Skip to main content

Table 3 Accuracy, sensitivity, and specificity of the two models with different thresholds

From: Precision education with statistical learning and deep learning: a case study in Taiwan

ThresholdPrediction modelAccuracyaSensitivitybSpecificityc
10%Multilayer perceptron77%53%80%
Logistic regression68%61%69%
15%Multilayer perceptron83%42%88%
Logistic regression80%50%84%
20%Multilayer perceptron87%42%93%
Logistic regression84%38%90%
50%Multilayer perceptron90%16%99%
Logistic regression88%0%100%
  1. aAccuracy = predicted number (dropout students + current students) / actual number (dropout students + current students)
  2. bSensitivity = predicted number of dropout students / actual number of dropout students
  3. cSpecificity = predicted number of current students / actual number of current students