Chris Robinson Mary Sauer Adam Schackmuth James Young December 11, 2014 Marketing Analytics Multi-Channel Retailing 1 Group 4 *Slides include notes and voiceover
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
1. Chris Robinson Mary Sauer Adam Schackmuth James Young
December 11, 2014 Marketing Analytics Multi-Channel Retailing 1
Group 4 *Slides include notes and voiceover
2. Section 1 Overview of Business Case & Marketing Data
Group 4 2
3. Multi-Channel Retailing Organization Analyzed data to
determine which channel has the most potential to maximize growth
Channels Retail Catalog Website Analysis can be used to identify
customer segments to: Attract new customers Retain the best
customers Avoid unprofitable customers Overview-Business Case /
Marketing Data 3Group 4
4. Business Case Questions we focused on: What channel should
strategic development be focused on to maximize growth? Do customer
segments correlate to a channel? How do we determine synergies
between the various sales channels? Does demographic data correlate
to a channel and push revenues into the other channels? Are
demographics and synergies important to growth of the company?
Product Food products purchased during the Christmas season as
gifts Overview-Business Case / Marketing Data 4Group 4
5. Customers Loyal to brand Products purchased for gifts Wide
variety of personal interests External Market Mail-Order catalog
market on decline Low cost of e-commerce makes it difficult for
brick-and-mortor stores to compete on price A multi-channel
approach is necessary in todays economy Overview-Business Case /
Marketing Data 5Group 4
6. Section 2 Description of Data Group 4 6
7. Dataset 9 contains 4 separate files: DMEFExtractSummaryV01
DMEFExtractContactsV01 DMEFExtractLinesV01 DMEFExtractOrdersV01
Description of Data 7Group 4
8. DMEFExtractSummaryV01 Summary File 101,051 records Customer
buying activity, demographic, psychographic and distance to retail
store information Data summarized by channel & season
(Internet, catalog, retail / Spring, Fall) This file contains all
of the information used in regressions and data analysis
Demographic (10,929 cases) Age (45-54 years old) Income - (over
$50k, most over $100k) Home (homeowners) Dwelling (single-family
home) Length Residence (over 20 years) Occupation
(professional/technical, administrative/management) Information can
be used to segment & target Description of Data 8Group 4
9. DMEFExtractSummaryV01 Summary File Cleaned data of no
responses, 10,929 cases 9Group 4 Description of Data Statistics
AgeCode IncCode HomeCode Dwelling LengthRes OccupCd N Valid 10929
10929 10929 10929 10929 10929 Missing 0 0 0 0 0 0 Mean 4.76 6.54
1.98 1.16 13.83 5.02 Median 5.00 7.00 2.00 1.00 15.00 5.00 Mode 4 9
2 1 20 1 Std. Deviation 1.240 2.198 .134 .588 6.010 4.743
10. DMEFExtractSummaryV01 Summary File - Continued Sales
Dollars summarized by channel(retail, internet, catalog) and season
(Fall, Spring) for 2004 2007, and Pre-2004 Internet & Catalog
purchases were categorized into Gift/Non-Gift Purchases Retail -
minimum ($1), maximum ($2,318) Internet - minimum ($18), maximum
($2,518) Catalog- minimum ($19), maximum ($2,106) Description of
Data 10Group 4
11. DMEFExtractContactsV01 Marketing contact records 3,389,239
records Customer contact dates and contact types (catalog or email)
Shows data for each month for 2005-2007 Data shows us: Contacts
peak in November and December 70% of contacts are made via email
Description of Data 11Group 4
12. DMEFExtractLinesV01 Line item detail 618,661 records Order
dates, dollar amount, items purchased as gifts Shows data for each
month for 2001-2007 Data shows us: ~90% of items are purchased as
gifts Description of Data 12Group 4 Gift Frequency Percent Valid
Percent Cumulative Percent Valid N 24098 11.2 11.2 11.2 Y 190774
88.8 88.8 100.0 Total 214872 100.0 100.0
13. DMEFExtractOrdersV01 Order/trip information 241,366 records
Order date, purchasing channel, payment method Shows data for each
month for 2001-2007 Data shows us: Preferred purchasing channel is
in-store; phone second Preferred payment method is a bank card;
cash second Description of Data 13Group 4
14. DMEFExtractOrdersV01 14Group 4 Description of Data
OrderMethod Frequency Percent Valid Percent Cumulative Percent
Valid I 54484 22.6 22.6 22.6 M 5315 2.2 2.2 24.8 P 72483 30.0 30.0
54.8 ST 109084 45.2 45.2 100.0 Total 241366 100.0 100.0 PaymentType
Frequency Percent Valid Percent Cumulative Percent Valid BC 187707
77.8 77.8 77.8 CA 41181 17.1 17.1 94.8 CK 7684 3.2 3.2 98.0 GC 422
.2 .2 98.2 HA 2229 .9 .9 99.1 NV 1687 .7 .7 99.8 PC 456 .2 .2 100.0
Total 241366 100.0 100.0
15. Section 3 Model Statement Group 4 15
16. Type of Model: Multinomial Logistic Regression Best suited
for modeling consumer choice 16 Model Statement Group 4
19. Discussion of Model Specification: Dependent Variable First
Channel Independent Variables Store Distance Customer Age First
Month of Contact Income Level Email Model Statement 19Group 4
20. Data Transformations Recode FirstYYMM to get FirstMonth
Experimented with creating interaction variables, but none were
significant Hypotheses 1. Customers who came through the internet
site would be younger than those who came through other channels.
2. Customers who lived farther from retail locations would be more
likely to choose the catalog or internet channels. Model Statement
20Group 4
21. Section 4 Interpretation of Findings Group 4 21
22. Set the stage: Dependent Variable: FirstChannel First time
users preference for order RET Retail store order CAT Catalog order
INT Internet Order Independent Variables: StoreDist = Distance to
nearest retail location AgeCode = Codes (1-7) for grouped ages
IncCode = Codes (1-9) for group income brackets Email = Y (yes) or
N (no) FirstMonth = derived from FirstYYMM the MM part (Jan (01)
Dec (12)) Goals - Understanding the customers first purchase may
lead to: Understanding how to market to these customers allowing
the company to increase profits and market growth. Additionally,
building customer loyalty by segmenting these customers and their
buying channels, Section 4: The Findings Group 4 22
23. Independent variable(s) impact on the dependent StoreDist
Further away distance more likely to use Internet as first order
purchase Shorter distance to retail location increases chance of
first time purchase as Retail channel. Segmenting these customers
within retail locations and marketing/advertising with store
coupons and flyers; using Internet marketing/advertising to those
not within reach of the retail locations; and further segmenting
non-internet using customers by use of catalog would make the most
sense AgeCodes All fell within the 5% significance level. Age
groups from 18-24 years old and 65-74 years old have less effect on
the dependent variable. The younger aged most likely do not have
the income to spend The elderly have less impact because they
probably do not spend much time on or perhaps never use the
Internet. Section 4: The Findings (continued) Group 4 23
24. Independent variable(s) impact on the dependent IncCode
Those in the low incomes levels (under 20K), and those in the
higher income level (100K and above), both are above the 5%
tolerance level It appears the income range of 30K to 99K has a
likely effect of making a first time purchase on the Internet. You
have to have money to spend money. Email: For the Catalog, analysis
does not show an impact and falls out of the 5% significance level.
It is significant for the Internet customer where most likely email
is a way of communication for billing, order receipt, etc. With
technology advances, many more customers have the ability to order
on the Internet and long as the customer remains receptive to this
channel, it may push down catalog orders. Exceptional customer
service drives catalog orders, which usually means the
multi-channel company invests in such practice and keeps it as part
of the business model. Section 4: The Findings (continued) Group 4
24
25. Independent variable(s) impact on the dependent FirstMonth
A few of the months fall out of the 5% significance level for both
Internet and Catalog. Summer months of Jun, Jul, and Aug and the
month of Oct for Internet Creates opportunity for first time
purchasers in the holiday months to use the channel of their
preference. Catalog has the months of Jan, Nov, and Dec as solid
months of first time purchases. Internet has the months most
effecting first time purchases as: Jan, May, Nov, Dec. These key
months should provide the multi-channel company an opportunity to
build brand loyalty efforts and encourage return purchases by
marketing/advertising to those first time purchasers. Section 4:
The Findings (continued) Group 4 25
26. Section 4: The Findings (continued) Group 4 26
27. Section 4: The Findings (continued) Group 4 27
28. Section 5 Summary and Conclusions Group 4 28
29. Multi-Channel Retailing Organization Overall Highly
Seasonal Mail Order/Catalog Holiday Peak 6-8X Higher Retail has
Smaller Holiday Peak More Consistent Throughout Year Most
Successful Segment Middle-aged High Income Home Owners Overall
Market Explosive Internet Growth Stagnating Mail Order & Retail
Storefront Summary 29Group 4
30. Multinomial Regression Consumer Choice Model Heavy Reliance
on IBMs SPSS Tool Two Models Developed First Time Mail Order
Purchases First time E-Commerce Purchases Two Hypotheses Effect of
Distance from Retail Store Younger Demographics Prefer Internet?
Summary 30Group 4
31. Distance from Retail Store The Farther Away Mail Order
& Internet Increase Conveniently Place Retail Pulls Sales Use
Model to Locate Retail Stores Age & Income Significance
E-Commerce Younger has Less Disposable Income Older Not Heavy
Internet Purchasers Model Good for Middle Aged & Middle Income
Mail Order Dont Like or Dont Want to Use Internet Channel
Conclusions 31Group 4
32. November & December Sales Peak Huge for Internet &
Mail Order Smaller but Still Significant for Retail Storefront Use
Retail Storefront to Smooth-Out Revenue Flow Mail Order &
Retail Down but Not Out First Time Buyers Mail Order Preferred
Channel Internet Close Behind Some Always Prefer Brick-and-Mortar
Experience Mail Order Preference Dont Like or Dont Want to Use
Internet Channel Conclusions 32Group 4
33. Use Model to Calibrate Retail Presence Distance to Store
Pulls Revenue Use Model to Fine-Tune Going Down- market
Higher-Income, Middle-Aged, Homeowners Opportunity to go
Down-market Continue Growing Internet Catalog not Going Away YET
Convert Mail-Order Buyers to Internet Opportunities 33Group 4