Students Academic Performance Prediction Using Decision Tree
This study explores student’s academic performance using decision tree algorithm having parameters like Student’s Academic Information and Students Activity. We collected records of 22 students from Spring 2017 semester, studying in undergraduate level from Oman’s private Higher Education Institution. Proposed work utilizes Electronic Commerce Technologies module since it is a core module offered in every computing specialization. Furthermore, WEKA data mining tool is used to evaluate the decision tree algorithm for discovery of student’s performance along with Moodle access time. Simulation results demonstrate that Random Forest Tree algorithm showed better accuracy than comparative decision tree algorithms. Hence, shows good agreement for the training set provided. Therefore, the proposed work aid in improving student’s grades in the module. Helping stakeholders to analyze and evaluate the module delivery and results. Early detection and solution can be made both at the institutional level and module level.
Keywords—component; VLE; WEKA; Data mining; Classification; Decision tree
Table of Content
- 1.1 Background of the Study
- 1.2 Statement of the Problem
- 1.3 Aim and Objectives of the Study
- 1.4 Research Questions
- 1.5 Significance of the Study
- 1.6 Scope of the Study
- 1.7 Limitation of the Study
- 1.8 Definition of Terms
Review of Literature
- 2.1 Conceptual Framework
- 2.2 Theoretical Framework
- 2.3 Empirical Review
- 3.1 Data and Attribute Selection
- 3.2 Proposed Model
- 3.3 Preparation
- Result and Analysis
Summary, Conclusion and Recommendation
- 5.0. Introduction
- 5.1. Summary
- 5.2 Conclusions
- 5.3. Recommendation
- 5.4. Further Work
In an educational system, a large amount of data is kept. This data may be students’ data, alumni data, teachers’ data, non-teaching staff data, resource data, and so on. Educational data mining is used in discovering the patterns in these data for decision-making (Edin Osmanbegovic, 2012).
Educational data mining can answer a lot of questions from the patterns obtained from student data, questions such as:
- Who are the students at risk of failing in the future?
- What is the quality of student participation?
- Who are the students likely to drop a course?
- What are the chances of student gaining promotion to the next class
- Which courses should a department offer to attract more students?
- How many students should be accepted into the department every session.
The results of educational data mining can be used by different members of the educational system such as the examiners, teachers, security officers and the students. Students can use them to identify the activities, resources and learning tasks needed to improve their learning. Teachers can use them to get more objective feedback, to differentiate the stronger students from the weaker students and to guide the weaker students (also considered as students at risk) and help them to succeed. The security officers can use the result of educational data mining to identify and locate students in the case of an emergency. The result of educational data mining can also be used by the institution to identify the most commonly made mistakes and to organize the contents of the institution’s website in an efficient way.
There are two types of educational systems:
A. Traditional education system:
The traditional education system involves direct contact between the students and the teacher. Students’ record which include information such as attendance, and grades may be kept manually or digitally. The performance of students is a measure of this information.
B. Web based learning system:
The web based learning system is also known as e-learning. It is becoming the more expedient approach towards education and it has become more popular as the students can learn from any place without any time constraint. In the web based education system, various data about the students are automatically collected through logs.
This project work describes a model that predicts the academic performance of students in a traditional education system. The following development will help us to understand the relevance of this model because reducing the number of students who fail is the main aim of this project work. Since inferior students are also enrolled into the institutions, the results of the institutions are depreciating when it comes to good grades therefore if we know in advance which students are likely to fail, the institutions or the teachers can take the necessary steps towards improving the results. This will help in improving the quality of graduates that are produced yearly from these institutions ( R.R. Kabra and R.S Bichkar, 2011).
1.1.Background of the Study
Since one of the goals oftertiary institutions is to contribute to the improvement of the quality and standard of higher education, the success in the creation of human capital has been a subject of continuous analysis. Hence the prediction of students’ success is very important to these higher education institutions, because the purpose of any teaching process is to meet students’ educational needs and enhance overall student’s academic success. In this regard, important data and information are gathered on a regular basis after which they are used in the prediction of students’ academic performance (Edin Osmanbegovic, 2012).
Measuring and predicting the academic performance of students has been a challenging task since students’ academic performance depends on diverse factors such as personal, socio-economic, psychological and other environmental variables. But the prediction of student’s performance is a very important endeavor as it helps the student and teachers to minimize poor academic performances and produce better educated and enlightened students in order to make the society a better place. With the help of performance prediction, a failing student can be identified and helped by putting all the factors affecting the student into consideration and providing solutions to counter this factors so as to facilitate better performance (Brijesh Kumar Bhardwaj and Saurabh Pal, 2011).
1.2. Statement of the Problem
Without adequate measures to curb the existing problem of persistent students’ failure, it will continue to remain a major problem for higher institutions. But with the analysis of the factors which are socio-economic, psychological and environmental, a headway can be made towards curbing the problem of student failure.
1.3. Aim and Objectives of the Study
The aim of this project is to predict a student’s performance using the decision tree method.
The specific objectives are:
- To identify various factors that affect the performance of students in their academic endeavors.
- To use the identified factors as well as the student’s past performance to predict the future performance of the student.
- To develop a model which can predict student’s academic performance using decision tree method.
1.4 Research Question
- What are the various factors that affect the performance of students in their academic endeavors?
- What model can predict student’s academic performance using decision tree method?
1.5. Significance of the Study
- To help teachers and tutors identify weak and strong students so teachers can lay more emphasis on instructions and procedures when dealing with the weak students
- To help the students identify and eliminate those factors either found in the student himself or the school or the society.
- To help the tutors and teachers find solutions to the problems affecting the weaker students so as to enhance overall academic performance.
1.6. Scope of the Study
This project work titled students academic performance prediction using decision tree attempts to analyze those factors that affect the students academically. Furthermore, this work predicts the future academic performance of students but does not automatically address these problems as the tutors and teachers and even the students themselves still need to take steps towards curbing the performance problem by eliminating this factors themselves.
1.7 Limitation of the Study
Like in every human endeavour, the researcher encountered slight constraints while carrying out the study. Insufficient funds tend to impede the efficiency of the researcher in sourcing for the relevant materials, literature, or information and in the process of data collection, which is why the researcher resorted to a limited choice of sample size. More so, the researcher simultaneously engaged in this study with other academic work. As a result, the amount of time spent on research will be reduced.
1.8 Definition of Terms
Data mining, also known as database knowledge discovery, is the process of extracting or “mining” information from huge volumes of data.
A decision tree is a flowchart-like tree structure in which each internal node represents a test on an attribute, each branch represents a test outcome, and each leaf node (or terminal node) represents a class label.
This is also known as school ready, academic accomplishment, and school performance, but the differences in ideas are only explained by semantics because they are used as synonyms.
In this chapter, the summary, further work, conclusion and recommendation are discussed so as to recommend institutions and individuals to make use of the decision tree in their students’ academic performance prediction and guide individuals and institutions who intend to use the decision tree in student academic performance prediction. The chapter also recommends whoever wishes to improve upon this work to make use of one of the decision tree inducers such as ID3, C4.5, CART, CHAID, QUEST.
In summary, the academic performance of students in any institution determines the overall success of the institution, and it is therefore necessary for the teachers and tutors to find a constructive approach that can be used to reduce or eliminate the rampant failure of students. In this project work, the several factors that affect the academic performance of students such as gender, interest in sports, mode of transportation to school, parental occupation, time invested in daily study, availability of internet connection, school location were analyzed and it was found that the most essential of these factors is the student’s past academic performance.
The analyzed factors can help the tutors and teachers as well as the students to curb the issue of unnecessary academic failure. The decision tree technique has been utilized in predicting the future academic performance of students. It has been discovered that students with higher score during their entrance exams have a higher tendency to continue and the students with lower entrance score have a tendency to encounter problems during their course of study in the institution.
The study investigated 8 different classifiers algorithms that might help the stakeholders to improve and improvise and early intervention to improve the results of the module and enhancing student’s experience. It was found that Random Forest, Naïve Bayes and SMO give good agreement for the training set. As, the kappa value of Random Forest and SMO found very good as it was 1. For the supplied dataset and training used it was found Random Forest was best suitable for the module based on the lower mean absolute error and relative absolute error. This model can be used with the other modules and can be tested for better analysis and accuracy in order to be applicable. This can help faculty members handling a module to check the possible outcome of students in the module and do the necessary actions. Stakeholders can benefit and analyze and evaluate the module delivery and results.
The decision tree method of students’ academic performance prediction is recommended for institutions, teacher, tutors and students to help in predicting the future academic performance of students and to help in recognizing the factors that work against the success of students and consequently help the students, teachers and tutors to reduce the impact of these factors or to totally eliminate the factors by taking necessary steps.
5.4. Further Work
In order to get results that can be represented in terms of percentage of accuracy, an interested individual or group who intend to carry out further work on this project is recommended to make use of any of the decision tree inducers by implementing collected student data on a workbench such as WEKA in order to be able to calculate the percentage of accuracy of the decision tree and to improve the level of understanding of the students, tutors and the teachers.
The Complete Material Will Be Sent to You in Just 2 Steps
Quick & Simple…
Make Payment (Through Transfer) of ₦5,000 to Any of the Account Below
|Acc No: 0811003731
|Acc No: 1225513212
Or CLICK HERE To Pay With Debit Card
|FOR STUDENTS OUTSIDE NIGERIA
|CLICK HERE To Purchase Material ($15)
|FOR GHANIAN STUDENTS
|Make Payment of 120 GHS to 0553978005 | Douglas Cloud Osabutey | MTN MoMo
Send the Following Details on WhatsApp ( 08143831497) After Payment
- Payment Details
- TOPIC: Students Academic Performance Prediction Using Decision Tree
The Complete Material Will Be Sent To You On WhatsApp After Receiving Your Details
T & C Apply