ML Quiz 2

Classification accuracy alone can be misleading if you have ________ number of observations in each class.

• A equal

• A correct

• A wrong

• An unequal

The confusion matrix visualizes the ____ of a classifier by comparing the actual and predicted classes.

• Connectivity

• Comparativity

• Accuracy

• Stability

We have a data-set where we are predicting number of people who have more than $1000 in their bank account. Consider a data-set with 200 observations i.e. n=200 from the above matrix

• Out of 200 cases, our classification model predicted “YES” 125 times, and “NO” 65 times.

• Out of 200 cases, our classification model predicted “YES” 135 times, and “NO” 60 times.

• Out of 200 cases, our classification model predicted “YES” 135 times, and “NO” 65 times.

• Out of 200 cases, our classification model predicted “YES” 135 times, and “NO” 5 times.

From the above Table

• In reality, there are totally 125 accounts who have a balance more than $1000 and 10 accounts with balance - less than $1000

• In reality, there are totally 60 accounts who have a balance more than $1000 and 70 accounts with balance - less than $1000

• In reality, there are totally 135 accounts who have a balance more than $1000 and 70 accounts with balance - less than $1000

• In reality, there are totally 130 accounts who have a balance more than $1000 and 70 accounts with balance - less than $1000

Machine learning classification metrics like “Accuracy” give ___ useful information.

• More

• Less

• Perfect

• Accurate

High entropy means that the partitions in classification are

• Not pure

• Useful

• Pure

• Useless

A confusion matrix is used for classification tasks where the output of the algorithm is in ……. class/classes

• Two

• More than three

• One

• Two or more

Suppose we would like to convert a nominal attribute X with 4 values to a data table with only binary variables. How many new attributes are needed?

• 8

• 1

• 4

• 2

The confusion matrix is used when there are two or more classes as the output of the classifier.

• True

• False

What lies in the x axis of ROC curve?

• Sensitivity

• Precision

• Specificity

• Recall

• 1 - Specificity