Quantifying human behaviour with Internet data

Suzy Moat Data Science Lab Behavioural Science, WBS

[email protected] 1 The advantage of looking forward Suzy Moat & Tobias Preis Future Orientation Index 2010 Based on Preis, Moat, Stanley and Bishop (2012)

more searches for “2009” more Google searches for “2011” Suzy Moat & Tobias Preis Future Orientation Index 2012 Based on Preis, Moat, Stanley and Bishop (2012) 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 Ratio of Google searches for “2011” to searches for “2009” during 2010 for 45 countries

0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 FutureRatio Orientation of Google searches for “2013” to searches Index for “2011” during 20122010 for 45 countries Richer countries look forward

A B Preis, Moat, Stanley & 5 “2007” “2008” “2009” 4 Bishop (2012) USD]

0 4 10 3 2 5 “2009” “2010” “2011” Featured by: 1 Search Volume 0

2008 2009 2010 GDP / Capita [10 0.0 0.5 1.0 1.5 2.0

Time with Weekly Granularity Future-Orientation Index Photo: Perpetual Tourist

2 Anticipating market moves Moat et al. (2013); Hypothetical strategy Preis et al. (2013)

number of page views

week t Moat et al. (2013); Hypothetical strategy Preis et al. (2013)

number of Wikipedia page views

week t-3 t-2 t-1 t Moat et al. (2013); Hypothetical strategy Preis et al. (2013)

number of Wikipedia page views Page views decreased: BUY stock in week t+1

week t-3 t-2 t-1 t Moat et al. (2013); Hypothetical strategy Preis et al. (2013)

number of Wikipedia page views Page views decreased: BUY stock in week t+1

Page views increased: SELL stock week in week t+1 t-3 t-2 t-1 t Wikipedia: Dow Jones companies

Moat, Curme, 0.6 Wikipedia Views Avakian, Kenett, DJIA Companies Wikipedia Edits Stanley & Preis DJIA Companies (2013) 0.4 Featured by:

Density Random 0.2 Strategy

0.0 −2 0 2 Return [Std. Dev. of Random Strategies]

Views data: signifcant difference Wikipedia: Financial topics

Moat, Curme, 1.00 Avakian, Kenett, Wikipedia Edits Stanley & Preis 0.75 Financial Topics (2013) Wikipedia Views Financial Topics 0.50 Featured by:

Density Random 0.25 Strategy

0.00 −2 0 2 Return [Std. Dev. of Random Strategies]

Views data: signifcant difference Wikipedia: Actors and flmmakers?

Moat, Curme, 0.4 Avakian, Kenett, Random Wikipedia Views Stanley & Preis Strategy Actors & Filmmakers 0.3 (2013)

0.2 Featured by:

Density

0.1

0.0

−2 0 2 Return [Std. Dev. of Random Strategies]

Views data: no signifcant difference How Google keywords perform

return (random strategy sds) 2 Random strategy mean + 2 sds 1 Random strategy mean + 1 sd 0 -1

“debt” “culture”

Preis, Moat & Stanley (2013) How Google keywords perform

return (random strategy sds) 2 Random strategy mean + 2 sds 1 Random strategy mean + 1 sd 0 -1

“debt” “credit” “culture” “stocks” “train” “garden” Preis, Moat & Stanley (2013) How Google keywords perform

return (random strategy sds) 2 Random strategy mean + 2 sds 1 Random strategy mean + 1 sd 0 -1

Financial relevance Returns signifcantly correlated with indicator # occurrences in FT of fnancial relevance # hits on Google Preis, Moat & Stanley (2013) What is searched for before falls?

debt internet money money technology crisis debt

Curme, Preis, Stanley & Moat (2014) What is searched for before falls?

Cumulative Returns (%) -100 0 100 200 Random Strategy Politics I Business

55 groups of search terms

Business and politics most related

Curme, Preis, Stanley & Moat (2014) 3 Photographers as sensors Flickr and tourist numbers

Barchiesi, Moat, Alis, Bishop & Preis (under review) Scenicness and wellbeing

Photo: Tom Richardson Seresinhe, Preis & Moat (under review) Scenicness and wellbeing

A

Newcastle

Liverpool Manchester Shefeld Birmingham London POOR HEALTH

Average rates of poor health (SMR)

0 0.5 0.6 0.7 0.8 0.9 1.2 3.2 B C Seresinhe, Preis & Moat (under review) SCENICNESS GREENSPACE

Average percentage of greenspace Average scenic rating

0 0.3 0.6 0.7 0.9 0.94 0.96 0.99 1 2.2 3.1 3.6 3.9 4.2 4.6 8

D 1.00

0.75 Model Scenicness only 0.50 Greenspace only Scenicness and Greenspace lity of the model

b 0.25 en the data (AICw) v

Proba gi 0.00 All areas Urban Suburban Rural A

Newcastle

Liverpool Manchester Shefeld Birmingham London POOR HEALTH

Average rates of poor health (SMR)Scenicness and wellbeing

0 0.5 0.6 0.7 0.8 0.9 1.2 3.2 B C SCENICNESS GREENSPACE

Average percentage of greenspace Average scenic rating

0 0.3 0.6 0.7 0.9 0.94 0.96 0.99 1 2.2 3.1 3.6 3.9 4.2 4.6 8

D 1.00 Seresinhe, Preis & Moat (under review) 0.75 Model Scenicness only 0.50 Greenspace only Scenicness and Greenspace lity of the model b 0.25 en the data (AICw) v

Proba gi 0.00 All areas Urban Suburban Rural A

Newcastle

Liverpool Manchester Shefeld Birmingham London POOR HEALTH

Average rates of poor health (SMR)Scenicness and wellbeing

0 0.5 0.6 0.7 0.8 0.9 1.2 3.2 B C

Self reported health is SCENICNESS

GREENSPACE better in Average percentage of greenspace Average scenic rating more scenic

0 0.3 0.6 0.7 0.9 0.94 0.96 0.99 1 2.2 3.1 3.6 3.9 4.2 4.6 8 locations

D 1.00 Seresinhe, Preis & Moat (under review) 0.75 Model Scenicness only 0.50 Greenspace only Scenicness and Greenspace lity of the model b 0.25 en the data (AICw) v

Proba gi 0.00 All areas Urban Suburban Rural A

Newcastle

Liverpool Manchester Shefeld Birmingham London POOR HEALTH

Average rates of Scenicnesspoor and health (SMR) wellbeing

0 0.5 0.6 0.7 0.8 0.9 1.2 3.2 B C SCENICNESS GREENSPACE

Average percentage of greenspace Average scenic rating

0 0.3 0.6 0.7 0.9 0.94 0.96 0.99 1 2.2 3.1 3.6 3.9 4.2 4.6 8

D 1.00 Seresinhe, Preis & Moat (under review) 0.75 Model Scenicness only 0.50 Greenspace only Scenicness and Greenspace lity of the model

b 0.25 en the data (AICw) v

Proba gi 0.00 All areas Urban Suburban Rural AA

NewcastleNewcastle

LiverpoolLiverpool ManchesterManchester SheSheffeldeld BirminghamBirmingham LondonLondon POOR HEALTH POOR HEALTH

AverAveragaeg erates rates of of Scenicnesspoorpoor healthand health (SMR) (SMR) wellbeing

0 0 0.5 0.5 0.6 0.6 0.7 0.7 0.8 0.8 0.9 0.9 1.2 1.2 3.2 3.2 BB CC SCENICNESS SCENICNESS GREENSPACE GREENSPACE

AverAveragaeg epercentage percentage ofof greenspace greenspace AverAveragaeg escenic scenic rating rating

0 00.3 0.3 0.6 0.6 0.7 0.7 0.9 0.9 0.94 0.94 0.96 0.96 0.99 0.99 1 1 2.2 2.2 3.1 3.1 3.6 3.6 3.9 3.9 4.2 4.2 4.6 4.6 8 8

DD 1.001.00 Seresinhe, Preis & Moat (under review) 0.750.75 ModelModel ScenicnessScenicness only only 0.500.50 GreenspaceGreenspace only only ScenicnessScenicness and and Greenspace Greenspace lity of the model lity of the model b b 0.250.25 en the data (AICw) en the data (AICw) v v Proba gi Proba gi 0.000.00 AllAll areas areas UrbanUrban SuSuburbanburban RuralRural A

Newcastle

Liverpool Manchester Shefeld Birmingham London POOR HEALTH

Average rates of poor health (SMR)

0 0.5 0.6 0.7 0.8 0.9 1.2 3.2 B C SCENICNESS GREENSPACE

ScenicnessAverage percentage and wellbeing of greenspace Average scenic rating

0 0.3 0.6 0.7 0.9 0.94 0.96 0.99 1 2.2 3.1 3.6 3.9 4.2 4.6 8

D 1.00

0.75 Model Scenicness only 0.50 Greenspace only Scenicness and Greenspace lity of the model

b 0.25 en the data (AICw) v

Proba gi 0.00 All areas Urban Suburban Rural

Seresinhe, Preis & Moat (under review) [email protected]

@suzymoat

Data from the Internet may help us measure and even predict human behaviour