Scribd
Upload
104 views3 pages

WNSAA Onsite Case Wine

Unicorn Winery has hired Digitas to analyze data on wine properties and quality ratings to help the winery understand how to modify aspects of wine production to maximize appeal. The assistant is asked to continue the analysis using data on over 6,000 wine samples. Notes provide details on the available data and initial exploratory work, which identified relationships between various properties and quality. The objective is to provide insights and recommendations to Unicorn Winery within two hours by focusing analysis on the most important factors.

Uploaded by

Abhishek Jha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
104 views3 pages

WNSAA Onsite Case Wine

Unicorn Winery has hired Digitas to analyze data on wine properties and quality ratings to help the winery understand how to modify aspects of wine production to maximize appeal. The assistant is asked to continue the analysis using data on over 6,000 wine samples. Notes provide details on the available data and initial exploratory work, which identified relationships between various properties and quality. The objective is to provide insights and recommendations to Unicorn Winery within two hours by focusing analysis on the most important factors.

Uploaded by

Abhishek Jha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

DigitasLBi

 Advanced  Analytics  Onsite  Case  


-­‐-­‐Return  all  materials  to  interviewer  before  leaving-­‐-­‐  
 
Business  Problem  
 
It  is  often  said  that  great  wine  is  made  in  the  vineyard,  not  in  the  winery.    However,  winemakers  
have  the  ability  to  modify  certain  aspects  of  the  wines  they  produce,  such  as  the  level  of  acidity,  
sweetness  or  alcohol,  as  well  as  the  shelf  life.    But  which  aspects  should  winemakers  modify  to  
positively  impact  consumers’  perceptions  and/or  sales  of  their  wines?  
 
Unicorn  Winery  has  hired  Digitas  Advanced  Analytics  to  help  the  organization  better  understand  
the  relationships  between  certain  physiochemical  properties  and  the  perceived  quality  of  wines  so  
that  its  winemaking  team  can  make  more  informed  decisions  during  production.  A  Digitas  AA  
analyst  already  obtained  data  from  a  third-­‐party  industry  organization  and  started  an  exploratory  
analysis.    However,  she  recently  was  assigned  to  another  project  and  will  not  be  able  to  finish  the  
work  for  Unicorn  Winery  herself.  
 
Your  Objective  
 
Your  objective  is  to  collaborate  with  your  Digitas  supervisor  to  continue  the  analysis  and  to  
provide  Unicorn  Winery  with  insights  on  how  to  maximize  the  appeal  of  its  wines.    It’s  also  looking  
for  ideas  on  other  analyses  it  might  conduct  in  the  future  to  support  the  business,  as  well  as  what  
data  would  be  required  to  run  them.      
 
To  help  you  get  started,  notes  on  the  available  data  and  results  from  your  predecessor’s  
exploratory  analysis  are  provided  on  the  following  pages.    You  may  use  any  of  these  results  in  
your  own  presentation.    The  dataset,  graph  images  and  a  PowerPoint  template  are  all  in  the  
project  folder  “Unicorn_Winery.”    Both  R  and  Python  are  also  available  for  analyzing  the  dataset  –  
choose  whichever  program  you  prefer.    Be  prepared  to  make  and  discuss  assumptions  as  needed.    
You  are  highly  encouraged  to  brainstorm  aloud  with  your  Digitas  supervisor  while  you  are  
working.      
 
You  have  two  (2)  hours  to  complete  the  work.    The  client  and  your  supervisor  understand  that  
more  time  is  typically  needed  to  do  a  really  thorough  analysis,  but  you  are  expected  to  focus  on  
what  you  think  matters  most  in  the  time  given.      You  can  spend  this  time  as  you  see  fit,  but  the  
following  allocations  are  recommended:  
 
30  minutes  -­‐  Data  and  EDA  review  and  analytic  plan  development  
60  minutes  -­‐  Analytic  plan  execution,  including  code  and  output  
30  minutes  -­‐  Synthesis  of  results  and  presentation  
 
Finally,  your  presentation  does  not  need  to  be  fully  developed  or  refined,  but  should  present  any  
relevant  insights  you  uncover  as  clearly  as  possible.    
 

  -­‐  1    -­‐    
DigitasLBi  Advanced  Analytics  Onsite  Case  
-­‐-­‐Return  all  materials  to  interviewer  before  leaving-­‐-­‐  
 
Dataset  
 

           
 
The  dataset  consists  of  12  measurements  on  6,497  samples  of  white  and  red  styles  of  Vinho  Verde  
wines.  There  are  NO  missing  data.    Descriptions  of  each  variable  are  below.  
 
Variable   Description  
fixed_acidity   Naturally  occurring  acid,  higher  levels  yield  fresher  or  more  tart  wines  
volatile_acidity   Acid  produced  during  fermentation,  leads  to  unpleasant  aromas    
citric_acid   Inexpensive  supplement  to  boost  total  acidity  
residual_sugar   Remaining  sugar  after  fermentation  or  sometimes  added,  higher  levels  yield  
sweeter  wines  
chlorides   Saltiness,  often  just  barely  detectable  
pH   Higher  levels  make  wines  taste  softer,  inversely  related  to  acidity  
alcohol   Produced  from  yeast  and  sugar  during  fermentation,  higher  levels  
associated  with  more  complex  wines  
density   Lower  for  "dry"  wines,  higher  for  sweet  wines  
free_sulfur_dioxide,     Antibiotics/antioxidants  to  protect  wine  and  sanitize  wineries;  detectable  as  
total_sulfur_dioxide   pungent  odor  at  higher  levels  and  responsible  for  label  “contains  sulfites”  
sulphates   Potassium  sulphate  used  to  lower  pH,  raise  acidity  and  intensify  color  in  red  
wines  
quality   Median  of  ratings  on  a  0  to  10  (poor  to  excellent)  scale  from  three  or  more  
experts  who  participated  in  blind  tastings  
style   Red  or  white  
 
 
 

  -­‐  2    -­‐    
DigitasLBi  Advanced  Analytics  Onsite  Case  
-­‐-­‐Return  all  materials  to  interviewer  before  leaving-­‐-­‐  
 
Exploratory  Results  (work  in  progress)  
 

       
 
Mean Median
 

       

       

       

       

  -­‐  3    -­‐    

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy