7/7/22, 10:12 PM Assignment 1 - Summer 2022 MGMT 59000-DY2-Y02 - Merge
https:
purdue.
ightspace.com/d2l/le/content/557459/viewContent/9756432/View 1/4
Assignment 1
Instructions
Summer 2022 MGMT 59000-DY2-Y02 - Merge
Overview
Assume you are the data analytics team for a gaming company in Europe. Annie, you
hotshot data scientist is hired away by your competitor.
Problem 1
Annie left with an incomplete query. Here is some data from one of your product showing
players and the level that they’re cu
ently playing:
Players
Player_ID Player_Name Rank Level_ID
13 Raven Cadet 48
25 CryHavoc Lieutenant 51
37 oolala Lieutenant 17
443 TheSquid Colonel 89
509 meh Cadet 48
… … … …
https:
purdue.
ightspace.com/d2l/le/content/557459/navigateContent/4861/Previous?pId=9756430
https:
purdue.
ightspace.com/d2l/le/content/557459/navigateContent/4861/Next?pId=9756430
https:
purdue.
ightspace.com/d2l/home/557459
7/7/22, 10:12 PM Assignment 1 - Summer 2022 MGMT 59000-DY2-Y02 - Merge
https:
purdue.
ightspace.com/d2l/le/content/557459/viewContent/9756432/View 2/4
Levels
Level_ID Level_Name
48 Caverns of Doom
51 Lake of the Undead
17 Forest of Evil Things
89 Island of Darkness
… …
You’d like to see how many players of each rank are playing each level. Annie's incomplete
query looks like this:
SELECT count(*) as num_players, Rank FROM Players
JOIN Levels ON (Players.Level_ID = Levels.Level_ID) GROUP BY LevelName;
What is wrong with this query, and why? How would you fix it? Please show the results.
Problem 2
Go to the following URL, and download the sampled dataset on Last.fm music service usage:
https:
www.kaggle.com/datasets/neferfufi/lastfm
Imagine you have been asked by to analyze this dataset to understand the engagement of
their customer base, with an eye toward investigating different monetization models.
a. Using GCP tools and any model of your choice, develop customer scoring metrics (one
y each team member) to indicate the value of users. Summarize the results of scoring
in a dashboard.
https:
www.kaggle.com/datasets/neferfufi/lastfm
7/7/22, 10:12 PM Assignment 1 - Summer 2022 MGMT 59000-DY2-Y02 - Merge
https:
purdue.
ightspace.com/d2l/le/content/557459/viewContent/9756432/View 3/4
Submissions
No submissions yet. Drag and drop to upload your assignment below.
Drop files here, or click below!
. Explain the approach you took in part (a), why you chose it, and what are its
limitations.
c. Explain what you would ideally do next, if you were doing this in your job and had the
time and resources you needed to do it to your satisfaction.
d. Each team is required to produce a dashboard combing the work of all individual team
members.
Please upload a zip file consisting of any scripts, outputs, screenshots, or any other relevant
work you did for this question.
Question 3
Briefly outline some ways data science and analytics could be applied to benefit, "The Last
of Us: Part II."
Question 4 (Individual Extra Credit: 2 Points
maximum)
Go to the following URL, and play the free demo version of the game Botanicula, developed
y Amanita Design: http:
otanicula.net
Imagine that the developers have asked you for advice on what metrics should be tracked in
this demo, to help them understand how people play and engage with it. What would you
advice be? Please be as specific and concrete as you can.
Question 5 (optional)
Please give us your feedback! How was the assignment? Too easy/hard? Too short/long?
How much time did you spend on it? What skills did you apply to complete this
assignment?
http:
otanicula.net