000			02500nam a22002777a 4500
003			OSt
005			20260304100515.0
008			260304b |||||||| |||| 00| 0 eng d
040			_aTUPM _bEnglish _cTUPM _dTUPM _erda
050			_aTHE QA 14 _bR43 2023 c.2.
100			_aReal, Olivia D. _eauthor
245			_aPrediction of students performance using decision tree towards improvement of FOMA course content/ _cOlivia D. Real .--
260			_aManila: _bTechnological University of the Philippines, _c2023.
300			_axiii, 171pages: _c29cm.
336			_2rdacontent
337			_2rdamedia
338			_2rdacarrier
500			_aMaster's thesis
502			_aCollege of Science .-- _bMaster of Arts in Teaching Mathematics: _cTechnological University of the Philippines, _d2023.
504			_aIncludes bibliographic references and index.
520			_aThe study aimed to predict the performance of the students in Fundamentals of Mathematics Analysis (FOMA) using Decision Tree. It involved 348 students from the Computer Studies Department, College of Science, who are officially enrolled in Bachelor of Science in Computer Science (BSCS), Bachelor of Science in Information Systems (BSIS), and Bachelor of Science in Information Technology (BSIT). Based on the gathered data, the findings of the study are the following: the students have an average performance in the four (4) assessments (formative and summative) that include seatwork, assignments, long quizzes, and final examination; significant positive marked relationship exists between formative and students’ final grade in FOMA, marked relationship between summative assessment and their final grade in FOMA, and substantial relationship between formative assessment and summative assessment, the appropriate predictive modeling is CHAID on the ten-level category, but in the binary pass/fail category C & RT Model performance is better because of its high sensitivity and overall accuracy; CHAID model performed well if the dataset is a multi-level classification and C&RT performed better if the dataset is a binary level category, hence the best algorithm for the prediction of the performance of the students in FOMA among the Decision Tree models is based on the dataset and its classification. Keywords: Student Performance, Decision Tree, C5.0, C & RT, and CHAID
650			_aMathematics _vstudy and teaching
650			_aDecision tree
650			_aFOMA course content
942			_2lcc _cTHE _n0
999			_c31301 _d31301