palantir
Paulson
Pensions
Peru
Politics
Potash
QE
Scams
Singapore
Spain
UK
Yuan
blockchain
companies
crash
cybersecurity
data
freedom
humor
islam
kleptocracy
nuclear
propaganda
social networks
startups
terrorism
Airlines
Andorra
Angola
Anti-Israel
Apple
Automobiles
BAC
BHP
Blackstone
COMEX
Caracas
Coal
Communism
Crypto
DRC
DSK
Double-Dip
EOS
Egypt
FT
Fannie Mae
Form
Foxconn
Freddie
GM
Gbagbo
History
ICO
Iraq
Italy
Ivanhoe
Ivory Coast
JPM
Juan Guaido
Lava Jato
Libya
London
M+A
MasterEnergy
Mc Donald's
Miami
Mugabe
Norway
Norwegian
Odebrecht
Oyo
PA
PPT
Panama
QE2
Republicans
Rio
Ron Paul
ShengNu
Soleimani
South Africa
Tokens
Tunisia
UN Watch
UNESCO
UNHRC
Uber
VW
Wyclef
anti-semitism
apparel
bang dae-ho
cash
censorship
chile
clothing
coffee
cotton
derivatives
emplyment
foreclosures
frontrunning
haiti
infrastructure
labor
levi's
mortgages
philosophy
shipping
social media
treasury
women
No comments:
Post a Comment
___________________________________
Commented on The MasterFeeds