Using Big Data to investigate the influence of climate and demography on wine consumer habits Alastair Reed 1, Michael Shannon 1, Daniel Mathews 2 1 Viticulture.

Using Big Data to investigate the influence of climate and demography on wine consumer habits Alastair Reed1, Michael Shannon1, Daniel Mathews2

1 Viticulture and Winemaking, Melbourne Polytechnic Contact: [email protected]

2School of Mathematic Sciences, Monash University

Today

Background

Australian wine retail sector

The study

Use of Big Data in wine to derive relationships between geography and climate

Results

Association between temperature, geography and consumer preference

Recommendations

Ongoing research and implications for future management

Introduction

The Australian wine retail sector is a clear duopoly

Dominated by two players; Wesfarmers Ltd [19%] and Woolworths Ltd [39%]

Data analysis opportunity!

Beverage Revenue

Wesfarmers Ltd $2.0 billion

Woolworths Ltd $4.1 millionFrom: Data estimated by IBIS World

What effects consumer preference?

Epigenetics of a varietal decision

1. Visual

Label, position, status

2. History

Regional bias, personal bias

3. Environment

Climatic effects, light levels

Decision Genes

Shiraz Sauvignon Blanc

Shiraz sale Sauvignon Blanc sale

Activation

Decision Gene expression can be developmentally influenced and/or environmental

Developmental vs EnvironmentalCase Study: Champagne

1/1/2013

1/10/2013

1/19/2013

1/28/2013

2/6/2013

2/15/2013

2/24/2013

3/5/2013

3/14/2013

3/23/2013

4/1/2013

4/10/2013

4/19/2013

4/28/2013

5/7/2013

5/16/2013

5/25/2013

6/3/2013

6/12/2013

6/21/2013

6/30/2013

7/9/2013

7/18/2013

7/27/2013

8/5/2013

8/14/2013

8/23/2013

9/1/2013

9/10/2013

9/19/2013

9/28/2013

10/7/2013

10/16/2013

10/25/2013

11/3/2013

11/12/2013

11/21/2013

11/30/2013

12/9/2013

12/18/2013

12/27/2013

0

0.1

0.2

0.3

0.4

0.5

0.6

Online Chardonnay sales in Melbourne, Australia, during 2013

Developmental vs EnvironmentalCase Study: Champagne

1/1/2013

1/10/2013

1/19/2013

1/28/2013

2/6/2013

2/15/2013

2/24/2013

3/5/2013

3/14/2013

3/23/2013

4/1/2013

4/10/2013

4/19/2013

4/28/2013

5/7/2013

5/16/2013

5/25/2013

6/3/2013

6/12/2013

6/21/2013

6/30/2013

7/9/2013

7/18/2013

7/27/2013

8/5/2013

8/14/2013

8/23/2013

9/1/2013

9/10/2013

9/19/2013

9/28/2013

10/7/2013

10/16/2013

10/25/2013

11/3/2013

11/12/2013

11/21/2013

11/30/2013

12/9/2013

12/18/2013

12/27/2013

0

0.1

0.2

0.3

0.4

0.5

0.6

Warm averageCold average

Developmental vs EnvironmentalCase Study: Champagne

1/1/2013

1/10/2013

1/19/2013

1/28/2013

2/6/2013

2/15/2013

2/24/2013

3/5/2013

3/14/2013

3/23/2013

4/1/2013

4/10/2013

4/19/2013

4/28/2013

5/7/2013

5/16/2013

5/25/2013

6/3/2013

6/12/2013

6/21/2013

6/30/2013

7/9/2013

7/18/2013

7/27/2013

8/5/2013

8/14/2013

8/23/2013

9/1/2013

9/10/2013

9/19/2013

9/28/2013

10/7/2013

10/16/2013

10/25/2013

11/3/2013

11/12/2013

11/21/2013

11/30/2013

12/9/2013

12/18/2013

12/27/2013

0

0.1

0.2

0.3

0.4

0.5

0.6

Melbourne Cup

Easter

Mother’s Day

Tax Returns?

Football finals

NYE

We wish to explain the environmental and developmental…

Can we quantify to what degree wine purchase decisions are influenced by the weather?

Can we explain to what degree wine purchase decisions are influenced by location on a city-level?

The data…

Over 3 million transactions from across Victoria, Australia

Closely examined:

Shiraz

Chardonnay

Riesling

Sauvignon Blanc

Pinot Gris/Grigio

Cabernet Sauvignon

Merlot

Pinot Noir

Wine Purchase DecisionCase Study: Victoria

1 2 3 4 5 6 7 8 9 10 11 120

5

10

15

20

25

30

Geographically diverse state

Desert in north-west

Alpine in the north-east

Temperate in the south

Melbourne’s Climate

Average temperature: 13 – 25°C

Extreme temperatures: -2 – 46°C

Consumer decisions cluster into groups

Temperature

Varieties correlate to temperature on a geographic scale

Association between relative Sauvignon Blanc (left) and Shiraz (right) sales and temperature, across Australia

0.18 0.185 0.19 0.195 0.2 0.205 0.21 0.215 0.22 0.2255

10

15

20

25

30

f(x) = 353.252146300215 x − 52.2410878210395R² = 0.692078572970318

0.05 0.06 0.07 0.08 0.09 0.1 0.11 0.12 0.135

10

15

20

25

30

f(x) = − 180.762346031977 x + 33.7165680206313R² = 0.405556053630358

All analysed varieties were correlated to temperature on a temporal scale

5 10 15 20 25 30 35 40 450.00%

10.00%

20.00%

30.00%

40.00%

50.00%

60.00%

f(x) = − 0.00359695794237473 x + 0.267774023270689R² = 0.197351352441506

Association between relative Shiraz sales and temperature

All analysed varieties were correlated to temperature on a temporal scale

Association between relative Sauvignon Blanc sales and temperature

5 10 15 20 25 30 35 40 450.00%

5.00%

10.00%

15.00%

20.00%

25.00%

30.00%

35.00%

f(x) = 0.00169245126087001 x + 0.119450352512055R² = 0.10228796113334

Google search associates Shiraz to temperature

10 15 20 25 30 3515

20

25

30

35

40

45

50

55

60

f(x) = − 0.779314046730358 x + 56.7949665501602R² = 0.370583390432392

Temperature (°C)

Goog

le se

arch

(rel

ative

)

Association between relative fortnightly Google searches and average temperature (excluding Christmas period)

Google search associates Sauvignon Blanc to temperature

Association between relative fortnightly Google searches and average temperature (excluding Christmas period)

20 25 30 35 40 45 50 55 60 650.1

0.12

0.14

0.16

0.18

0.2

0.22

f(x) = 0.000610093115845559 x + 0.144491466125468R² = 0.133136983710597

Link between red wine sales and temperature is consistently stronger than white, except Sauvignon Blanc…

Proportion of stores with significant correlation (r)

Average income** when significant correlation

Average income when insignificant correlation

Cabernet Sauvignon 0.96 (0.29) $1632 $1110

Merlot 0.86 (0.26) $1639 $1436

Pinot Noir 0.57 (0.22) $1793 $1371

Shiraz 0.98 (0.44) $1623 $995

Chardonnay 0.45 (0.17) $1703 $1535

Pinot Gris 0.67 (0.23) $1765 $1303

Riesling 0.61 (0.25) $1778 $1352

Sauvignon Blanc 0.96 (0.29) $1626 $1244

Average 0.76 (0.27) $1695a $1294b

*>0.027 **fortnightly

Geography

Decision Gene approach

Relative purchase figures can be treated the same as allele frequencies (the frequency of gene variants), where an individual has two alleles for each gene

Genotypes:

aa = purchase

Aa or AA = no purchase

We can then use the frequencies to describe the characteristics of a population

Comparing the relative frequency of alleles allows populations to be compared using distance-matrices, visualized with traditional phylograms.

Clustering between distinct geographic areas

Phylogram generated using the Neighbour-Joining (NJ) method on sales frequencies of 7 varieties across 28 retail outlets (derived using POPTREE2 [Takezaki 2010)

Chardonnay sales contradict the cliché

N

High Riesling sales follow SE-NW corridor

N

High Riesling sales follow SE-NW corridor

N

Demographics roughly align with Chardonnay/Riesling distinction

Sauvignon blanc is most popular in an outer suburban ring

N

Summary

Significant associations can be made between developmental and environmental factors and consumer preference

Temporal and spatial trends can be identified but need further analysis for confirmation

We are looking for collaborators to consolidate this research, all welcome!

[email protected]

Acknowledgements

Special thanks to the Australian Grape and Wine Authority and Melbourne Polytechnic for supporting my attendance at AAWE