Description
This is a continuing assignment I’ll upload the first two related assignments . For this phase, you will submit a Tableau packaged workbook (*.TWBX) containing your prepared and extended data. Your submission should contain all necessary joins and/or blends, any additional data preparation identified in previous milestones, and at least one (1) hierarchy. In addition, the submission should contain a minimum of three (3) visualizations pertaining to your analysis. The visualizations submitted for this milestone are considered works-in-progress; they are not required to be in their final state or to be part of your M4 dashboard submission. The goal in submitting them is for you to demonstrate that you were able to connect the source data with TABLEAU, have started your analysis, and to provide a starting point about your plans moving into M4. Finally, on a NAPKIN draw a rough draft of how you imagine your final dashboard. Following an example of a napkin dashboard: From the picture above, consider in your napkin draft: Size of your dashboard (e.g. 800 x 800 pixels). TABLEAU allows you to customize the size. Is it for a Desktop audience? Tablet audience? etc. Also consider how your final work will look on a mobile phone. What’s the title of your dashboard? Simple visualizations, for example, N.1 (Sales Total) or N.2 (Averages) Advanced visualizations, for example, N.3 (Sales over time), N.4 Sales by Format (Bar graph), N.5 Sales by location (Map) Are you going to consider images or logo images? Top right-hand corner. How about filters? or Actions? (Actions will be covered in the lectures, no worries) Imagine how all the objects will interact with each other. M3 Deliverables: If necessary, a revised version of your dataset that addresses any issues/needs outlined in your M2 review. A Tableau packaged workbook (*.TWBX) meeting the specifications outlined above. An image in *.jpg format of your Napkin dashboard rough draft. Do not turn in your image as file type -> *.HEIC
Unformatted Attachment Preview
Customer Churn Analysis
Name
Institution
Course
Instructor
Date
1
Customer Churn Analysis
What is the variation in churn rates depending on the preferred login device used by
customers?
2
How does the preferred login device vary across different city tiers?
Churn rate by preferred mode of payment
3
Insights
During my investigation, I have had the opportunity to work with an extensive dataset
comprising 5,630 individuals who are consumers. The substantial dataset utilized in this study
provides a solid basis for my analysis, guaranteeing the results’ dependability and
comprehensiveness. I’ve uncovered a critical insight within this dataset—a noteworthy overall
churn rate of 16.84%. The metric indicates significant customer attrition, highlighting the
importance of implementing customer retention initiatives to ensure long-term viability.
4
Upon further investigating user activity, I have identified noteworthy patterns concerning the
devices users use to log in. Customers who choose computer-based login methods demonstrate
somewhat elevated churn rates compared to smartphone users. This finding highlights the
importance of understanding and adapting to diverse user behaviors and preferences depending
on the selected login device. Furthermore, our research of geographical data indicates distinct
differences in churn rates among cities of different tiers. Specifically, Tier 1 cities exhibit lower
churn rates than Tier 2 and Tier 3 cities. The observed discrepancies might be ascribed to various
variables, such as market competitiveness and diverse customer preferences. Identifying these
differences facilitates the development of customized approaches that address the specific
characteristics of each urban classification, thus enhancing efforts to retain customers.
5
References
Verma, A. (2021, January 26). Ecommerce customer churn analysis and prediction. Kaggle.
https://www.kaggle.com/datasets/ankitverma2010/ecommerce-customer-churn-analysisand-prediction?sort=most-comments
6
Customer Churn Analysis
Name
Institution
Course
Instructor
Date
1
Customer Churn Analysis
What is the variation in churn rates depending on the preferred login device used by
customers?
2
How does the preferred login device vary across different city tiers?
Churn rate by preferred mode of payment
3
Insights
During my investigation, I have had the opportunity to work with an extensive dataset
comprising 5,630 individuals who are consumers. The substantial dataset utilized in this study
provides a solid basis for my analysis, guaranteeing the results’ dependability and
comprehensiveness. I’ve uncovered a critical insight within this dataset—a noteworthy overall
churn rate of 16.84%. The metric indicates significant customer attrition, highlighting the
importance of implementing customer retention initiatives to ensure long-term viability.
4
Upon further investigating user activity, I have identified noteworthy patterns concerning the
devices users use to log in. Customers who choose computer-based login methods demonstrate
somewhat elevated churn rates compared to smartphone users. This finding highlights the
importance of understanding and adapting to diverse user behaviors and preferences depending
on the selected login device. Furthermore, our research of geographical data indicates distinct
differences in churn rates among cities of different tiers. Specifically, Tier 1 cities exhibit lower
churn rates than Tier 2 and Tier 3 cities. The observed discrepancies might be ascribed to various
variables, such as market competitiveness and diverse customer preferences. Identifying these
differences facilitates the development of customized approaches that address the specific
characteristics of each urban classification, thus enhancing efforts to retain customers.
5
Below is the E-commerce dataset data dictionary:
Field Name
CustomerID
Data Type
Serial
Churn
Boolean
Tenure
Integer
PreferredLoginDevice
Text
CityTier
WarehouseToHome
Integer
Integer
PreferredPaymentMode
Text
Gender
Text
HourSpendOnApp
Integer
NumberOfDeviceRegistered
Integer
PreferedOrderCat
Text
SatisfactionScore
Integer
MaritalStatus
Text
NumberOfAddress
Integer
Description
Unique Customer
ID
Churn Flag (0 or
1)
Tenure of
customer in
organization (in
months)
Preferred login
device of customer
City tier
Distance between
warehouse and
home of customer
(in kilometers)
Preferred payment
method of
customer
Gender of
customer
Number of hours
spent on mobile
application or
website
Total number of
devices is
registered to a
particular
customer
Preferred order
category of
customer in last
month
Satisfactory score
of customers on
service
Marital status of
the customer
Total number of
addresses
registered to a
particular
customer
Example
50001
1
4
Phone
3
6
Debit Card
Female
3
4
Laptop &
Accessory
2
Single
9
6
Complain
Boolean
OrderAmountHikeFromlastYear Integer
CouponUsed
Integer
OrderCount
Integer
DaySinceLastOrder
Integer
CashbackAmount
Currency
Any complaint has
been raised in last
month (0 or 1)
Percentage
increases in order
from last year
Total number of
coupons used in
last month
Total number of
orders placed in
last month
Day(s) since last
order by customer
Average cashback
in last month
1
11
1
1
5
160
7
References
Verma, A. (2021, January 26). Ecommerce customer churn analysis and prediction. Kaggle.
https://tinyurl.com/mr4apma2
8
Purchase answer to see full
attachment
