Final

Question 1

What is probability?

Answer 1

How likely an event will occur

Question 2

What is conditional probablity?

Answer 2

The probability that A occurs given that B already occured

Question 3

What is an unsupervised technique?

Answer 3

Finds relationships between groupings of data points

Question 4

What is support

Answer 4

How frequently does the item occur in the dataset

Question 5

What is confidence?

Answer 5

How often a rule is found to be true?

Question 6

How do support and confidence thresholds work?

Answer 6

“-Select minimum acceptable values for support and confidence

• find association rules with support and confidence above chosen thresholds
• items with high support are called frequent”

Question 7

Why should you use association rules?

Answer 7

“-simple data model

-understandable and actionable rules “

Question 8

What is the apriori technique?

Answer 8

“-reduces number of calculations

• If a bundle is frequent then all of its subsets are frequent
• if a bundle is infrequent then all of the supersets are infrequent”

Question 9

What is lift?

Answer 9

“-confidence/expected confidence
-the ratio that the actual probability of a transaction occuring both item A and B to the probabillity that A and B would occur if they were independent “

Question 10

What is supervised method?

Answer 10

A way to describe the relationship between input attributes and a target attributes

Question 11

What is regression?

Answer 11

estimating the relationship between variables

Question 12

What is correlation?

Answer 12

The strength of the linear relationship

Question 13

What are some output types for data mining techniques?

Answer 13

“-regression

• classification
• ordinal “

Question 14

What is a regression analysis

Answer 14

looks at numerical range

Question 15

What is a classification analysis

Answer 15

factor or binary output like yes or no

Question 16

What is an ordinal technique

Answer 16

classfication with output

Question 17

What technique would you use for grouping things by similarity?

Answer 17

clustering

Question 18

What techinique is used to determine the relationship between input and output variables?

Answer 18

regression

Question 19

What technique would you use to assign labels to data based on charachterisitcs?

Answer 19

Classification

Question 20

What technique would you use to determine if there was a relationship between variables in the data?

Answer 20

association rules

Question 21

What technique would you use to find structure in a temporal data set.

Answer 21

time series

Question 22

What is a parametric model?

Answer 22

makes an assumption about the form or the shape of our data and then estimate the parameters of that function

Question 23

What is a non parametric model?

Answer 23

does not make an explicit assumption as to the function

Question 24

what is model stability?

Answer 24

process of finding a model that give accurate predictions for the whole population and not just individual samples

Question 25

What is overfitting?

Answer 25

model error where the results to closely fit the data set

Question 26

What is cross validation?

Answer 26

looking at how results will effect a certain data set

Question 27

What are posterior probabilities ?

Answer 27

The statistical probability that a hypothesis is true calculated in the light of revelant observations

Question 28

What is sensitivity

Answer 28

The true positive rate. the proportioni of positives that are correctly identified.

Question 29

What is specifity?

Answer 29

The true negative rate. the proportion of negatives that are correctly identified as such

Question 30

What is discriminant analysis?

Answer 30

Used to seperate groups from each other

Question 31

What are decision trees?

Answer 31

"Allows you to develop classification systems to predict or classify current and future observations based on a set of decision rules divide up a large collection of records into successively smaller sets of records by appying binary rules "

Question 32

What are the benefits of decision trees?

Answer 32

"-the input data and be ocntinous or discrete - the underlying assumption of of relationship beteen indpenedent and dependent variable - suited for classification and regression - easy to interpret "

Question 33

Why perform cluster analysis ?

Answer 33

find patterns in data

Question 34

WHat are challenges with cluster analysis?

Answer 34

"-how to we define similar? | -how do we handle otuliers "

Question 35

How do we define similarity?

Answer 35

"-symmetry | -triangle inequality"

Question 36

What is euclidean distance

Answer 36

distance between centroid and individual data point

Question 37

What is hieratchical clustering?

Answer 37

determine clusters based on some arbitary maximum distance a cluster object can be from another cluster object

Question 38

What is centroid based clustering

Answer 38

data is a part of a centroid

Question 39

What is confidence?

Answer 39

how certain you are that your results are accurate

Question 40

What is lift?

Answer 40

how well the model is performing

Question 41

What is inference vs prediction

Answer 41

"-inference used when we want to understand relationships between variables -prediction is used to predict "

Question 42

CRISP DM cycle

Answer 42

``` "-Business Understanding -Data Understanding -Data Prep -Modeling -Evaluation Deloyment " ```

Question 43

Which of the following metrics measures a model's ability to correctly identify positive values (select all that apply).

Answer 43

"-sensitivity - recall - true positive rate "

Question 44

What is a rule about association rules?

Answer 44

D. A large `confidence` in an association rule, will typically result in a higher lift when support is low

Question 45

Which of the following are true of Parametric Models? Select all that apply.

Answer 45

"A.Inferences can usually be made from a smaller number of predictors than with non-parametric models B.They are often simpler than non-parametric models D.They are usually less prone to overfitting than non-parametric models"

Question 46

Describe the Hold-Out approach to Cross Validation. | Why it is performed / why is it necessary?

Answer 46

You randomly select some parts of the data to use for test and you keep another subset for use it for training. Once you train the model you validate with the test set. You cross validate by repeatedly taking subsets to become training sets and test sets. It is performed to predict the accuracy and will tell how well a model will generalize to future observations