Academic Analytics: Applying C4.5 Decision Tree Algorithm in Predicting Success in the Licensure Examination of Graduates

Clarin, Jeffrey A.; Romana, Cherry Lyn C. Sta.; Feliscuzo, Larmie S.

doi:10.1109/ccoms.2019.8821710

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…J.Clarin, C.Sta. Romana and L.Feliscuzo (2019, p.193) and (2020, p. 143) [16], [17] had established a predictive analytics system using Decision Tree Algorithm. The main focus of their study was to forecast the performance of graduates in the teacher education program.…”

Section: Review Of Related Literaturementioning

confidence: 99%

J48-Based Algorithm in Predicting the Success Rate in the Board Examination

Clarin¹

2020

IJATCSE

Self Cite

View full text Add to dashboard Cite

J48 algorithm was utilized in this study to predict the performance rate in the Board Examinations for Teachers Education program (LET) of the secondary teacher education graduates. To develop the model, the raw scores in the college entrance examination as well as the general average (GA) in the core subjects, professional subjects, and common subjects were considered. Likewise, the performance in the LET review and in the actual LET Board, whether pass or fail were also taken into consideration. A total of 348 examples was deliberate came from 2012 to 2017 list of graduates. The pruned tree summed up to 16 utilizing 10 leaves. The Kappa value was established to be 0.8195 meaning an almost perfect agreement. In other words, all of the categorized instances by the researcher-developed J48-based academic analytics model had closely matched the actual count data. Hence, predicted failures, could be promptly given appropriate intervention programs by the dean and the professors in order to enhance the scores and GA of students. By so doing, the success rates in the LET will be improved. The J48 algorithm was tested at Aklan State University (ASU) [1] due to the absence of a data-mining system that could predict success in the LET. Therefore, the sets of data used in this study were from ASU specifically in Kalibo Campus. In its entirety, this study might help in determining the success rates of graduates in the LET that could eventually help in the accreditation of teacher education programs.

show abstract

Section: Review Of Related Literaturementioning

confidence: 99%