Student Academic Performance Prediction Using Supervised Learning Techniques
Student Academic Performance Prediction Using Supervised Learning Techniques
Student Academic Performance Prediction Using Supervised Learning Techniques
Muhammad Imran (*), Shahzad Latif, Danish Mehmood, Muhammad Saqlain Shah
Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, Pakistan
dr.imran@szabist-isb.edu.pk
1 Introduction
92 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
from huge sets of data, also known as knowledge discovery in databases (KDD). It has
been applied successfully in multiple domains including banking, medical, business and
now has been used for educational purposes called Educational Data Mining.
The prediction of student performance is a crucial task which is being researched by
using EDM. This task foresees the value of an unidentified variable which describes
the students regarding outcome (Pass/Fail), grades, marks etc. Predicting student Attri-
tion, failures, success are the main areas which are discussed in the literature review of
this study. Each stakeholder belongs to this domain wants an early warning system to
predict learning on early stages. This early warning system not only reduced the learn-
ing costs but also time and space requirements.
One of the biggest challenges is to improve the quality of the educational processes
so as to enhance student’s performance. Instructors can update their teaching method-
ology to fulfill the requirement of poor performance students and can provide additional
guidance to deserving students. The prediction results might help students develop a
good understanding of how well or bad they would perform in a course and then can
take steps accordingly. Increasing the student retention is a long-term target of any ed-
ucational institutions around the globe. There are many positive impacts of increased
retention such as increased college reputation, ranking and better job opportunities for
alumni etc.
To analyze data using classification technique, well known classification algorithms
such as Decision tree (DT), Artificial neural networks (ANN), K-neatest neighbor
(KNN) and Rule Induction (RI) are being used for prediction purposes. Quality of a
predictive classification model is measured by its ability to find out the unknown pat-
terns accurately. This study employed three classification algorithms J48 from DT,
NNge from IR and MLP from ANN for experimental purposes. The major objective of
the proposed methodology is to build the ensemble classification model that classifies
a students’ performance as Pass or Fail.
2 Previous Work
Dorina et al. [1] proposed a predictive model for student’s performance by classify-
ing students into binary class (successful / unsuccessful). The proposed model was con-
structed under the CRISP-DM (Cross Industry Standard Process for Data Mining) re-
search approach. The classification algorithms (OneR, J48, MLP and IBK) were ap-
plied on the given dataset. The results show that the highest accuracy was achieved by
the MPL model (73.59%) for identification of successful while other three models per-
form better for the identification of unsuccessful students. The model was unable to
work out for data high dimensionality and class balancing problems.
Edin Osmanbegovicet al. [2] builds a model to predict student academic success in
a course by reducing data dimensionality problem. Various machine learning classifiers
such as NB, MLP and j48 were evaluated in this study. The result shows that the Naïve
Bayes gained the highest accuracy 76.65%. The proposed model not handles the class
imbalance problem.
Carlos et al. [3] addressed a student failure prediction model based on machine learn-
ing techniques to resolve the class imbalance and data dimensionality problems. Ten
classifiers were applied on dataset. The ICRM classifier achieved the highest accuracy
92.7% among others. Due to varying student’s characteristics at each educational level,
the performance of proposed model was not tested for other levels of education.
Another EDM Challenge is to predict the drop-outs of the students from their courses
[4]. Four data mining methods with six combinations of attributes were participated in
this study. The result shows that the support vector machine model with the combina-
tion of the predictor variables was more accurate while classifying the data. The inclu-
sion of an attribute, earned grades of pre-requisite courses in the data set was the limi-
tation of this study because it might be possible that during study of any course the
student might have improved his knowledge of pre-requisite of this course.
Ajay et al. [5] conducted study on the prediction of student performance. The main
contribution of the study was to introduce a new social factor called “CAT” which de-
scribes that in early times Indians were divided into four types of groups on the basis
of their social status etc, which have a direct effect on the student education. Four clas-
sifiers oneR, MLP, J48, and IB1 were applied on the data set. The results indicated that
the IBI model was the highest accuracy (82%) achieved.
Build an improved version of the ID3 model, which predicts the student academic
performance [6]. The weakness of the ID3 model was its intension to select those at-
tributes as a node which had more values. In a result generated tree was not efficient.
The proposed model overcomes such problem. Two output classes were produced by
this model (Pass and Fail). The classifiers including J48, wID3 and Naïve Bayes were
applied and results compared. The wID3 achieved high accuracy 93%.
Alaa Khalaf et al. [7] proposed a model to predict student success performance in
courses. Three Decision Tree classifiers such as (J48, Hoeding tree, Reptree) were em-
ployed by this study. The highest accuracy 91.47 % was achieved by Reptree. The
model was unable to work out for data high dimensionality and class balancing prob-
lems.
Dech Thammasiri et al. [8] proposed a model to provide early classification of poor
academic performance of freshmen. Four classification methods with three balancing
methods were applied to resolve class imbalance problem. In results the combination
of support vector machine and SMOTE achieved the 90.24% highest overall accuracy.
An early warning system was proposed to predict the student learning performances
during an online course based on their learning portfolios data [9]. The results showed
the approaches accompanied by time dependent variables had high accuracy than other
approaches which were not included it. The model was not tested on offline mode. The
performance might be decreased in offline mode using time dependent attributes.
Mostly previous studies were assumed that the data mining algorithms performed
well with only large data sets but this study supported that the data mining is also suit-
able for small datasets as well [10]. This research proposed a student success prediction
model. A small dataset including student academic data was used by using three deci-
sion tree approaches (Reptree, J48, M5P). The result claims that the Reptree obtained
the highest accuracy above 90% among them. The proposed model not supported to
data high dimensionality and class balancing problems.
94 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
Camilo et al. [11] proposed a model to predict student academic attrition by over-
coming class imbalance problem. Two algorithms Naïve Bays and Decision tree were
used by this study. A cost-sensitive approach. Metacost was used to manage this prob-
lem. After that highest accuracy was got by naviey bays upto 85%. The data collection
at the end of academic period is not feasible because no one can get benefit at that time.
A student academic performance prediction model was proposed in this study [12].
The classifiers namely J48, Decision Stump, Reptree, NB and ANN with three kinds of
attribute setups were evaluated in this study. The J48 classifier achieved the high accu-
racy 90.51%.
Proposed approached was contributed by evaluated three number of classes (drop-
out, persisting, and completed) while predicting student dropout [13]. Ten classification
models were assessed. The results of experiments depict that the Naïve Bayes algorithm
had the highest predicting levels for the three classes of students.
Bilal et al. [14] presented a student failure prediction model which identified the
students that might be at-risk. Four output classes (Average, Risk, below Average and
Above Average) were generated by the proposed model based on the CGPA of the
students. Six classifiers including were applied on the given dataset. The ID3 got the
highest accuracy 79.23%. The model was unable to work out for class imbalance prob-
lem.
An ensemble model including classifiers (NB, SVM, KNN) was proposed for the
identification of weak students [15]. The dataset included a most effective attribute as
standard based grading assessment in addition to typical score-based grading. The re-
sults of proposed model with six other individual classifiers were compared and con-
clude that the accuracy of ensemble model was 85% which is higher than others.
A multilevel classification model was proposed to resolve the multiclass classifica-
tion problem in the prediction of student performance [17]. The goal of study was not
only to increase the model accuracy but also increase the accuracy of the individual
classifier. The model contains two levels. Initially a re-sampling technique was per-
formed on the dataset to overcome the class distribution problem in the preprocessing
phase. In the first level, four classification models were applied on the dataset namely
IBK, MLP, NB, J48. Results were evaluated and compared. The results show that the
decision classifier (j48) was highly accurate and selected for use in the next level. In
the level two, outliers were identified by comparing the previously predicted results
with actual results and removed accordingly. Once again re-sampling technique with
high accurate classifier which was selected previous (J48) was applied onto the filtered
dataset and results were compared with the results of applying remaining classifiers
also on the filtered dataset. The results depict that the J48 classifier got the above 90%
accuracy for overall model as well as for individual classes prediction.
An early student failure identification model was proposed in this study by evaluat-
ing data mining techniques as well as preprocessing approaches. Several techniques and
models were applied (ANNs, decision trees, support vector machines, naïve bayes) in
this study and conclude that the support vector machines is outperformed from the oth-
ers ones [18]. The data was collected from two different types of data sources. Model
not supported for reducing the classification errors.
3 Methodology
To address the common issues of above literature review such as class imbalance,
data hi-dimensionality and classification errors, this study has proposed a model which
have following phases. Figure 1 shows the main steps of proposed methodology.
96 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
500
0
Pass Fail
After re-sampling on the training set, 50% PASS and 50% FAIL students are ob-
tained.
98 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
TPrate= TP/TP+FN
• F-Measure: measured from recall and precision values (double value of precision
multiplied by recall divided by the value of summation of recall and precision).
100 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
100,00%
80,00%
60,00%
40,00% J48
20,00% Nnge
0,00% MLP
re
ll
I
on
IC
CC
ca
su
isi
Re
ea
ec
M
Pr
F-
Fig. 3. Single Classifier Based Performance Measures
In the second experiment, proposed methodology has performed step by step. Re-
sults can be seen in table 3 with graphical representation in figure 4. It has been ob-
served that the highest accuracy achieved is 95.78% by J48 classifier and the lowest
accuracy achieved 92.81% by NNge. It has observed that after reducing class imbal-
ance, data high dimensionality as well as by using ensemble method the proposed
model accuracy has improved significantly for all classifiers.
120,00%
100,00%
80,00%
60,00% J48
40,00% Nnge
20,00%
MLP
0,00%
re
I
on
ll
IC
CC
ca
su
isi
Re
ea
ec
M
Pr
F-
During this experiment, we have also measured the classification errors in terms of
Root Mean Squared Error (RMSE). Figure 5 shows the graphical representation of
RMSE. This clearly shows the results with and without ensemble classification errors
rates.
RMSE
0,4
0,2
0 RMSE
e…
…
se
8
LP
ns
J4
En
M
8E
LP
J4
102 http://www.i-jet.org
Paper—Student Academic Performance Prediction using Supervised Learning Techniques
5 Conclusion
6 References
[1] Dorina Kababchieva. (2012). Student Performance Prediction using Data Mining Classifi-
cation Algorithms. International Journal of Computer Science and Management Research,
vol. 1.
[2] Edin Osmanbegovic and Mirza Suljic. (2012). Data mining approach for predicting student
performance. Journal of Economics and Business, vol. X, Issue 1.
[3] Carlos Marques-Vera and Alberto Cano. (2013). Predicting student failure at school using
genetic programming. ApplIntell, vol. 38, pp.315–330.
[4] Shaobo Huang and Ning Fang. (2013). predicting student academic performance in an engi-
neering dynamic course: A comparison of four types of predictive mathematical models.
Computers & Education, vol. 61, pp. 133–145. https://doi.org/10.1016/j.compedu.2012.08.
015
[5] Ajay Kumar Pal and Saurabh Pal. (2013). Data Mining Techniques in EDM for Predicting
the Performance of Students.International Journal of Computer and Information Technol-
ogy, vol. 02, Issue 06.
[6] Ramanathan, Saksham Dhanda and Suresh Kumar D. (2013). Predicting Student Perfor-
mance using Modified ID3 Algorithm. International Journal of Engineering and Technol-
ogy, vol. 5 No 3.
[7] Alaa Khalaf Hamoud. (2016). Selection of Best Decision Tree algorithm for prediction and
classification of student Action. American International Journal of Research in Science,
Technology, Engineering & Mathematics, vol 1, pp. 26-32.
[8] Dech Thammasiri, DursunDelen, PhayungMeesad andNihatKasap. (2014). A critical assess-
ment of imbalanced class distribution problem: The case of predicting freshmen student at-
trition. Expert Systems with Applications, 41, pp.321–330. https://doi.org/10.1016/
j.eswa.2013.07.046
[9] Ya-Han Hu, Chia-Ling L and Sheng-Pao Shih. (2014). Developing early warning systems
to predict students’ online learning performance. Computers in Human Behavior, 36, pp.
469–478. https://doi.org/10.1016/j.chb.2014.04.002
[10] SreckoNatek and Moti Zwilling. (2014). Student data mining solution–knowledge manage-
ment system related to higher education institutions. Expert Systems with Applications, 41,
pp.6400–6407. https://doi.org/10.1016/j.eswa.2014.04.024
[11] Camilo Ernesto Lopez Guarín, Elizabeth León Guzmán, and Fabio A. González. (2015). A
Model to Predict Low Academic Performance at a Specific Enrollment Using Data Mining
IEEE Transactions, vol. 10(3).
[12] Sana Akhai and Ruchi Karia. (2017). Automated Performance Evaluation Sys-
tem.IJARIIT,3(2).
[13] Laci Mary Barbosa Manhaes, Sergio Manuel Serra da Cruz and Geraldo Zimbrão. (2016).
Towards Automatic Prediction of Student Performance in STEM Undergraduate Degree
Programs. ACM. https://doi.org/10.1145/2695664.2695918
[14] Bilal Mehboob, Rao Muzamal Liaqat andNazar Abbas Saqib. (2016). Predicting Student
Performance and Risk Analysis by Using Data Mining Approach. International Journal of
Computer Science and Information Security (IJCSIS), vol. 14, No 7.
[15] Farshid Marbouti and Krishna Madhavan. (2016). Models for early prediction at risk stu-
dents in a course using standard based grading.Computers & Education, 103, pp. 1-15.
https://doi.org/10.1016/j.compedu.2016.09.005
[16] Cortez, Paulo, Alice Maria andGonçalves Silva. (2008). Using data mining to predict sec-
ondary school student performance. [Online]. Available: http://archive.ics.uci.edu/ml/
machine-learning-databases/00356/student.zip. [Accessed: 23- Jun- 2016].
[17] Mrinal Pandey and S.Tarun. (2014). A Multi-Level Classification Model Pertaining to the
Students’ Academic Performance Prediction. International Journal of Advances in Engineer-
ing & Technology,4: 1329-1341.
[18] Santana, M.A., Costa, E.B., Fonseca, B., Rego, J., and de Araújo, F.F (2017). Evaluating the
effectiveness of educational data mining techniques for early prediction of students’ aca-
demic failure in introductory programming courses. Computer. Human. Behavior,73: 247–
256. https://doi.org/10.1016/j.chb.2017.01.047
7 Authors
Muhammad Imran is Assistant Professor of computer science in the department of
computer science at Shaheed Zulfikar Ali Bhutto Institute of Science and Technology
(SZABIST), Islamabad, Pakistan. He received hid PhD degree in Information Technol-
ogy from University Tun Hussin onn Malaysia. His main research interests include data
mining, Evolutionary computing, Computer Vision and Medical image processing.
(dr.imran@szabist-isb.edu.pk)
Shahzad Latif received PhD degree in Electronics Engineering from ISRA Univer-
sity, Islamabad Pakistan. Currently he is Assistant Professor in the department of com-
puter science at Shaheed Zulfikar Ali Bhutto Institute of Science and Technology
(SZABIST), Islamabad, Pakistan. His main research interests include Computational
Intelligence, Digital Signal Processing and Fuzzy systems (dr.shahzad@szabist-
isb.edu.pk)
Danish Mehmood received PhD degree in Smart Grid from Comsats University,
Islamabad Pakistan. Currently he is Assistant Professor in the department of computer
science at Shaheed Zulfikar Ali Bhutto Institute of Science and Technology
(SZABIST), Islamabad, Pakistan. (dr.danish@szabist-isb.edu.pk)
Muhammad Saqlain Shah got his degree of Master of Science in the Faculty of
Computing and engineering sciences from Shaheed Zulfikar Ali Bhutto Institute of Sci-
ence and Technology (SZABIST), Islamabad, Pakistan. His main research interests in-
clude data mining, machine learning (msaqlain80@hotmail.com)
Article submitted 2019-02-13. Resubmitted 2019-03-22. Final acceptance 2019-03-25. Final version pub-
lished as submitted by the authors.
104 http://www.i-jet.org