K-Means

Question 1

Radius: ____________ from any point of the cluster to its centroid

Answer 1

square root of average distance

Question 2

Diameter: _______________ between all pairs of points in the cluster

Answer 2

square root of average mean squared distance

Question 3

What is the elbow method?

Answer 3

plots the value of the cost function produced by different values ofk.

Question 4

The value ofkat which improvement in distortion ___________ the most is called the elbow

Answer 4

declines

Question 5

Cost Function: For each k, calculate the ______________

Answer 5

total within-cluster sum of square (wss).

Question 6

Support:

Answer 6

Freq (X,Y) / N

Question 7

Confidence:

Answer 7

Freq (X,Y) / Freq (X)

Question 8

Lift:

Answer 8

Support / Support(X) * Support(Y)

Question 9

Conviction:

Answer 9

1-supp(y)/(1- conf(x->y))

Question 10

If an itemset is frequent, then all of its ______ must also be frequent

Answer 10

subsets

Question 11

If an itemset is not frequent, then all of its _______ cannot be frequent

Answer 11

supersets

Question 12

The ______ of an itemset never exceeds the _________ of its subsets

Answer 12

support

Question 13

Mining Association Rules

Answer 13

1. Generate all itemsets whose support >=minsup
2. Generate high confidence rules from each frequent itemset

Question 14

An association rule r is strong if

Answer 14

Support(r) ≥ min_sup
Confidence(r) ≥ min_conf

Question 15

Classification Accuracy

Answer 15

the number of correct predictions made as a ratio of all predictions made.

Question 16

Log Loss

Answer 16

a performance metric for evaluating the predictions of probabilities of membership to a given class.

Question 17

Area Under ROC Curve

Answer 17

a performance metric for binary classification problems.

Question 18

Sensitivity

Answer 18

the true positive rate also called the recall. It is the number instances from the positive (first) class that predicted correctly.

Question 19

Specificity

Answer 19

the true negative rate. Is the number of instances from the negative class (second) class that were predicted correctly.

Question 20

Gini Coefficient

Answer 20

2*AUC – 1

Question 21

The ROC curve

Answer 21

the plot between sensitivity and (1- specificity)

Question 22

AUC

Answer 22

the ratio under the curve and the total area

Question 23

Lift charts

Answer 23

a measure of the effectiveness of a predictive model calculated as the ratio between the results obtained with and without the predictive model.

Question 24

Calculate the points of the lift curve by

Answer 24

determining the ratio between the result predicted by our model and the result using no model.