Data Mining Classification Algorithms Research Articles

Impact Analysis of Filter and Wrapper-Based Feature Selection Techniques for Webpages Phishing Attacks Identification

Phishing, which involves fraudulently gaining access to sensitive assets of unsuspecting individuals through deceptive and malicious emails, is a major global threat to internet users. The proliferation of phishing sites and their operations is occurring at an alarming rate, raising significant concerns about how to forestall them. Numerous research efforts are underway to detect phishing attempts before they can compromise important information and cause damage. Compared to conventional methods, machine learning has proven highly effective at detecting phishing attacks by analyzing different features. This study analyzed the behaviors of seven classification data mining algorithms on optimal subset features selection using Wrapper (Boruta) and Filter-based (Mutual-Information). Real-life phishing webpage datasets were used for the analysis. Ensemble classifiers such as Voting, Gradient Boosting, and Random Forest were used in the experiments. Two experiments were conducted. In the first experiment, K-Nearest Neighbor (K-NN) yielded the highest accuracy among single classifiers, with a score of 94.1%, while Random Forest (RF) ensemble achieved 96.7%. In the second experiment, using another baseline feature set, RF performed excellently under the Boruta method with an accuracy of 97.25%, while K-NN retained the highest accuracy of 95.20% among single classifiers. This study provides empirical evidence that feature selection techniques have a great impact on the performance of ML models, for both single and ensemble classifiers, in the detection of phishing attacks.

Exploring the Effectiveness of Data Mining Classification Algorithms in Credit Card Fraud Detection

Credit card fraud is a widespread problem that impacts both individuals and companies. Data mining provides a powerful solution to not only detect but also prevent this type of fraud. This research explores this approach by utilizing data mining classification techniques to determine the potential for fraudulent credit card transactions. Data from various sources is collected and processed to extract relevant features. This research will compare 8 classification algorithms, namely Naive Bayes, Decision Trees, Artificial Neural Network, SVM, Linear Regression, Logistic Regression, LDA and Random Forest, in classifying transactions as legitimate or fake. These findings suggest that the combined use of these data mining classification methods offers a powerful tool in combating credit card fraud. To combat the problem of credit card fraud and maintain financial security for both individuals and institutions, this researcher explores the power of data mining. By using potential classification techniques, this research aims to predict fraudulent transactions on credit cards.

Detection of ChatGPT fake science with the xFakeSci learning algorithm

Generative AI tools exemplified by ChatGPT are becoming a new reality. This study is motivated by the premise that “AI generated content may exhibit a distinctive behavior that can be separated from scientific articles”. In this study, we show how articles can be generated using means of prompt engineering for various diseases and conditions. We then show how we tested this premise in two phases and prove its validity. Subsequently, we introduce xFakeSci, a novel learning algorithm, that is capable of distinguishing ChatGPT-generated articles from publications produced by scientists. The algorithm is trained using network models driven from both sources. To mitigate overfitting issues, we incorporated a calibration step that is built upon data-driven heuristics, including proximity and ratios. Specifically, from a total of a 3952 fake articles for three different medical conditions, the algorithm was trained using only 100 articles, but calibrated using folds of 100 articles. As for the classification step, it was performed using 300 articles per condition. The actual label steps took place against an equal mix of 50 generated articles and 50 authentic PubMed abstracts. The testing also spanned publication periods from 2010 to 2024 and encompassed research on three distinct diseases: cancer, depression, and Alzheimer’s. Further, we evaluated the accuracy of the xFakeSci algorithm against some of the classical data mining algorithms (e.g., Support Vector Machines, Regression, and Naive Bayes). The xFakeSci algorithm achieved F1 scores ranging from 80 to 94%, outperforming common data mining algorithms, which scored F1 values between 38 and 52%. We attribute the noticeable difference to the introduction of calibration and a proximity distance heuristic, which underscores this promising performance. Indeed, the prediction of fake science generated by ChatGPT presents a considerable challenge. Nonetheless, the introduction of the xFakeSci algorithm is a significant step on the way to combating fake science.

Technical–tactical differences between female and male elite football: A data mining approach through neural network analysis, binary logistic regression, and decision tree techniques

The technical−tactical performance of women’s football has improved markedly in recent years. Despite this improvement, there are still differences between men’s football and women’s football. The objectives of this study were to know the technical and tactical key performance indicators (KPIs) that differentiate elite men’s and women’s football teams as well as to determine which statistical techniques demonstrate superior classification ability and interpretability in football terms. For this purpose, 768 matches corresponding to the latest editions of the UEFA Champions League, UEFA Euro and FIFA World Cup for men and women were analyzed. First, the differences at the bivariate level were analyzed using student’s t-test for independent sample ( p < 0.05) for the male and female teams. Secondly, three data mining classification algorithms were applied: (i) Artificial Neural Network (ANN), (ii) Binary Logistic Regression, and (iii) Decision Tree. Significant differences were found between men’s football and women’s football in variables related to technical elements such as lost balls (ES = 1.19), ball recoveries (ES = 1.00), and accurate passes (ES = 0.97), as well as regulatory aspects like fouls (ES = 0.59), successful tackles (ES = 0.46), and yellow cards (0.45). On the other hand, the classification models presented excellent or good predictive capability [Range AUC 0.774−0.982], with very small differences between the ANN’s and logistic regression models. This result justifies the use of simpler models as the linear regression model to understand the differences between men’s and women’s football. Moreover, the observed differences may offer insights for future efforts aimed at enhancing the performance of women’s football.

Prediction of student exam performance using data mining classification algorithms

AbstractStudent outcomes are of great importance in higher education institutions. Accreditation bodies focus on them as an indicator to measure the performance and effectiveness of the institution. Forecasting students’ academic performance is crucial for every educational establishment seeking to enhance performance and perseverance of its students and reduce the failure rate in the future. The main goal of this study is to predict the performance of undergraduate first-level students in the Computer Department during the years 2016 to 2021 to enhance their performance in future by discovering the best algorithm use to analyze the educational data to identify the students’ academic performance. The secondary data was collected by reviewing the Student Affairs Department at the Faculty of Specific Education at Damietta University, in addition to the Statistics Department at the university. The dataset contained 830 instances after excluding 139 instances of missing values, irrelevant rows, and outliers. The dataset was divided into train (577 instances (70%)), test (253 instances (30%)) and involved six features such year, midterm, practical exam, writing exam, final total degree, and grade. This paper use five machine learning (ML) algorithms which was selected according to the literature review and high accuracy in predicting educational data mining: For the purpose of comparison, a number of different machine learning algorithms, such as Random Forest, Decision Tree, Naive Bayes, Neural Network, and K-Nearest Neighbours, were utilized and evaluated with evaluation metrics such as confusion matrix, accuracy, precision, recall, and F-measure. The Random Forest and Decision Tree classifiers emerged as the top-performing algorithms, accurately categorizing 250 instances when predicting students' performance in the statistics course. This was determined based on the findings of the study. Out of a total of 253 instances that were included in the testing set, they only made three incorrect classifications.

Predicting Diabetes Disease Using Data Mining Classification Algorithms and Comparison of Algorithm Performances

Data is always produced everywhere in the universe. In our globalizing world, where the internet is rapidly spreading, countless data set examples can be given. We produce data when we shop at a bookstore, make a transfer from our bank account, travel with an airline, or get tested in a hospital. Test results of hospital patients, production reports of a manufacturing factory, and exam results of students are examples of data sets. This data pile grows daily, and the data has no meaning. Data gains meaning by being processed by various tools and transformed into information. Today, information has become the most incredible power. In this study, a prediction study of diabetic patients was made with ten different algorithms from classification methods, one of the data mining methods. At the end of the prediction study, the algorithms' performances were compared. The unique aspect of this study is that the performance of the algorithms is compared by making predictions with ten different classification methods instead of just one or a few classification methods.

Comparison of Data Mining Classification Algorithms for Stroke Disease Prediction Using the SMOTE Upsampling Method

Stroke is a circulation disorder in the brain that can cause symptoms and signs related to the affected part of the brain and is the leading cause of death and disability in Indonesia. Everyone is at risk of experiencing a stroke, and it is important to recognize and manage risk factors. Data Mining techniques can help in the extraction and prediction of information, as well as finding hidden patterns in stroke medical data. The dataset used in this research comes from Kaggle and is imbalanced, so the SMOTE Upsampling technique is used to address this imbalance issue. The results of the study conclude that the use of SMOTE technique in the C4.5, NB, and KNN algorithms can increase precision, recall, and AUC. The C4.5 algorithm and SMOTE technique as the best performing algorithm were selected for testing new data, and the results show that the model created can predict stroke risk more accurately than the C4.5 model without SMOTE. However, it should be noted that based on the author's interview with one of the medical practitioners, the model cannot be directly used in medical practice because the observations in the medical field to determine factors related to stroke are highly complex. Thus, a new understanding revealed that predicting stroke in a practical setting is highly complex. While data mining can be used as a predictive tool in the initial stage for predictions in the general population, it is strongly recommended to undergo direct examination by doctors in a hospital to obtain more accurate and comprehensive medical evaluations.

An overview of big data mining and data privacy protection technologies

With the advent of the era of big data, data mining techniques have significantly improved their ability to extract valuable information from data. However, privacy dangers are growing. Consequently, securing the protection of personal privacy during the mining of massive amounts of data has become a significant challenge. This paper examines the relationship between data mining techniques and privacy protection measures through a review of the pertinent literature. It provides a concise analysis of the benefits and drawbacks of commonly utilized classification algorithms in data mining. In addition, it examines the interplay between data mining techniques and privacy protection and summarizes important privacy protection techniques. In addition, this paper provides a summary of the most important privacy protection methods. These techniques include data anonymization, association rule concealing, data perturbation, etc. By comprehending these privacy protection techniques, appropriate privacy safeguards can be selected to ensure the privacy and security of the data when conducting data mining.

Educational data mining: Methods and applications

Educational data mining is a rapidly growing field that applies various statistical and data mining techniques to analyze educational data. This paper provides a general review of the literature on educational data mining, focusing on the methods and applications. Methods used in education data mining include classification and clustering. A classification algorithm is a supervised learning technique that seeks to categorize a given set of data objects into specified categories, build a classification model using the input data that already exists, and then apply the model to categorize new data items. The Naive Bayes, Decision Tree, Neural Network, and K-Nearest Neighbors have commonly employed classification algorithms in educational data mining. Clustering is unsupervised learning, whose objective is to divide a collection of data objects into various groups, where samples within a cluster exhibit a high level of resemblance and those between clusters are dissimilar. In educational data mining, the K-means Clustering Algorithm, Grid-Based Clustering, and Hierarchical Clustering are common clustering techniques. Those data mining algorithms are used in education such as student behavior prediction, student bad behavior detection, and student grouping. Overall, this research demonstrates that education data mining has a significant potential to improve educational programmers and student results. To solve the legal and privacy issues associated with the collecting and use of educational data, however, more research and solutions are required.

Data Cleaning in Medical Procurement Database: Performance Comparison of Data Mining Classification Algorithms for Tackling Missing Value

Data Cleaning in Medical Procurement Database: Performance Comparison of Data Mining Classification Algorithms for Tackling Missing Value

PENERAPAN METODE DECISION TREE UNTUK PRAKIRAAN CUACA KOTA BEKASI

To predict the weather requires a lot of weather data variables, many influencing factors such as the large amount of data. Because this makes prediction accuracy and speed less accurate. So with that made a way to make predictive model research using several data mining techniques. The data to be used in this study were obtained from timeanddate.com, timeanddate.com is a site that provides data and information about daily weather conditions. The data used ranges from December 2021 to August 2022. The research aims to obtain weather classification patterns using the data mining classification algorithm, namely the C4.5 algorithm. The results of testing the C4.5 algorithm using the php website and program get an accuracy of 82%.

Prediksi Keberhasilan Pemasaran Layanan Jasa Perbankan Mengunnakan Algoritma Logistic Regreesion

Determining public interest in marketing banking services using data mining techniques. Prospect segmentation is one of the processes used in the marketing strategy of the banking industry. Data mining support plays an important role in classifying potential bank customers and evaluating the success of marketing their services. This is important to support the conclusion about the success rate of telemarketers in carrying out bank marketing tasks. a product whose way of working requires information about potential customers. This is a classification technique that is often used to classify prospects using logistic regression according to research maps supporting prospect data mining. Defining an accurate data mining classification algorithm to predict telemarketing success based on a 2010 experiment. In marketing banking service products, the results of the evaluation process of this algorithm are determined by cross-validation, Confusion Matrix, ROC curve and T-test. The logistic regression algorithm is more accurate with an accuracy of 92.32% and an AUC value of 0.962, so the algorithm used is included in the good classification group.

Modeling and Predicting the Changes in Hearing Loss of Workers with the Use of a Neural Network Data Mining Algorithm: A Field Study

The aim of the study study was to model, with the use of a neural network algorithm, the significance of a variety of factors influencing the development of hearing loss among industry workers. The workers were categorized into three groups, according to the A-weighted equivalent sound pressure level of noise exposure: Group 1 (LAeq 85 dB). The results obtained for Group 1 indicate that the hearing thresholds at the frequencies of 8 kHz and 1 kHz had the maximum effect on the development of hearing loss. In Group 2, the factors with maximum weight were the hearing threshold at 4 kHz and the worker’s age. In Group 3, maximum weight was found for the factors of hearing threshold at a frequency of 4 kHz and duration of work experience. The article also reports the results of hearing loss modeling on combined data from the three groups. The study shows that neural data mining classification algorithms can be an effective tool for the identification of hearing hazards and greatly help in designing and conducting hearing conservation programs in the industry.

RFID-based logistics big data asset evaluation and data mining research

Abstract With the rapid rise of e-commerce platforms, in view of the sharp increase in the amount of data in the logistics system, the timely update and processing of relevant logistics information data have assumed a particular relevance. In this paper, we fully draw on the excellent performance of radio frequency identification (RFID) technology and data mining technology, begin by using RFID technology to authenticate logistics commodities, move on to extracting relevant feature information and finally carry out a detailed comparison between k-nearest neighbour algorithm, support vector machine (SVM) algorithm, logistic regression (LR) algorithm and improved LR algorithm. The algorithm provides a solution method for asset information collection channel and data mining classification algorithm. It meets the needs of different customers, and provides a variety of working modes, which helps to improve the time and operation efficiency of data processing algorithms. The results show that the SVM algorithm only achieves 93.8% accuracy when iterating 50 times for the classification results of the classification samples containing the objective functions of x 1 and x 2. The improved LR algorithm stochastic gradient descent algorithm has a classification accuracy of 94.6% after 50 iterations. The RFID-based logistics big data asset evaluation and data mining research identification algorithm has obvious advantages, and the accuracy rate reaches 97.3%.

Big Data Stream Mining Using Integrated Framework with Classification and Clustering Methods

Abstract: The causes of numerous sorts of big data and data stream problems include the quick development of industry firms, the vast amount of data generated by these innovations, and the exponential growth of industrial company websites. There are numerous stream data mining algorithms for classification and grouping, each with its own unique set of attributes and important features. Ensemble classifiers aid in enhancing the greatest prediction performance results from these cutting-edge techniques. Ensemble approaches teach multiple types of classifiers and clusters rather than a single classifier. Their machine learning prediction findings are merged to form a voting schedule. This research offered a framework for stream data mining based on miss categorization stream data, utilizing the advantages of assembly technology. Real-world data streams are used in experiments. The experimental results are compared to modern popular ensemble techniques such as Boosting and Bagging. The test results show an increase in accuracy rate and decrease in classification time.

Performance Comparison of Data Mining Classification Algorithms on Student Academic Achievement Prediction

Performance Comparison of Data Mining Classification Algorithms on Student Academic Achievement Prediction

Student performance prediction using datamining classification algorithms: Evaluating generalizability of models from geographical aspect

Student performance prediction using datamining classification algorithms: Evaluating generalizability of models from geographical aspect

Comparative Performance Evaluation Results of Classification Algorithm in Data Mining to Identify Types of Glass Based on Refractive Index and It’s Elements

Data science is becoming familiar to the public and companies in the era of Industrial Revolution 4.0. One part of data science is data mining. Data mining is the process of collecting information to see patterns from very large datasets and data discovery which is processed in such a way as to become knowledge based on the interpretation of the information obtained. The purpose of this paper is to compare the performance evaluation results of several classification algorithms in data mining (such as DT C-45, Neural Network, KNN, LDA, Naïve Bayes, SVM, and Rule Induction) for identifying types of glass based on the refractive index and its elements. The data set used is a glass identification dataset taken from the UCI Machine Learning Repository. The results of the evaluation can be seen from the criteria like of Accuracy and Kappa using 10 fold cross validation. As a result, the K-Nearest Neighbors (KNN) algorithm has the best Accuracy and Kappa values, namely 72.90% for Accuracy and 0.632 for Kappa values. To determine the significance of the accuracy value, the T-Test method is used.

Multiple disease prediction using Machine learning algorithms

Data mining for healthcare is an interdisciplinary field of study that originated in database statistics and is useful in examining the effectiveness of medical therapies. Machine learning and data visualization Diabetes-related heart disease is a kind of heart disease that affects diabetics. Diabetes is a chronic condition that occurs when the pancreas fails to produce enough insulin or when the body fails to properly use the insulin that is produced. Heart disease, often known as cardiovascular disease, refers to a set of conditions that affect the heart or blood vessels. Despite the fact that various data mining classification algorithms exist for predicting heart disease, there is inadequate data for predicting heart disease in a diabetic individual. Because the decision tree model consistently beat the naive Bayes and support vector machine models, we fine-tuned it for best performance in forecasting the likelihood of heart disease in diabetes individuals.

Identification of Significant Features and Data Mining Techniques in Predicting Heart Stroke

The health-care industry generates a large amount of data, which is processed using certain methodologies. One technique that is frequently utilized is data mining. Heart disease is the leading cause of death on a global scale. This system foresees the risk of heart disease developing. The results of this system give you a % likelihood of getting heart disease. Medical parameters are utilized to categories the datasets. This system uses a data mining classification algorithm to analyze such parameters. The datasets are processed in Python programming using two main Machine Learning Algorithms: Decision Tree Approach and Naïve Bayes Algorithm, with the latter showing to be the best algorithm in terms of heart disease accuracy.