Predictive modeling of the first year evaluation based on demographics data: Case study students of Telkom University, Indonesia

Fahrudin, Tora; Buliali, Joko Lianto; Fatichah, Chastine

doi:10.1109/icodse.2016.7936158

Cited by 6 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Low economic indicators trigger students to choose to get a job than continuing their studies in higher education. Another similar study as shown in [10], variable age and study program are also correlated to decide dropout students through the first-year study.…”

Section: Astesj Issn: 2415-6698mentioning

confidence: 85%

Predictive Modelling of Student Dropout Using Ensemble Classifier Method in Higher Education

Hutagaol¹,

Suharjito²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Currently, one of the challenges of educational institutions is drop-out student issues. Several factors have been found and determined potentially capable to stimulate dropouts. Many researchers have been applied data mining methods to analyze, predict dropout students and also optimize finding dropout variables in advance. The main objective of this study is to find the best modeling solution in identifying dropout student predictors from 17432 student data of a private university in Jakarta. We also analyze and measure the correlation between demographic indicators and academic performance to predict student dropout using three single classifiers, K-Nearest Neighbor (KNN), Naïve Bayes (NB) and Decision Tree (DT). We found indicators such as student's attendance, homework-grade, mid-test grade, and finals-test grade, total credit, GPA, student's area, parent's income, parent's education level, gender and age as student's dropout predictors. The results only get 64.29 (NB), 64.84% (DT), and 75.27%(KNN) while we tried to combine algorithms with Ensemble Classifier Methods using Gradient Boosting as meta-classifier and gets better about 79.12%. In addition, we also get the best accuracy of about 98.82% using this method which was tested by 10-fold cross-validation.

show abstract

Section: Astesj Issn: 2415-6698mentioning

confidence: 85%

Predictive Modelling of Student Dropout Using Ensemble Classifier Method in Higher Education

Hutagaol¹,

Suharjito²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…In addition to the predictor variables, the prediction method is one of the important components that determine the accuracy of the prediction results. There are several prediction methods that are often used [22], namely Decision Tree (DT) [1], [9], [12], [16]- [21], Naïve Bayes [1], [15], [16], [18]- [21], K-Nearest Neighbor [1], [14], [15], [18], Rule based [9], Artificial Neural Network (ANN) and its development [11], [13], [16], [18], Random Forest (RF) [15], Support Vector Machine (SVM) [15], [16], [18], and the Regression group [18].…”

Section: B Prediction Methodsmentioning

confidence: 99%

“…Evaluation of model performance is calculated using various measures, namely accuracy [1], [10]- [12], [16], [20], [21], Recall [1], [9]- [11], [19], [20], Precision [1], [9]- [11], [19], [21], F1-measure [1], [9], [10], [19], Mean Square Error (MSE) [3], Mean Absolute Error (MAE) [3], [13], Area under the Curve (AUC) [19]- [21], and Kappa [18]- [20]. The most widely used measure is accuracy.…”

Section: B Prediction Methodsmentioning

confidence: 99%

“…Various kinds of predictor variables are used by researchers to get the results of predicting student performance with high accuracy. Predictor variables that are usually used are academic data [3], [5], [10]- [12], [14], [16], [17], [19]- [21], demographics [9]- [11], [14], [18]- [21], social [9], [11], [21], managerial [11], [21], and psychological [11], [16].…”

Section: A Predictor Variablementioning

confidence: 99%

“…One form of existing research is to form a predictive model to provide the information needed to screen, monitor and improve student academic performance [8]. Research related to the prediction of student passing from the evaluation of first year studies [9], [10] is useful for screening excellent prospective students. Meanwhile, research related to the prediction of passing a course [11], [12] and prediction of the score of a course [3], [13], [14] can be used to support decision making in determining appropriate efforts to help students, especially those with less ability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Two-Stage Early Prediction Model to Monitor the Students' Academic Progress

Limanto

Buliali

Saikhu

2022

2022 10th International Conference on Information and Communication Technology (ICoICT)

View full text Add to dashboard Cite

The dropout rate and the percentage of students who graduate on time are some of the problems at higher education institutions. Various research has been conducted to overcome these problems, one of which is predicting student performance. The results of student performance predictions can be used as an early warning for students, lecturers and institutions to prepare a strategy so that students who are predicted to "fail" can succeed at the end of the class. However, not all predictor variables that have significant effects on the model can be obtained at the beginning of the class. The purpose of this research is to develop a two-stage prediction model to determine the passing of each student from the courses undertaken. The first stage of the prediction model was developed at the beginning of the class while the second was developed at the end of the eighth week by adding two predictor variables, namely the score of the mid term test and the number of attendance in class. The two predictors were added to improve the performance of the predictive model. Four different methods are used in the prediction: Decision Tree, Random Forest, Support Vector Machine, and Logistic Regression. In testing, all performance measures of LogisticsRegression method were superior to other methods both in the first and second stages. It is also seen that the addition of predictor variables was able to increase the accuracy, recall, and F1measure values of all prediction models by up to 7%.

show abstract

Tri-XGBoost model improved by BLSmote-ENN: an interpretable semi-supervised approach for addressing bankruptcy prediction

Smiti,

Soui,

Ghedira

2024

Knowl Inf Syst

View full text Add to dashboard Cite

Predictive modeling of the first year evaluation based on demographics data: Case study students of Telkom University, Indonesia

Cited by 6 publications

References 11 publications

Predictive Modelling of Student Dropout Using Ensemble Classifier Method in Higher Education

Predictive Modelling of Student Dropout Using Ensemble Classifier Method in Higher Education

A Two-Stage Early Prediction Model to Monitor the Students' Academic Progress

Tri-XGBoost model improved by BLSmote-ENN: an interpretable semi-supervised approach for addressing bankruptcy prediction

Contact Info

Product

Resources

About