Question 2 (40 points):
Imagine that you are the head of the marketing department of a chained beauty salon, namely, Galaxy Fashion. The recent global situation has significantly affected Galaxy Fashion’s business. In this regard, and to help the business, the CEO decided to run the following campaign: The CEO decided to randomly distribute 25% (discount) vouchers to its followers both on social media platforms (on Instagram, TikTok, Facebook, and Twitter) and through e- mail.
The CEO of Galaxy Fashion is now done with the campaign and is asking you to evaluate the results. In particular, the CEO would like to understand:
First Question (15 points): Overall, did the 25% (discount) voucher increase the number of transactions? By how much?
Second Question (10 points): Which channel(s) should be considered for the distribution of the 25% (discount) voucher in future campaigns?
To this end, you put together data from 10,000 of the customers (around half that received a voucher and the rest that did not receive a voucher; see ‘Galaxy_Fashion_a.csv’ dataset) that includes the following list of variables:
Variable Name
Description
id
ID of the customer
transac_after
number of transactions that the customer did after the campaign
voucher
“yes” if the customer received 25% (discount) voucher, “no” otherwise
channel
the channel that the customer received the voucher: = 1: e-mail
= 2: Facebook
= 3: Instagram
= 4: TikTok = 5: Twitter
prev_purchases
number of previous purchases
prev_spent
total of £ spent on previous purchases
last_visit
number of weeks since the last visit
single
1 if the customer is single, 0 otherwise
browsing_time
time (in minutes) spent on the website during the last visit
added_basket
“yes” if added a product to the basket during the last visit, “no” otherwise
Use the provided dataset (i.e., ‘Galaxy_Fashion_a.csv’) and run a linear model that helps you to find the drivers of the number of transactions after the campaign (i.e., the variable ‘trans_after’) using all the other (useful) variables listed in the respective dataset.
Page 3 of 8
In addition to answering the questions raised by the CEO, you conducted a separate analysis to investigate:
Third Question (15 points): Overall, did the 25% (discount) voucher increase the revenue?
To this end, you use the same dataset as above and replace the variable ‘transac_after’ with ‘reven_after’ (i.e., the revenue the customer generates after the campaign; see ‘Galaxy_Fashion_b.csv’ dataset).
Notes that you should consider in your answer:
• Include your R code and its respective results in your solution.
• Make sure that you clearly explain, justify, and detail all the assumptions and steps in
your solution. These might include data cleaning (e.g., dropping variable(s),
observation(s), changing type of variable(s), etc.) or any other assumptions or steps.
• Carefully and completely interpret your results (including all your coefficients).
• Critically evaluate the implications (based on all your results) for Galaxy Fashion. Make
sure that you use specific and concrete examples in your solution.
Page 4 of 8