A comparative analysis of classification algorithms in data mining for accuracy, speed and robustness

2012 ◽  
Vol 14 (2) ◽  
pp. 105-124 ◽  
Author(s):  
Neslihan Dogan ◽  
Zuhal Tanrikulu
Keyword(s):  
Data Mining ◽  
Comparative Analysis ◽  
Classification Algorithms ◽  
Accuracy Speed

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.

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.

scholarly journals A Comparative Analysis of Classification Algorithms on Diverse Datasets

2018 ◽  
Vol 8 (2) ◽  
pp. 2790-2795 ◽  
Author(s):  
M. Alghobiri
Keyword(s):  
Data Mining ◽  
Performance Evaluation ◽  
Comparative Analysis ◽  
Nearest Neighbor ◽  
Absolute Error ◽  
Classification Algorithms ◽  
Kappa Statistics ◽  
Data Sets ◽  
Evaluation Measures ◽  
F Measure

Data mining involves the computational process to find patterns from large data sets. Classification, one of the main domains of data mining, involves known structure generalizing to apply to a new dataset and predict its class. There are various classification algorithms being used to classify various data sets. They are based on different methods such as probability, decision tree, neural network, nearest neighbor, boolean and fuzzy logic, kernel-based etc. In this paper, we apply three diverse classification algorithms on ten datasets. The datasets have been selected based on their size and/or number and nature of attributes. Results have been discussed using some performance evaluation measures like precision, accuracy, F-measure, Kappa statistics, mean absolute error, relative absolute error, ROC Area etc. Comparative analysis has been carried out using the performance evaluation measures of accuracy, precision, and F-measure. We specify features and limitations of the classification algorithms for the diverse nature datasets.

scholarly journals Early Detection of Red Palm Weevil, Rhynchophorus ferrugineus (Olivier), Infestation Using Data Mining

Plants ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 95
Author(s):  
Heba Kurdi ◽  
Amal Al-Aldawsari ◽  
Isra Al-Turaiki ◽  
Abdulrahman S. Aldawood
Keyword(s):  
Data Mining ◽  
Plant Size ◽  
Support Vector ◽  
Classification Algorithms ◽  
Palm Tree ◽  
Rhynchophorus Ferrugineus ◽  
Red Palm Weevil ◽  
Palm Weevil ◽  
Using Data ◽  
F Measure

In the past 30 years, the red palm weevil (RPW), Rhynchophorus ferrugineus (Olivier), a pest that is highly destructive to all types of palms, has rapidly spread worldwide. However, detecting infestation with the RPW is highly challenging because symptoms are not visible until the death of the palm tree is inevitable. In addition, the use of automated RPW weevil identification tools to predict infestation is complicated by a lack of RPW datasets. In this study, we assessed the capability of 10 state-of-the-art data mining classification algorithms, Naive Bayes (NB), KSTAR, AdaBoost, bagging, PART, J48 Decision tree, multilayer perceptron (MLP), support vector machine (SVM), random forest, and logistic regression, to use plant-size and temperature measurements collected from individual trees to predict RPW infestation in its early stages before significant damage is caused to the tree. The performance of the classification algorithms was evaluated in terms of accuracy, precision, recall, and F-measure using a real RPW dataset. The experimental results showed that infestations with RPW can be predicted with an accuracy up to 93%, precision above 87%, recall equals 100%, and F-measure greater than 93% using data mining. Additionally, we found that temperature and circumference are the most important features for predicting RPW infestation. However, we strongly call for collecting and aggregating more RPW datasets to run more experiments to validate these results and provide more conclusive findings.

Sign in / Sign up

Export Citation Format

Share Document