Programmer Performance Prediction with Cognitive Tests: A Granular Approach
SubjectCorrelation coefficient , Engineering profession , Aggregates , Education , Predictive models , Prediction algorithms , Distance measurement
MetadataShow full item record
AbstractUniversities and students face the challenge of finding the career that best suits the students. Programming is currently one of the highly sought-after careers and is one of the highest paying jobs. However not all students succeed in this career. In fact failure rates in programming field is relatively high globally. In this research, we used a spatial rotation test and Non-Verbal reasoning test as well as gender, at the beginning of the semester to observe the relationship between those tests and students' grades at the end of the semester for 2 groups. Group 1 are Computer Science students studying programming course and group 2 are non-Computer Science students studying programming course. For each group, we created a predictive model using 2 methods. Method 1 uses the conventional aggregate score of cognitive tests and method 2 uses answers to selected questions in each test. In method 2, we applied a data-driven methodology which utilize individual answers to questions as input to the model. To the best of our knowledge we are the first in this field to apply this method. The modeling results show usefulness of those test to predict programming and non-programming course grades using both methods, however method 2 demonstrates much higher superiority over the aggregate method 1.