nerdexam
Amazon

MLS-C01 · Question #95

Given the following confusion matrix for a movie classification model, what is the true class frequency for Romance and the predicted class frequency for Adventure?

The correct answer is B. The true class frequency for Romance is 57.92% and the predicted class frequency for Adventure. In a confusion matrix, the true class frequency for a given class is calculated by dividing the total number of actual instances of that class by the grand total of all instances (i.e., the row sum divided by the overall total). The predicted class frequency is the column sum…

Modeling

Question

Given the following confusion matrix for a movie classification model, what is the true class frequency for Romance and the predicted class frequency for Adventure?

Exhibit

MLS-C01 question #95 exhibit

Options

  • AThe true class frequency for Romance is 77.56% and the predicted class frequency for Adventure
  • BThe true class frequency for Romance is 57.92% and the predicted class frequency for Adventure
  • CThe true class frequency for Romance is 0.78% and the predicted class frequency for Adventure
  • DThe true class frequency for Romance is 77.56% * 0.78 and the predicted class frequency for

How the community answered

(17 responses)
  • A
    6% (1)
  • B
    76% (13)
  • C
    6% (1)
  • D
    12% (2)

Explanation

In a confusion matrix, the true class frequency for a given class is calculated by dividing the total number of actual instances of that class by the grand total of all instances (i.e., the row sum divided by the overall total). The predicted class frequency is the column sum divided by the overall total. Based on the referenced confusion matrix, the true class frequency for Romance is 57.92% (meaning 57.92% of all actual observations belong to the Romance class) and the predicted class frequency for Adventure falls at the corresponding value in option B. Options A and D suggest 77.56% for Romance, which does not match the row proportion from the matrix; option C suggests an implausibly low 0.78%.

Topics

#Confusion Matrix#Classification Metrics#Model Evaluation#Frequency Calculation

Community Discussion

No community discussion yet for this question.

Full MLS-C01 Practice