Multivariate Predictive Modelling of Mathematics Semestral Grade via Bayesian Networks Machine Learning Algorithm

  • Norie Neil C. Acosta College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines
  • Christian Kalki M. Lamadrid College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines
  • Rolando B. Barrameda College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines

Abstract

Purpose – This study pertains to the novel use of Bayesian Networks to elucidate the interplay between multivariate factors of demographics, personality types, mathematics anxiety, and study habits in predicting the mathematics grades of college students. The research tried to uncover the combination of predictor variables that would likely explain the failure of students across different math courses.

Method – The methodology follows a survey of 1200 DLSU-D students across the seven colleges of the university. Personality types were evaluated using the Myers-Briggs Type Indicator (MBTI), and mathematics anxiety was measured using the Abbreviated Math Anxiety Scale (AMAS). The machine learning implemented the framework of Probabilistic Graphical Models in Python (PGMPy) for data visualization and analyses. Predictions of possible grades were summarized, and the full Bayesian Network was established.

Results – Bayesian analyses have shown that the chances of failing a math subject are generally low for each year level. Personality variables conclude that college students with analyst roles have a higher probability of having a perfect 4.00 grade in a math subject than in an explorer role. Predicting the chances of failure between having or not having math anxiety seems almost no significant difference.

Conclusion – The subject, anxiety, consistency, and enjoyment variables are minimally enough to infer the probability of mathematics grades; hence all other variables can be ignored.  There was a total of 8 math subjects with predicted probabilities of failing students over a total of 13.

Recommendations – Researchers recommend the use of other probabilistic graphical models aside from Bayesian Networks to verify and compare the joint probabilities between the variables of the study.

Research Implications – Providing comprehensive insights to properly accommodate at-risk students in each math subject will greatly help mathematics professors recalibrate their attention and teaching strategies.

Author Biographies

Norie Neil C. Acosta, College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines

Norie Neil C. Acosta is currently a 4th year BS Applied Mathematics student at the College of Science and Computer Studies of De La Salle University – Dasmariñas, Cavite, Philippines. He was a recipient of the Gawad Talino 2019 Excellence in Mathematics Award by the Mercury Drugs Foundation. He is a consistent academic scholar, financial assistance scholar, city scholar, and provincial scholar ‒ currently maintaining a Summa Cum Laude Latin honor. As an Applied Mathematics student, he has a prospective inclination to truth and certainty of pure mathematics, statistics, data science, machine learning, and artificial intelligence. Norie Neil is currently under his thesis writing in spatiotemporal data mining of dengue epidemiology.

 

 

Christian Kalki M. Lamadrid, College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines

Christian Kalki M. Lamadrid is currently a 3rd year BS Computer Science student under the College of Science and Computer Studies of De La Salle University – Dasmariñas, Cavite, Philippines. He is taking the Intelligent Systems track and focusing on developing practical AI applications in software and robotics. He is proficient in software engineering and web development and has a background in computer engineering. Christian Kalki is adept in different programming languages and has an eye for their applications in different scientific research and studies.

Rolando B. Barrameda, College of Science and Computer Studies, De La Salle University – Dasmariñas, Cavite, Philippines

Mr. Rolando Barrameda is an Asst. Professor at the Computer Studies Department of De La Salle University - Dasmarinas, Cavite, Philippines, and has been teaching for nearly 16 years. He earned his Master's in Information Technology and continues to pursue his Ph.D. in Computer Science, currently working on his Dissertation with a specialization in Deep Learning, Machine Learning, and Artificial Intelligence. He authored and co-authored research papers that were published in different Scopus Indexed International Journals. He was a trainer and a speaker who delivered several local and international paper presentations. A certified Microsoft Office Specialist and Certified Microsoft Technology Associate.

Published
2023-01-05
How to Cite
ACOSTA, Norie Neil C.; LAMADRID, Christian Kalki M.; BARRAMEDA, Rolando B.. Multivariate Predictive Modelling of Mathematics Semestral Grade via Bayesian Networks Machine Learning Algorithm. International Journal of Computing Sciences Research, [S.l.], v. 7, p. 1937-1955, jan. 2023. ISSN 2546-115X. Available at: <//stepacademic.net/ijcsr/article/view/410>. Date accessed: 20 apr. 2024.
Section
Special Issue: IRCCETE 2023