Research Article

Using Machine Learning Techniques to Predict Learner Drop-out Rate in Higher Educational Institutions

Table 2

Attributes for student attrition modelling.

SectionAttributes | options

Personal and family biodataGender {male; female}
Age {18–22; 23–25; 26 or older}
My guardians/parents are {strict; accomodating}
Do you have siblings {yes; no}
What is the social class of your family {Upper; Middle; Lower}
My guardians/parents are (educational terms) {highly educated, moderately educated; uneducated}

Senior high school (SHS) trackerSHS school category {Single; Mixed}
Residential status in SHS {Day; Boarding}
In SHS, were you counselled on the programme to select at the university

University trackerThe majority of my lecturers are {Yes; No}
Do you think most of your lecturers should adopt new teaching strategies for you to understand the courses in detail {Yes; No}
Do you think campus facilities for students are standard enough for excellent academic work {Yes; No}
During lecturers, I prefer to be {Active, answer questions; Passive, be quiet}
Have you ever been counselled by the university’s counselling unit before? {Yes; No}
Do you have friends on campus {Yes; No}
Residential status in the university {Hostel; Hall; Home}
Accommodation status {One in a room; Two in a room; Three or more in a room}
Do you find it financially difficult to pay your fees every academic year {Yes; No}
Is it difficult to get accommodation every academic year? {Yes; No}
So far, how will you rate your overall academic performance { Excellent (CGPA 3.5 and above); Good (CGPA 2.5 to 3.4); Poor (CGPA 2.4 and below)}
What is your current level {100; 200; 300}

Decision trackerHave you ever considered/thought of stopping your programme of study at the university? {Yes, I want to quit; No, I will never quit}