The error rate for the classification matrix will be 8.65%
An effective predictive analytics technique for assessing a classification model is a classification matrix, sometimes referred to as a confusion matrix. For a measure with a binary result, it comprises two rows and two columns that are used to compare projected values and actual values. The confusion matrix can be used to calculate a classification model or system's sensitivity, specificity, accuracy, precision, negative prediction value, and error rate.
The error rate is calculated as the sum of all inaccurate predictions divided by the total number of entries in the matrix. The error rate should ideally be 0.0, and the closer it gets to 1.0, the worse the test performs as a gauge of whether or not someone has WNV.
Determine what we know first:
Records with fraud classifications = 88
Records deemed to be free of fraud: 952
With this knowledge, we can calculate the number of records in the database as:
n = 88 + 952 = 1,040
Next, arrange the classification or confusion matrix using expected and actual values as follows:
n=1,040 Non-Fraudulent Fraudulent/th>
Actual: Non-Fraudulent (A) 920 (C) 58
Actual: Fraudulent (B) 32 (D) 30
Third, we determine the error rate, which is the proportion of all records to the sum of wrong fraudulent and non-fraudulent records, or:
Error Rate = (C + B) / n = (32 + 58) / 1040 = 90 / 1040 = 0.0865 = 8.65%
Therefore Error Rate is 8.65%
To know more about Classification Matrix, refer to this link:
https://brainly.com/question/26866373
#SPJ4
