M6

Question 1

2 types of learning of predictive analytics

Answer 1

supervised and unsupervised learnings

Question 2

what is a branch of data analytics that uses machine learning techniques to explore unlabeled data, uncover hidden structures, and make informed inferences about likely future behaviors or outcomes without relying on predefined target variables?

Answer 2

unsupervised learning

Question 3

what analytics aim to anticipate future events or trends based on current and historical data?

Answer 3

predictive analytics

Question 4

what learning helps identify clusters of similar behaviors or customers, anomalies and outliers, and latent structures in service processes?

Answer 4

unsupervised learning

Question 5

real-world use cases of unsupervised learning

Answer 5

healthcare
retail/e-commerce
telecom
smart cities

Question 6

segmenting shoppers to predict buying preferences

Answer 6

retail/e-commerce

Question 6

grouping patients based on treatment response to forecast health risks

Answer 6

healthcare

Question 7

identifying usage clusters to optimize network load and predict churn

Answer 7

telecom

Question 7

clustering neighborhood usage to forecast demand surges

Answer 7

smart cities

Question 8

2 types of unsupervised learning

Answer 8

time-series
cluster analysis

Question 9

time-series in service system

Answer 9

it supports demand forecasting in
1. electricity consumption
2. service calls,
3. emergency calls
4. service parts delivery

Question 10

what unsupervised learning is a sequence of data points recorded at successive, equally spaced points in time?

Answer 10

time-series

Question 11

time-series helps identify?

Answer 11

trend = long-term movement
seasonality = regular, periodic patterns
cyclicality = long-term economic or behavioral cycles
randomness/noise = irregular, unpredictable variation

Question 12

what are the popular forecasting models?

Answer 12

moving average
autoregressive
arima

Question 13

this forecasting model smooths short-term fluctuations to highlight trends

eg. averaging ticket volume to predict call center workload

Answer 13

moving average

Question 14

this forecasting model predicts current value using a linear combination of past values

eg. estimating service requests based on past daily values

Answer 14

autoregressive

Question 15

this forecasting model combines AR and MA with differencing for trends/seasonality

eg. forecasting energy usage, traffic flow, or call demand

Answer 15

ARIMA

Question 16

real industry application of time-series

Answer 16

airlines
telecom
healthcare

Question 17

forecasting booking trends to enable dynamic ticket pricing systems and optimize fleet allocation during peak travel seasons

Answer 17

airlines

Question 18

using ARIMA to predict bandwidth demand and optimize infrastructure upgrades, preventing service interruptions

Answer 18

telecom

Question 19

forecasting hospital appointments or emergency visit for staffing optimization. trends help align nurse shifts and specialist availability with peak demand

Answer 19

healthcare

Question 20

cluster analysis in service system

Answer 20

process of finding groups of objects such that the objects in a group are similar to one another and different from the objects in another group

Question 21

what technique is used to group data points into clusters based on similarity without the need for predefined outcome labels?

Answer 21

cluster analysis

Question 22

what are the clustering techniques?

Answer 22

K-means
hierarchical
DBSCAM

Question 23

what clustering technique divides data into k clusters by minimizing intra-cluster variance eg. segmenting customers by service use frequency

Answer 23

k-means

Question 24

what clustering technique creates a nested clusters in a tree-like structure (dendogram)? eg. exploring layers of user type

Answer 24

hierarchical

Question 25

what clustering technique forms cluster by density of data points? eg. detecting unusual usage or fraudulent behavior

Answer 25

DBSCAn

Question 26

what type of users access our services? are there hidden segments in behavior or complaints? what patterns predict valuable or at-risk customer?

Answer 26

cluster analysis

Question 27

real-industry applications of cluster analysis

Answer 27

e-commerce banking IT Services smart cities

Question 28

clustering shopper data to 1. identify deal-seekers vs. premium buyers 2. recommend products based on peer cluster behavior 3. personalize homepage and offers to increase conversions

Answer 28

e-commerce

Question 29

segmenting clients by transaction history and credit behavior to: 1. predict high-value customers 2. detect unusual patterns that may indicate fraud 3. customize financial services

Answer 29

banking

Question 30

clustering incident tickets based on keywords, time to resolution and source: 1. automates ticket triage 2. identifies recurring system 3. enhances knowledge base organization

Answer 30

IT services

Question 31

clustering neighborhoods based on water and electricity usage patterns to: 1. predict peak demand 2. design energy efficiency programs 3. prioritize infrastructure upgrades

Answer 31

smart cities