A Comparative Analysis of Classification Algorithms on Students’ Performance

2020 ◽  
Vol 8 (2) ◽  
pp. 20-34
Author(s):  
Nilar Aye
Keyword(s):  
Data Mining ◽  
Comparative Analysis ◽  
Comparative Evaluation ◽  
Classification Algorithms ◽  
Large Dataset ◽  
Classification Technique ◽  
Education Data ◽  
Future Events ◽  
Student’S Performance ◽  
Events Data

Recently educational system, many features control a student’s performance. Students should be well stimulated to study their education. Motivation leads to interest, interest leads to success in their lives. Appropriate assessment of abilities encourages the students to do better in their education. Data mining is to find out patterns by analyzing a large dataset and apply those patterns to predict the possibility of the future events. Data mining is a very critical field in educational area and it provides high potential for the schools and universities. In data mining, there are various classification techniques with various levels of accuracy. This paper focuses to make comparative evaluation of four classifiers such as J48, Naive Bayesian, Bayesian Network and Decision Stump by using WEKA tool.  This study is to investigate and identify the best classification technique to analyze and predict the students’ performance of University of Jordan.

Detection of Anomalous Transactions in Mobile Payment Systems

2020 ◽  
Vol 1 (2) ◽  
pp. 58-66
Author(s):  
Ibrar Hussain ◽  
Muhammad Asif
Keyword(s):  
Data Mining ◽  
Comparative Analysis ◽  
Economic Activity ◽  
Research Study ◽  
Mobile Payment ◽  
Financial Fraud ◽  
Classification Algorithms ◽  
Classification Models ◽  
Payment Systems ◽  
Substantial Impact

Mobile payment systems are providing an opportunity for smartphone users for transferring money to each other with ease. This simple way of transferring through mobile payment systems has great potential for economic activity. However, fraudulent transactions may occur and can have a substantial impact on the economy of a country. Financial fraud and anomalous transactions can cause a loss of billions of dollars annually. Therefore, there is a need to detect anomalous transactions through mobile payment systems to prevent financial fraud. For this research study, a synthetic dataset is generated by using a PAYSIM simulator due to the lack of availability of a realistic dataset. This research study performed experiments on a financial transactional dataset using eight data mining classification algorithms. The performance of classification models was measured by using evaluation metrics: accuracy, precision, F-score, recall, and specificity. A comparative analysis of classification models was also performed based on their performance.

scholarly journals C5.0 Algorithm Implementation on Web-Based Software and Usability Evaluation

SISTEMASI ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 394
Author(s):  
Deny Jollyta
Keyword(s):  
Data Mining ◽  
Decision Makers ◽  
Classification Algorithms ◽  
Test Results ◽  
Classification Problems ◽  
Process Data ◽  
Web Based ◽  
Classification Technique ◽  
Software Classification ◽  
Algorithm Implementation

AbstrakPerangkat lunak merupakan alat bantu yang memudahkan pengguna dalam pengolahan data dengan cepat dan tepat. Para pengambil keputusan membutuhkan alternatif perangkat lunak yang dapat digunakan setiap saat dengan teknik klasifikasi data algoritma C5.0 sesuai kriteria yang diinginkan. Namun perangkat lunak yang ada umumnya terdiri dari sejumlah teknik dan belum dapat digunakan secara online. Sebagai salah satu algoritma klasifikasi yang popular dalam ilmu data mining, C5.0 dapat memberikan hasil yang lebih baik. Penelitian bertujuan untuk membangun perangkat lunak yang dapat melakukan klasifikasi data menggunakan algoritma C5.0 berbasis web. Perangkat lunak dapat digunakan oleh siapa saja, terutama para pengambil keputusan. Penelitian ini juga dilengkapi dengan pengujian perangkat lunak usability sebelum digunakan. Hasil pengujian memperlihatkan bahwa perangkat lunak yang dibangun dapat diterima dengan nilai usability 76,892% dan berada pada predikat Baik. Diharapkan melalui penelitian ini, dapat memberikan alternatif perangkat lunak yang mampu menyelesaikan masalah klasifikasi menggunakan algoritma C5.0.Kata kunci: perangkat lunak, klasifikasi, algoritma c5.0, usability AbstractSoftware is a tool that makes it easy for users to process data quickly and precisely. Decision makers need an alternative software that can be used at any time with the C5.0 algorithm data classification technique according to the desired criteria. However, the existing software generally consists of a number of techniques and cannot be used online. As one of the popular classification algorithms in data mining science, C5.0 can provide better results. This study aims to build software that can classify data using the web-based C5.0 algorithm. Software can be used by anyone, especially decision makers. This research is also complemented by testing Usability software before used. The test results showed that the software built can be accepted with a Usability value of 76.892% and is in the Good predicate. It is hoped that through this research, it can provide alternative software that is able to solve classification problems using the C5.0 algorithm.Keywords: software, classification, c5.0 algorithm, usability

scholarly journals Social Media Data using Various Classification Algorithms in Datamaning

2019 ◽  
Vol 8 (12S) ◽  
pp. 588-589
Keyword(s):  
Data Mining ◽  
Social Media ◽  
Training Data ◽  
Classification Algorithms ◽  
Data Set ◽  
Social Media Data ◽  
The Past ◽  
Classification Technique ◽  
Mathematical Techniques ◽  
Media Data

Data Mining is one of the most successful domains in research. It describes the past and speculates the future for analysis. There are several techniques used in data mining. Among them classification is one of the main data mining techniques based on machine learning. In classification technique data set is classified into predefined set of groups or classes. Mathematical techniques such as decision tree, linear regression, neural networks and statistics are used for classification methods. Classification is a problem to identify which set of categories the new observation belongs to using training data set. This paper analyses the data taken from social media and uses the classification algorithm for making a comparative study on social advertisement using python.

Research on Text Classification Technique

2013 ◽  
Vol 278-280 ◽  
pp. 2081-2084
Author(s):  
Shi Min Wang ◽  
Xian Zhe Cao
Keyword(s):  
Data Mining ◽  
Text Classification ◽  
The Other ◽  
Classification Algorithms ◽  
Classification Technique

At first the paper will introduce the basic conception and the generic progress of text classification, after that it will introduce three text classification algorithms in detail and finally it will verify NB, SVM and KNN by experiment with the data mining software-weka. The result of experiment shows that KNN is more efficient than the other two algorithms in recall and precision.

Sign in / Sign up

Export Citation Format

Share Document