A1: Direct Mail Household EDA

r multi-part question and need the explanation and answer to help me learn.

PLEASE FOLLOW EACH SUBMISSION INSTRUCTION AS WELL AS FOCUS IN THE RUBRIC
You are the lead marketing data scientist for Bedding Bathing & Yonder (BBY). BBY is an American chain of domestic merchandise retail stores with an online presence. The chain primarily operates stores throughout the United States. BBY offers a membership and loyalty program designed to give customers easy access to great benefits and discounts through email, and physical direct mail coupons tailored to the household shopping habits. Loyalty customers have shared some basic information about their household and as a result the company’s marketing department has excellent data assets for these customers.
Senior management has asked you make an in-depth exploratory analysis of the customer base. The goal of the management team is to create micro-segments and personas for the loyalty program. Keep in mind, interesting data correlations may not be beneficial in a marketing context. For example, identifying 5 customers with very specific attributes may be interesting but hardly a segment worth attracting. Further, this data has been randomized due to privacy concerns so some attributes may not be useful.

You are asked to examine the data, clean it, use supplemental data to enrich the data then identify 4 or more interesting insights from the user data. All relevant cleaning, enriching and EDA steps along with the 4+ insightful data nuances should be organized into a presentation. You will present to the head of marketing who is looking for an “ah –ha” persona or previously unknown data relationship. As the head of marketing, relevant information is consumed visually instead of in table form. Thus, your presentation should include visualizations when appropriate. Your submission will include code, bulleted written document and PowerPoint slides with narration.
Data
Source: The data has been synthesized using existing proprietary household data sets from various third parties obtained for a single US community. Some variables have been randomized, others have been anonymized, and further de-identification is performed on the geolocation attributes (lat/lon these have been completely manufactured). Thus, the data is likely not able to be reconstructed in its initial proprietary form but is still representative in some regards.
Data Tables
File Name
Rows
Columns
Description
consumerData_training15K_studentVersion.csv
10000
26
Consumer purchasing habits
DonationsData_training15K_studentVersion.csv
15000
15
Household donation history
inHouseData_training15K_studentVersion.csv
15000
20
Data BBY has as part of membership
magazineData_training15K_studentVersion.csv
15000
10
Household magazine subscription history
politicalData_training15K_studentVersion.csv
15000
13
Household political leanings
All data tables have a unique identifier, “tmpID” which can be used to join the data. If joined properly, the training data will have 80 variables described below. It may not be the case all variables are useful or even ethical to use for insights, EDA and/or persona building.
Data Dictionary
Variable Name
Example
Definition
tmpID
5126
Unique Household Identifier
ResidenceHHGenderDescription
Female Only Household
Head of household gender
EthnicDescription
Chinese
ethnic description
BroadEthnicGroupings
German
secondary ethnic description
PresenceOfChildrenCode
Known Data
If known, children purhcases indicate a child in home
ISPSA
8
Index of Social Position for Small Areas (ISPSA)
Index of Social Position for Small Areas (ISPSA) an exclusive
lifestyle classification system providing household
characterization by social class affiliation. ISPSA is a score
weighted on several census factors related to education and
occupation.
HomeOwnerRenter
Likely Homeowner
Home dwelling type
MosaicZ4
Bohemian Groove
Persona Descriptions from Experian
– i.e. https://assets.cengage.com/gale/help/dnow/Mosaic/M…
MedianEducationYears
13
Number of formal education in years
NetWorth
$50000-99999
Binned, net worth of household
Investor
Yes
Indication of an investor in the household
BusinessOwner
Yes
Indication of a registered business owner in the household
Education
Grad Degree – Likely
Modeled highest formal education attained
OccupationIndustry
Unknown
Head of household professional industry
HorseOwner
Yes
Indication of a equestrian rider and/or owned horse
CatOwner
Yes
Indication of a cat(s) in household
DogOwner
Yes
Indication of a dog(s) in household
OtherPetOwner
Yes
Indication of a non cat/dog/horse pet in household
HomeOffice
Yes
Indication of a home work office
BookBuyerInHome
3 book purchases in home
Household book purchases from book-scan
UpscaleBuyerInHome
1 upscale merchandise purchase
Household luxury goods pruchase indicator
BuyerofAntiquesinHousehold
Household antique purchase indicator
BuyerofArtinHousehold
Yes
Household fine art purchase indicator
GeneralCollectorinHousehold
Yes
Household collector purchases indicator i.e. cards, stamps
BooksAudioReadinginHousehold
Yes
Audio book purchase indicator
ComputerOwnerInHome
Yes
Presence of a home computer
ReligiousContributorInHome
1 religious contribution in home
Donation to a religious charity indicator
PoliticalContributerInHome
1 political contribution in home
Donation to a political nonprofit, candidate or elected official
DonatesEnvironmentCauseInHome
Unknown
Donation to environmentally focused non-profit
DonatesToCharityInHome
Unknown
Donation to a non-profit of any kind in household
DonatestoAnimalWelfare
Yes
Donation to ethical treatment of animals nonprofit indicator
DonatestoArtsandCulture
Yes
Donation to arts, performing, and culture related nonprofit organizations
DonatestoChildrensCauses
Yes
Donation to child advocacy and welfare non profit organizations
DonatestoHealthcare
Yes
Donation to healthcare and wellbeing organiations
DonatestoInternationalAidCauses
Yes
Donation to international, non-US causes i.e. relief agencies
DonatestoVeteransCauses
Yes
Donation to conflict and war veteran support organizations
DonatestoHealthcare1
Yes
Donation to healthcare and wellbeing organiations
DonatestoInternationalAidCauses1
Yes
Donation to international, non-US causes i.e. relief agencies
DonatestoWildlifePreservation
Yes
Donation to environmentally focused non-profit
DonatestoLocalCommunity
Yes
Donation to county, zip and community organizations
FirstName
Isiah
Fictitious first name for the head of the household
LastName
Bechtelar
Fictitious last name for the head of the household
Gender
M
BBY loyalty member gender
Age
49.55844156
BBY loyalty member age
TelephonesFullPhone
(539)-471-5789
Fictitious telephone number (US)
lat
48.29635
latitude
lon
-95.54055
longitude
county
Beltrami County
County (administrative division of a state, providing certain local governmental services) name
city
Grygla
City (administrative municipality) name
state
Minnesota
US state name
fips
27007
Federal Information Processing System (FIPS) Codes for States and Counties.
FIPS codes are numbers which uniquely identify geographic areas.
stateFips
27
FIPS state code
HomePurchasePrice
$243,000
County register record for home price in last sale
LandValue
$11,000
County register land deed assessed value
DwellingUnitSize
1-Single Family Dwelling
Occupancy Type
storeVisitFrequency
7
Number of times loyalty member has been in store in last 12 months
PropertyType
Residential
Household property type
EstHomeValue
$187,500
Estimated home value including land according to third party, non-county register model
yHat
123.0180871
Average household spend with BBY in USD. Some noise has been added to the amounts for further anonymization
FamilyMagazineInHome
2 family-oriented magazine purchases
Magazine subscription related to family relations in house
FemaleOrientedMagazineInHome
1 female magazine purchase
Magazine subscription with female target in house
ReligiousMagazineInHome
1 religious magazine purchase
Magazine subscription on religious topic in house
GardeningMagazineInHome
2 gardening magazine purchases
Magazine subscription covering gardening, and landscaping in house
CulinaryInterestMagazineInHome
1 culinary magazine purchase
Magazine subscription focused on fine dining, diet, cooking or baking
HealthFitnessMagazineInHome
4 health and fitness magazine purchases
Magazine subscription focused on health and wellbeing, working out, yoga or other fitness/active/sport related activities
DoItYourselfMagazineInHome
3 Do-It-Yourself magazine purchases
Magazine subscription focused on home improvement, woodworking, or other self initiated projects
FinancialMagazineInHome
1 financial magazine purchase
Magazine subscription focused on retirement, investment opportunities or retail equity
InterestinCurrentAffairsPoliticsInHousehold
Yes
Magazine subscription focused on newworthy events, local or global in nature
PartiesDescription
Republican
Registered political party affiliation
ReligionsDescription
Protestant
Likely religious denomination
LikelyUnionMember
Yes
Likely union roster appearance
GunOwner
Yes
Registered gun owner
Veteran
Unknown
Likely foreign war veteran or member of the armed service
supportsAffordableCareAct
Support
Political support for nationalized US healthcare
supportsGayMarriage
Support
Political support for LGBTQ+ rights
supportsGunControl
Oppose
Political support for gun ownership
supportsTaxesRaise
Oppose
Political support for raising taxes among wealthy households
overallsocialviews
Conservative
Overall classification of political leanings in the head of the household
DonatestoConservativeCauses
Yes
Donates to traditionally conservative cause nonprofit organizations
DonatestoLiberalCauses
Yes
Donates to traditionally liberal cause nonprofit organizations
Further data enrichment is possible using FIPS code but is not required for the case. The US Census publishes data using the FIPS code and some online data sets exists for community level attributes. However, the FIPs in this data set are incomplete and do not get to the block level. As a result, additional geospatial work is not required to complete the case. Exclusive to the case, for those that are interested, some starting links are shared below.
https://data.world/datasets/fipsLinks to an external site.
https://www.huduser.gov/portal/datasets/usps_crosswalk.htmlLinks to an external site.
FIPS Code Explanation
Source: https://www.policymap.com/2012/08/tips-on-fips-a-q…Links to an external site.
Course Scripting Supplemental
You will receive an initial script with code examples to get you started since this is the first case of the course.
The Submission
The submission will include business analyst slides covering the problem, data and 4 insights. Without a presentation, the “organization” section of the rubric will be 0. Exceptional submissions are well ordered and provide a coherent narrative covering all 4 insights.
The submission will include a written supplemental representing the 4 insights identified and described in the business presentation. The written portion can be 3-5 sentences for each insight in a bulleted list format. Exceptional submissions include statistics from external credible sources that support the identified personas or insights. For example, “…focus on pet owners over age XX because [some org/research] says this segment will grow YY over the next 5 years…”. Without a written supplemental that coincide with the narration and supported by code the “written supplemental” section will be 0.
The submission will include either a recorded screen narration of the business presentation, a text file with a URL to a recording (like youtube video) or audio that is embedded into the slide deck. Tone, volume, cadence, use of filler words and pronunciation will be accounted for in this section. No points will be deducted based on English proficiency (ie ESL) but technical descriptions that are incorrect will be detrimental. Failure to submit a narration, the “delivery” section of the rubric will be 0.
An R script covering all data munging, modeling (if applicable), evaluation (if applicable) and visualization construction used to create the presentation artifacts (you do not need to use R to construct the slides but it is possible) and come to the case outcomes. Your code must use the following R functions at least once throughout your code, group_by, aggregate & subset. Make sure to that your code contains ample comments. Failure to turn in an R script will result in a “Documentation” score of 0.
Criteria for Success
The presentation will be evaluated on an equal weighted scale with the following criteria. For example, 20 points per each category [depends on the individual course weighting found in Canvas]
Organization – Was the presentation well organized?
Delivery – Was the content delivered clearly and persuasively with the audience in mind?
Code Documentation – Was the data mined to support the conclusion?
Written Supplemental – Are the bullets clear and supported in narration and code?
Data Mining Process – Overall, as a complete portfolio of work, is the topic interesting, organized, researched, supported and delivered effectively?
Rubric
Direct Mail Household EDA
Direct Mail Household EDA
Criteria Ratings Pts
This criterion is linked to a Learning OutcomeOrganizationWas the presentation well organized?
20 pts
Masterful
15 pts
Slightly Exceeds Expectation
10 pts
Proficient
5 pts
Developing
0 pts
Does not meet expectation
20 pts
This criterion is linked to a Learning OutcomeDeliveryWas the content delivered clearly and persuasively with the audience in mind?
20 pts
Mssterful
15 pts
Slightly Exceeds Expectation
10 pts
Proficient
5 pts
Developing
0 pts
Does Not Meet Expectations
20 pts
This criterion is linked to a Learning OutcomeCode DocumentationWas the data mined to support the conclusion?
20 pts
Masterful
15 pts
Slightly Exceeds Expectation
10 pts
Proficient
5 pts
Developing
0 pts
Does not meet expectation
20 pts
This criterion is linked to a Learning OutcomeWritten SupplementalAre the bullets clear and supported in narration and code?
20 pts
Masterful
15 pts
Slightly Exceeds Expectation
10 pts
Proficient
5 pts
Developing
0 pts
Does not meet expectation
20 pts
This criterion is linked to a Learning OutcomeData Mining ProcessOverall, as a complete portfolio of work, is the topic interesting, organized, researched, supported and delivered effectively?
20 pts
Masterful
15 pts
Slightly Exceeds Expectation
10 pts
Proficient
5 pts
Developing
0 pts
Does not meet expectation
20 pts
Total Points: 100
Requirements: follow each submission instruction

The post A1: Direct Mail Household EDA first appeared on Bessays.