Customer Survey

Winchester Canyon Flowers and Gifts

Customer Survey

Age
Born between 1996 and 2014
Born between 1980 and 1995
Born between 1961 and 1981
Born between 1946 and 1962
Born between 1945 and 1922
Gender
Female
Male
Transgender Female
Transgender Male
Gender Variant/Non-conforming
Not listed
Prefer not to answer
Geographical Location
North East
South West
West
Southwest
Midwest
Marital Status
Single
Married
Divorced
Widowed
Education
Not completed high school
High school graduate
Some college completed
Bachelor's 4 year degree
Master's degree
Advanced degrees
Occupational Status
Managers
Professional
Technician and associate professional
Clerical support workers
Service and sales workers
Skilled agricultural and forestry, fishing
Craft and related trades
Plant and machine operators, assemblers
Elementary occupations
Armed Forces
Student
Retired
Household Income
Under $15,000
$15,000 - $24,999
$25,000 - $34,999
$35,000 - $49,999
$50,000 - $74,999
$75,000 - $99,999
$100,000 - $149,999
$15,000 - $199,999
$200,000 - over
Race
American Indian or Alaska Native
Asian
Black or African American
White
Native Hawaiian of Pacific Islander
Hispanic or Latino or Spanish Origin
Two or more races
Race of Ethnicity unknown
Technical Competence
Extremely Competent
Quite Competent
Competent
Not Very Competent
Multi-tasking
Very Competent
Quite Competent
Competent
Incompetent
Favorable work-life balance
Well balanced
Balanced
Not well balanced
Planned Retirement age
Before 65
66, 67, 68
69, 70,71,
Internet and Social Media
Connected 24/7
Connected most of the time
Connected Daily
Connected Weekly
Team Oriented
Very team-oriented
Pretty much team-oriented
Not really team-oriented
On-line purchases
The only way I shop
Buy mostly on line
Some on-line purchases
Do not buy things on-line
Brand Consiciousness
I only buy brand name merchandise
I usually buy brand name merchandise
Brand names are not that important to me

If you are interested in creating your own online survey check out the following two links.

Making an on line survey
Upper Crust mobile ordering Application

Data Preparation

The first objective is to collect the information submitted from the survey. Below is an example of one of the form mail surveys received.

Thank You For Filling Out This Form

Below is what you submitted to jerry@janetbelch.com on Wednesday, August 7, 2019 at 13:32:26

Age: Born between 1961 and 1981 gender: Female
location: West
maritalStatus: Single
education: Bachelor's 4 year degree
occupation: Professional
income: $75,000 - $99,999
race: White
Technical Competence: Quite Competent
Multi-tasking: Very Competent
Work-Life Balance: Well Balanced
Retirement Age: 69, 70, 71
Internet and Social Media: Connected Daily
Team-oriented: Pretty much team-oriented
On-line Purchases: Buy mostly on line
Brand Consciousness: I only buy brand name merchandise

Open up a spreadsheet and enter the headings for the columns.

Now we need to enter numbers to represent the data. See the chart below as to how to convert the alphabetic data into numbers.

The customers that replied to our survey were Millenials and Generation X and Baby Boomers. The teenagers, Generation Z had not made any online purchases.

Age
- 1 = Generation Z
- 2 = Generation Y
- 3 = Generation X
- 4 = Baby boomers
Gender
- 1 = Female
- 2 = Male
- 3 = Transgender Female
- 4 = Transgender Male
- 5 = Gender Variant/Non-conforming
- 6 = Not Listed
- 7 = Prefer not to answer
Location
- 1 = Northeast
- 2 = Southwest
- 3 = West
- 4 = Southeast
- 5 = Midwest
Marital Status
- 1 = Single
- 2 = Married
- 3 = Divorced
- 5 = Widowed
Education
- 1 = Not finished high school
- 2 = Completed high school
- 3 = Some college
- 4 = Completed Bachelor's degree
- 5 = Master's degree
- 6 = Advanced degrees
Occupation
- 1 = Managers
- 2 = Professionals
- 3 = Technicians
- 4 = Clerical Support
- 5 = Sales and Services
- 6 = Skilled Agriculture
- 7 = Craft Trades
- 8 = Plant and machine operators
Household Income
- 1 = Under $15,000
- 2 = $15,000 to $24,999
- 3 = $25,000 to $34,999
- 4 = $35,000 to $49,999
- 5 = $50,000 to $74,999
- 6 = $75,000 to $99,999
- 7 = $100,000 to $149,999
- 8 = $150,000 to $199,999
- 9 = Greater than $200,000
Race
- 1 = American Indian or Alaska native
- 2 = Asian
- 3 = Black or African American
- 4 = White
- 5 = Native Hawaiian or Pacific Islander
- 6 = Hispanic, Latino or Spanish origin
- 7 = Two or more races
- 8 = Race and ethnicity unnown
Technical Competence
- 1 = Extremely Competent
- 2 = Quite Competent
- 3 = Competent
- 4 = Not Very Competent
Multi-tasking
- 1 = Very Competent
- 2 = Quite Competent
- 3 = Competent
- 4 = Incompetent
Work-Life Balance
- 1 = Well balanced
- 2 = Balanced
- 3 = Not well balanced
Retirement Age
- 1 = Before 65
- 2 = 66, 67, 68
- 3 = 69, 70,71,
Internet and Social Media
- 1 = Connected 24/7
- 2 = Connected most of the time
- 3 = Connected Daily
- 4 = Connected Weekly
Team Orientation
- 1 = Very team-oriented
- 2 = Pretty much team-oriented
- 3 = Not really team-oriented
On-line Purchases
- 1 = The only way I shop
- 2 = Buy mostly on line
- 3 = Some on-line purchases
- 4 = Do not buy things on-line
Brand Consciousness
- 1 = I only buy brand name merchandise
- 2 = I usually buy brand name merchandise
- 3 = Brand names are not that important to me

Key in the headings for each column: age, gender, geographical location, marital status, education, occupation, income,race, technical competence, multitasking, work-life, retirement age, Internt, team orientation, on-line purchases, brand consciousness.
Look at numeric responses listed above for each category
Key in the appropriate numbers for each category and each respondent.
Remember each row corresponds to one record, or one customer's responses.
A partial spreadsheet with this data is available if you click on the link
The actual finished copy is on our website and is automatically loaded into your Python Neural network program.
I am only including all this information so that you can see how to use it if you wish to create your own dataset.

Partial spreadsheet

Looking at the spreadsheet, it has already been coded for you using numbers to represent the different demographics.

The next part of the data preparation involved formatting the numbers into two decimal places. The Python code wants this for its algorithum. There is probably a way around this but I did not see it.

I also deleted the row that contained the column headings since we no longer need this information. The headings are coded for Python in the Python code.

Now we need to look at the rows of the spreadsheet, our respondents' answers, to classify them into a generational category. Look at the chart below.

Born between 1996 and 2014 = Generation Z
Born between 1980 and 1995 = Generation Y or Milleniels
Born between 1961 and 1981 = Generation X
Born between 1946 and 1964 = Babyboomers
Born between 1922 and 1945 = Traditionalists
Born between 1901 and 1924 = Greatest Generation

After looking at the survey results, I added a column to the right of the column brand loyality with the generation designation for each respondent. For example, respondent 1 is a Generation X, so I added the words GenX in this column.

The answers to all the questions were evaluated to determine which generation each customer belonged to. Age of course is the main determining facotor. After saving the worksheet as a .xlsx extension, I then needed to save the worksheet as a .csv file. This is the file type needed by our Python program. After saving the worksheet in the csv format, I then uploaded it to our website, so it would be easy for you to access it. The Python program actually gets the file from the web site. Supervised learning is a machine-learning task that learns for data that has been labeled. The labeling is done under the supervison of the modeler. In our case, the labels are the generations assigned to each customer.

Examples can be seen by clicking on the links that appear below.

Partial spreadsheet with generation designation
Partial spreadsheet with comma separated values
Link back to Linear Regression Tutorial