Quantifying Economic Behaviour Using Big Data Tobias Preis Warwick - - PowerPoint PPT Presentation

quantifying economic behaviour using big data
SMART_READER_LITE
LIVE PREVIEW

Quantifying Economic Behaviour Using Big Data Tobias Preis Warwick - - PowerPoint PPT Presentation

Quantifying Economic Behaviour Using Big Data Tobias Preis Warwick Business School Tobias.Preis@wbs.ac.uk www.tobiaspreis.de A map of the world built only from GPS locations of Flickr photos The big data explosion 1 The advantage of


slide-1
SLIDE 1

Tobias Preis

Warwick Business School Tobias.Preis@wbs.ac.uk www.tobiaspreis.de

Quantifying Economic Behaviour Using Big Data

slide-2
SLIDE 2

The big data explosion

A map of the world built only from GPS locations of Flickr photos ¡

slide-3
SLIDE 3

The advantage of looking forward

1

slide-4
SLIDE 4

Future Orientation Index 2010

0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8

more Google searches for “2009” more Google searches for “2011”

Based on Preis, Moat, Stanley and Bishop (2012)

slide-5
SLIDE 5

Richer countries look forward

B

Future-Orientation Index GDP / Capita [10 4 USD]

1 2 3 4 0.0 0.5 1.0 1.5 2.0

Preis, Moat, Stanley & Bishop (2012) Featured by:

slide-6
SLIDE 6

Photo: Perpetual Tourist

Predicting stock markets

2

slide-7
SLIDE 7

Financial markets: big data

Photo: Perpetual Tourist

slide-8
SLIDE 8

The Internet: big data

slide-9
SLIDE 9

Hypothetical strategy

week t

Moat et al. (2013); Preis et al. (2013)

number of Google searches for keyword

slide-10
SLIDE 10

number of Google searches for keyword week t t-1 t-2 t-3

Moat et al. (2013); Preis et al. (2013)

Hypothetical strategy

slide-11
SLIDE 11

Search volume decreased: BUY stock in week t+1 week t t-1 t-2 t-3

Moat et al. (2013); Preis et al. (2013)

Hypothetical strategy

number of Google searches for keyword

slide-12
SLIDE 12

Search volume decreased: BUY stock in week t+1 Search volume increased: SELL stock in week t+1 week t t-1 t-2 t-3

Moat et al. (2013); Preis et al. (2013)

Hypothetical strategy

number of Google searches for keyword

slide-13
SLIDE 13

−40 40 2005 2007 2009 2011 5 16 % proft

“culture” trading strategy buy and hold strategy mean ± 1 sd of random strategies

Preis, Moat & Stanley (2013) Featured by:

Example: “culture”

slide-14
SLIDE 14

100 200 300 2005 2007 2009 2011 326 16 % proft

“debt” trading strategy buy and hold strategy mean ± 1 sd of random strategies

Preis, Moat & Stanley (2013)

Example: “debt”

Featured by:

slide-15
SLIDE 15

Random strategy mean + 2 sds Random strategy mean + 1 sd

return (random strategy sds) 1 2

  • 1

“debt” “culture”

How different keywords perform

Preis, Moat & Stanley (2013)

slide-16
SLIDE 16

Random strategy mean + 2 sds Random strategy mean + 1 sd

return (random strategy sds) 1 2

  • 1

“debt” “culture” “stocks” “credit” “garden” “train”

Preis, Moat & Stanley (2013)

How different keywords perform

slide-17
SLIDE 17

# occurrences in FT # hits on Google

Returns signifjcantly correlated with indicator

  • f fjnancial relevance

Financial relevance

Random strategy mean + 2 sds Random strategy mean + 1 sd

return (random strategy sds) 1 2

  • 1

Preis, Moat & Stanley (2013)

How different keywords perform

slide-18
SLIDE 18

Wikipedia: Dow Jones companies

Return [Std. Dev. of Random Strategies] Density

0.0 0.2 0.4 0.6 −2 2 Wikipedia Views DJIA Companies Wikipedia Edits DJIA Companies Random Strategy

Views strategies profjtable

Moat, Curme, Avakian, Kenett, Stanley & Preis (2013) Featured by:

slide-19
SLIDE 19

Wikipedia: Financial topics

Moat, Curme, Avakian, Kenett, Stanley & Preis (2013) Featured by:

0.00 0.25 0.50 0.75 1.00 −2 2

Return [Std. Dev. of Random Strategies] Density

Wikipedia Views Financial Topics Wikipedia Edits Financial Topics Random Strategy

Views strategies profjtable

slide-20
SLIDE 20

Wikipedia: Actors and fjlmmakers?

0.0 0.1 0.2 0.3 0.4 −2 2

Return [Std. Dev. of Random Strategies] Density

Wikipedia Views Actors & Filmmakers Random Strategy

Strategies NOT profjtable

Moat, Curme, Avakian, Kenett, Stanley & Preis (2013) Featured by:

slide-21
SLIDE 21

debt housing crisis apple

  • range

tree housing debt Curme, Preis, Stanley & Moat (2014)

What is searched for before falls?

slide-22
SLIDE 22

55 groups of search terms Business and politics most related

Curme, Preis, Stanley & Moat (2014)

What is searched for before falls?

Cumulative Returns (%)

  • 100

100 200

Random Strategy Politics I Business

slide-23
SLIDE 23

Sensing disasters

3

slide-24
SLIDE 24

Preis and Moat (under review); ¡

Time 0.00 0.02 0.04 0.06 0.08 0.10 20 Oct 25 Oct 30 Oct 05 Nov 10 Nov 15 Nov 20 Nov

Flickr Photos with Hurricane Related Tags Landfall of Hurricane Sandy

960 980 1000 1020 20 Oct 25 Oct 30 Oct 05 Nov 10 Nov 15 Nov 20 Nov

Landfall of Hurricane Sandy Averaged Pressure in US State New Jersey

A B

Preis, Moat, Bishop, Treleaven and Stanley (2013)

Flickr and Hurricane Sandy

Flickr: photos taken Air pressure

slide-25
SLIDE 25

Data from the Internet may help us measure and even predict human behaviour How can open data help you?

Tobias.Preis@wbs.ac.uk