For each of the data mining problems below, say which data mining task best

describes that problem. Note that the question is not asking you to give the

name of any algorithm to solve that task, it is just asking for the name of the

task. For instance, if you think the task is classification, your answer should be

just $$classification$,$ without any algorithm name.

$($i$)$ A library has a database of users which contains, for each user, a list of

the books that they have borrowed. The library wants to analyse this

data to divide the users into groups, where each group should consist

of users who have borrowed similar sets of books.

$[2$ marks$]$

$($ii$)$ A company has a large number of subscribers to its movie streaming

services, where each customer can watch any movie at any time. The

company maintains a database with information about all movies

watched by each customer, including the time when each movie was

watched. The company wants to analyse this data to find out which

groups of movies tend to be watched together by a customer within the

same week $($from Monday to Sunday$).$

$[2$ marks$]$

$($iii$)$ A company has a database of complaint calls received from their

customers. For each call, the database has the gender and age of the

customer who made that call, the call$$s duration, and the information

whether or not the customer cancelled their contract with the company

within $48$ hours after making that call. The company wants to analyse

this data in order to understand the differences between the

characteristics of calls made by two groups of customers: the ones who

cancelled and the ones who did not cancel their contract within $48$

hours after their call.