Effect of class absenteeism on grade performance: A Probabilistic Neural Net (PNN) based GA trained model Conference Paper uri icon


  • Most faculty inherently believe that students who frequently miss class significantly increase their likelihood of poor grades by doing so. The purpose of this research was to develop a Probabilistic Neural Net (PNN) based Genetic Algorithm to assess the relationship between absenteeism and student grade performance in a structural systems course taught by the author. The model was trained to classify the outcomes (pass/fail) of 130 students using records of class attendance and end-of-course final grades. The relative importance/weight of attendance on final grades was then determined. It was found that course attendance and grade performance were positively correlated. The model was then used to accurately predict the success rate of a new group of 80 students based on provided attendance records. Overall, this research shows that the developed PNN based GA model can be used to predict the outcome of student performance in the structural systems class based on anticipated class absence patterns. 2012 American Society for Engineering Education.

published proceedings

  • ASEE Annual Conference and Exposition, Conference Proceedings

author list (cited authors)

  • Haque, M. E.

publication date

  • January 1, 2012 11:11 AM