Competency Discovery System: Integrating the Enhanced ID3 Decision Tree Algorithm to Predict the Assessment Competency of Senior High School Students

Abstract

The study presents the development of Competency Discovery System, which integrates enhanced Iterative Dichometer 3 (ID3) decision tree algorithm, to predict assessment competency of senior high school students. It was also successful in integrating the feature selection to select the data attributes that have impact on the performance of students. Pre-processing of data collected from school database and available spreadsheets was performed to determine the attributes that may possibly influenced the students' competency assessment. It provides a decision tool for teachers to enhance students' performance, particularly in the academic and technical aspect, based on factors that might affect their learning process. The academic and technical performance is often used for predicting the learning behaviour of the students and can be a crucial factor in building their better future. Moreover, the system identifies students that were likely to fail, and that may need assistance in view of the National Certificate programmingrelated assessment. The National Certificate assessment aim to regulate the students can perform to the standards expected in the workplace based on the defined competency standards. Passing the competency assessment shows that the students is ready to join the labour workforce. Predicting the future outcomes based on the historical records can help the teacher guide the students' assessment performance. This is also beneficial to students as they have the opportunity to prepare for taking the assessment. Majority of the participants assessed the software as 'highly acceptable' with support on its implied functions in terms of reliability, efficiency, usability, security, and user-friendliness.

Comprehensive Evaluation of College Students’ Physical Health and Sports Mode Recommendation Model Based on Decision Tree Classification Model

“…Vasquez and Comendador used ID3 algorithm to judge the working technology and learning ability that high school students have mastered at present, and make recommendation decisions for students, so as to judge the suitable direction of students' study in the future university [11]. Pang collected the evaluation data set of teaching assistants from the university machine learning database, established ID3 decision tree based on these data, and found the maximum information gain in different iteration levels.…”

Deep Learning in Skin Disease Image Recognition: A Review

“…The recognition accuracy is more than 70% [18]. In the same year, Ning et al used machine learning ID3 [19], classification and regression tree [20], and AdaBoost three different algorithms for feature extraction of their performance [21]. The AdaBoost performed well in these algorithms [22].…”

Measuring Students' Academic Performance through Educational Data Mining

“…Our goal here is to study/predict students' learning activities based on a set of attributes described in [12]. Similar works are found in [13] and [14]. The training datasets that are combined from Sample A are used to build the model as shown in Table I (from one to fifty samples).…”