Predictive Model to Predict the Test Scores of the Computer Skills-2 Course for Future Students in Irbid University College

In this paper, we are interested in predicting the computer skills-2 scores for Irbid University college students based on a relationship between the time spent studying for the computer skills-2 test and the final scores, we used it as training data to learn a model that uses the study time to predict the test scores of future students in Irbid University College who are planning to take computer skills-2 course. The predicting model use regression analysis as a type of supervised learning that use to predict the continuous outcomes, we are given a number of predictor variables (the time spent on study for computer skills-2 daily, the time spent on study before exam, the branch of secondary education (Al-Tawjihi) and the student major) and a continuous response variable (outcome/test scores), and we try to find a relationship between those variables that allows us to predict an outcome. The data for 400 students in two semesters was used as the test set for training the predictive model and we used data for 50 students to validate the predictive model. Results showed that the predicting model is useful to use to predicate students' scores. The error range between the predicative score and the actual score for the 50 students it's between +6 and -6. While the root mean squared error (RMSE) = 2.424871 and the root mean squared percentage error (RMSPE) = 4%. The time spent on study for computer skills-2 daily has the most critical influence on the student score.