Study shows reliable model to predict licensure exam outcome

Upgrade to High-Speed Internet for only ₱1499/month!

Enjoy up to 100 Mbps fiber broadband, perfect for browsing, streaming, and gaming.

Visit Suniway.ph to learn

December 24, 2025 | 12:00am

MANILA, Philippines — A study conducted by experts from the University of the Philippines-Diliman showed that logistic regression is a reliable model for predicting the performance of licensure examination takers.

Released by the UP Office of the Vice President for Academic Affairs, the study was authored by Arturo Patungan of UP-Diliman College of Education and University of Santo Tomas Department of Mathematics and Physics, and Ma. Nympha Joaquin of UP-Diliman College of Education.

The authors noted that the passing rate in the Licensure Examination for Teachers or LET has been declining in the Philippines, from 31.45 percent in 2010 to just 27.28 percent in 2018.

A study was conducted to predict the performance of future math teachers in the LET using machine learning, the UP Office of the Vice President for Academic Affairs said, with the researchers testing three different algorithms: Gradient Boosted Trees, Logistic Regression and Naïve Bayes.

After evaluating the models based on accuracy, precision and other performance metrics, all three models showed good results, with logistic regression proving to be the most reliable.

The authors said that the logistic regression model performed best when applied to evaluation data, making it the most suitable for predicting LET outcomes.

The researchers said that the significance of the study lies in its potential to substantially improve teacher preparation and the overall quality of education in the Philippines.

Patungan and Joaquin said logistic regression can help higher education institutions identify students who may need additional support, enabling more targeted interventions and personalized learning strategies, which could result in better preparation for the LET and lead to higher passing rates.

The study underscores the importance of leveraging machine learning to drive positive change in teacher education, ensuring that prospective teachers are better equipped for the challenges they will face in the classroom.

Over 70,000 examinees passed the licensure examination for professional teachers given last Sept. 21 and Nov. 30.