BUS5CA Customer Analytics and Social Media

*Tenure: how long ago a customer opened the account.
BUS5CA Customer Analytics and Social Media
Semester 2 2020
Assignment 3
Customer Churn Analysis
Release Date: 5th October 2020
Due Date: 25th October 2020 @ 11:59pm
Assignment Type: Individual
Weight: 40%
Format of Submission: A report (electronic form) and electronic submissions of analytics files
(SAS files and/or R scripts) on LMS.
Learning Objective:
The learning objective of this last assignment is to further develop your customer analytics
skills via performing customer churn analysis tasks.
Case Study:
Customer retention is a critical stage for customer relationship management (CRM), in
particular for established businesses after their initial exponential growth. Churn
management or attrition management is important as when customers leave, there are
negative impacts on revenues. Churn analytics has been widely applied to proactive
customer retention where descriptive and predictive analytics are utilised to identify and
predict customer propensity to churn.
Alpha Bank is conducting an analysis on their existing customer base with their
demographics information and account information recorded. As a business analyst, you are
tasked to analyse the data to provide insights of the churn population and develop as well
as evaluate predictive models for customer retention purposes.
Requirements:
The project is seeking insights and solutions relating to:
• Understanding the characteristics of its churned and not-churned customers;
• Understanding the characteristics of loyal customers (i.e. customers who do not
churn and are above a certain threshold of the tenure value*);
• Developing and evaluating models to predict customer propensity to churn;
• Recommending potential campaigns to buy back or win back the valued customers
who churned.
2
Data Descriptions:
The dataset required for this assignment is available on the remote server under the F drive:
‘F:BUS5CAAssignment3_DatasetBank_Churn.csv’. You should import the dataset file
into your SAS project, without keeping a copy under your own workspace folder.
The detailed descriptions of the dataset attribute is as follows:

Variable Names VariableDescriptions
CustomerID CustomerID
CreditScore Thecreditscoreofthiscustomer
Country Locationofthiscustomer(France,GermanyorSpain)
Gender MaleorFemale
Age Ageofthiscustomer
Tenure Tenureindexrepresentinghowlongthiscustomer opened
the account with Alpha bank (1-10 where 1 means a
relativeshorttimeand10meansarelativelongtime)
Balance Amountintheaccount
NumOfProducts Thenumberof products thatthiscustomerhaswithAlpha
Bank
HasCreditCard Whetherthiscustomerhasacreditcard(Yes/No)
IsActiveMember Whether this customer is active with different
functionalities with Alpha Bank, such as programs ,bonds,
insuranceetc. (Yes/No)
EstimatedSalary SalaryofthiscustomerestimatedbyAlphaBank
Churn Doesthiscustomerchurn?(Yes/No)

3
Task 1: Understanding the characteristics of churned, non-churned customers and loyal
customers (10%)
Conduct descriptive analysis based on the customer data and construct customer profiles
for each customer group.
Hints:
• Compare variables for churned, non-churned customers and loyal customers using
descriptive analytics.
• Loyal customers are a subset of non-churned customers. They are the top non-churned
customers based on the tenure variable (tenure >= 9).
Task 2: Developing and evaluating models to predict propensity to churn (20%)
a) What is the overall churn rate and the group churn rate for the categorical variables?
(For example: gender (yes and no), country (France, Germany and Spain), etc.)
b) Identify the combination of two categorical variables that has the highest group churn
rate.
c) Use SAS Enterprise Miner to develop and evaluate at least three predictive models for
churn prediction.
• Apply standardization (z-score normalization) on the continuous/interval variables.
Why you need to apply this? (You may use the Transform Variable node covered in
the workshop activities in Week 8.)
• What are the selected variables used for building the prediction models?
• What are the predictive performance of various models and how they rank against
one another? (Note: You should drill down to various machine learning metrics,
which include the overall accuracy, the misclassification rate (churn / non-churn),
ROC, Lift.)
• How do you best interpret the model?
Hints:
• Refer to the workshop activities in Week 10.
• Use 70% training data, 30% validation data partitioned randomly.
• You can get the confusion matrix from the output window of the model comparison
node under the name ‘Event Classification Table’.
• You may use other analytics tools to support this task if needed (such as Excel or R).
• Overall churn rate = (Number of churning customers / Total number of customers in
the dataset)
• Group churn rate = (Number of churning customers in the group / Total number of
customers in the group)
4
Task 3: Campaign recommendations based on insights obtained from Task 1 and Task 2
(10%)
Provide campaign recommendations based on insights obtained from the first two tasks
above.
Hint: You need to use your knowledge in campaign management or perform some research
to answer this question.
You are required to:
a) Prepare a report with answers for the above three key tasks.
(You can use an appendix for any additional screenshots which you feel are
important for the report. Please do not put screenshots in the main content of the
report. The main content of the report should consist of well-formatted graphs and
tables.)
b) The written report should be saved with the file name:
StudentID_Assignment3_Report.doc
c) Save the SAS project for Task 2 as the SPK file with the file name:
StudentID_Assignment3_Task2.spk
d) If you have some R code for Task 1 and 2, save it as:
StudentID_Assignment3_Task1.R or StudentID_Assignment3_Task2.R;
or if you have used Excel for Task 1 and 2, save it as:
StudentID_Assignment3_Task1.xlsx or StudentID_Assignment3_Task2.xlsx.
The same submission rule applies for any other visualization/analytics tools.
e) Submit the written report, the SAS Model files, and the supporting R files/Excel files
or other visualisation/analytics files to the LMS Assignment submission site.
Report Guidelines:
1. The report should consist of a table of contents, an introduction, and logically
organised sections/topics, a conclusion and a list ofreferences where necessary.
2. Choose a fitting sequence of sections/topics for the body of the report.
3. You must include diagrams, tables and charts from the analytics solutions to effectively
present your results.
4. Page limit: no more than fifteen (15) pages for the main report writing and no more
than twenty (20) pages including appendices.
5. Reports should be written in Microsoft Word (font size 11 with 1.15 line spacing) and
submitted as a Word file.
6. Final submission will comprise two separate submissions:
a. StudentID_Assignment3_Report.doc (should not be zipped);
b. StudentID_Assignment3_AllFiles.zip (in zip format) including all analytics files – all
the SAS SPK files and the R files/Excel files or other visualisation/analytics files).
5
Marking Rubrics:
A grade will be awarded to each of the tasks and then an overall mark determined for the
entire assessment. The rubric below gives you an idea of what you must achieve to earn a
certain ‘grade’.
As a general rule, to meet a ‘C’, you must first satisfy the requirements of a ‘D’. And for an
‘A’, you must first satisfy the requirements of a ‘B’, which must of course first meet the
requirements of a ‘C’ and so on.
The marking rubric for this assignment is given below.

Criterion Pass Credit Distinction HighDistinction
CasestudyTask1:
Characteristicsof
churnedornot
churnedcustomers
andloyalcustomers
(10 marks)
Limitedeffortto
addressquestions
andpresent
informationand
insights.
Limitedknowledgeof
thetoolsinvolved.
Faireffortto
addressquestions
andpresent
informationand
insights.
Fairknowledgeof
thetoolsinvolved.
Excellenteffortto
addressquestions
andpresent
informationand
insights.
Excellentknowledge
ofthetools
involved.
Exceptional effortto
addressquestions
andpresent
informationand
insights.
Comprehensive
knowledgeofthe
toolsinvolved.
CasestudyTask 2:
Developingand
evaluatingmodelsto
predictpropensityto
churn
(20 marks)
Limitedeffortto
addressquestions
andpresent
informationand
insights.
Limitedknowledgeof
SASEnterpriseMiner.
Faireffortto
addressquestions
andpresent
informationand
insights.
Fairknowledgeof
SASEnterprise
Miner.
Excellenteffortto
addressquestions
andpresent
informationand
insights.
Excellentknowledge
ofSAS Enterprise
Miner.
Exceptional effortto
addressquestions
andpresent
informationand
insights.
Comprehensive
knowledgeofSAS
EnterpriseMiner.
CasestudyTask3:
Campaign
recommendations
basedoninsights
obtainedfromTasks
1and2
(10 marks)
Recommendations
reflectafairgraspof
theproblemdomain,
data,insightsand
expectations.
Recommendations
reflectagoodgrasp
of theproblem
domain, data,
insightsand
expectations.
Recommendations
reflectanexcellent
graspofthe
problem domain,
data,insights
andexpectations.
Recommendations
reflectaninclusive
graspoftheproblem
domain,data,
insights and
expectations.

Other important information:
• Standard plagiarism and collusion policy, and extension and special consideration
policy of this university apply to this assignment.
• A cover sheet is NOT required. By submitting your work online, the declaration on
the university’s assignment cover sheet is implied and agreed to by you.

The post BUS5CA Customer Analytics and Social Media appeared first on My Assignment Online.

GET HELP WITH YOUR PAPERS

CLICK HERE TO GET THIS ANSWER FROM EXPERTS DONE

WhatsApp
Hello! Need help with your assignments?