Decision Tree C4 Research Articles

Analysis of Data Mining Applications for Determining Credit Eligibility Using Classification Algorithms C4.5, Naïve Bayes, K-NN, and Random Forest

This study aims to enhance the credit evaluation process within Credit Union (CU) Karya Bersama Lestari (KABARI). The study leveraged four distinct algorithms, namely Decision Tree C4.5, Naive Bayes, K-Nearest Neighbors (K-NN), and Random Forest, to predict the suitability of extending loans to potential borrowers. Rapid Miner was employed as a tool to maximize accuracy by analyzing the Confusion matrix. Testing was conducted on a dataset consisting of 459 member loan submissions. The results of the analysis revealed that the K-Nearest Neighbors (K-NN) algorithm achieved the highest accuracy among the evaluated algorithms. Specifically, the Decision Tree algorithm demonstrated an accuracy rate of 95.65%, along with a precision and recall of 94.12%. The Naive Bayes algorithm achieved an accuracy rate of 95.65%, supported by precision and recall values of 100% and 88.24%, respectively. The K-Nearest Neighbors algorithm displayed the highest accuracy rate of 97.83%, accompanied by 100% precision and 94.12% recall. Meanwhile, the Random Forest algorithm exhibited an accuracy rate of 93.48%, complemented by precision and recall values of 100% and 82.35%, respectively. The study's conclusions bear relevance for refining loan approval processes and fostering improved lending practices within financial institutions like CU KABARI.

Prediction Model for Unfavorable Outcome in Spontaneous Intracerebral Hemorrhage Based on Machine Learning.

The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

Classification of Myopathy and Normal Electromyogram (EMG) Data with a New Deep Learning Architecture

Electromyograms (EMG) are recorded movements of nerves and muscles that help diagnose muscles and nerve-related disorders. It is frequently used in the diagnosis of neuromuscular diseases such as myopathy, which causes many changes in EMG signal properties. The most useful auxiliary test in the diagnosis of myopathy is EMG. Therefore, it has become imperative to identify computer-assisted anomalies with full accuracy and to develop an efficient classifier. In this study, a new machine learning method with a deep learning architecture that can score normal and myopathy EMG from the EMGLAB database is proposed. Using the discrete wavelet transform Coiflets 5 (Coif 5) wavelet, the EMG signals are decomposed into subbands and various statistical features are obtained from the wavelet coefficients. The success rates of the decision tree C4.5 algorithm, which is one of the traditional learning architectures, and the Long Short-term Memory (LSTM) algorithm, which is one of the deep learning architectures, were compared. Unlike the studies in the literature, with the LSTM algorithm, a 100% success rate was achieved with the proposed model. In addition, a real-time approach is presented by analyzing the test data classification time of the model.

Decision Tree C4.5 Performance Improvement using Synthetic Minority Oversampling Technique (SMOTE) and K-Nearest Neighbor for Debtor Eligibility Evaluation

Nowadays, information technology especially machine learning has been used to evaluate the feasibility of debtors. One of the challenges in this classification model is the occurrence of imbalanced datasets, especially in the German Credit Dataset. Another challenge is developing an optimal model for evaluating debtor eligibility. Based on these challenges, this study aims to develop an optimal model for evaluating debtor eligibility on the German Credit Dataset, using the decision trees, k-Nearest Neighbor (k-NN) and Synthetic Minority Oversampling Technique (SMOTE). SMOTE and k-NN is used to overcome challenges regarding imbalanced datasets. While the decision tree are applied to produce a debtor classification model. In general, the steps taken are preparing datasets, pre-processing data, dividing datasets, oversampling with SMOTE, and classification models using decision trees, and testing. Model performance evaluation is represented by accuracy values obtained from the confusion matrix and area under curve (AUC) values generated by the Receiver Operating Characteristic (ROC). Based on the tests that have been carried out, the best accuracy value in the test is obtained at 73.00% and the AUC value is 0.708, in parameters k = 3 and Max-Depth = 25. Based on the analysis produced, the proposed model can improve performance compared to if the dataset is not applied SMOTE.

Comparative study on risk prediction model of type 2 diabetes based on machine learning theory: a cross-sectional study

ObjectivesTo compare the prediction effects of six models based on machine learning theories, which can provide a methodological reference for predicting the risk of type 2 diabetes mellitus (T2DM).Setting and...

Web Design for Stroke Early Detection Using Decision Tree C5.0

Stroke is a disease that needs serious attention because it can cause disability and even death. According to World Health Organization (WHO) in 2022, stroke is the second leading cause of death and a leading cause of disability in the world. In Indonesia, stroke is the first leading of non-communicable disease proportion according to Riset Kesehatan Dasar in 2018. This study aims to design a web application that can help stroke early detection in a person so that people are more concerned about preventing a stroke. This study used Decision Tree (DT) C5.0 method by utilizing 10 stroke risk factors to analyze the risk of stroke in a person. Decision Tree method can break down complex datasets into several simple rules illustrated by a tree, hence the name Decision Tree. The DT C5.0 is one kind of Decision Tree method that has fast performance in classifying data compared to other methods. Therefore, this study observes how DT C5.0 works in detecting stroke risk. The output of this web application is a statement whether a person has a stroke risk or not. The secondary dataset used for model development totaled 5,109 data consisting of 249 stroke patient data and 4,860 non-stroke patient data. In this study, data balancing and cross validation were carried out so that the performance of the training results model was obtained, namely accuracy 83.54%, precision 78.67%, sensitivity 92.20%, and specificity 74.87%. Furthermore, the performance of the test results model is accuracy 84.42%, precision 79.26%, sensitivity 93.10%, and specificity 75.80%.

An Ensemble Voting Approach for Dropout Student Classification Using Decision Tree C4.5, K-Nearest Neighbor and Backpropagation

An Ensemble Voting Approach for Dropout Student Classification Using Decision Tree C4.5, K-Nearest Neighbor and Backpropagation

Sentiment Analysis of Shopee Food Application User Satisfaction Using the C4.5 Decision Tree Method

Sentiment analysis on public opinion regarding the shopee food application is an interesting topic in the context of evaluating service quality in the shopee food application. In this digital era, user opinion has a very important role in shaping public perception of the application. Therefore, sentiment analysis is needed to understand user opinion about the shopee food application. This study uses Decision Tree C4.5 to analyze public sentiment on the use of the Shopee Food application on Twitter users. However, beforehand it is necessary to overcome the problem of data imbalance which is common in datasets, where the number of positive, negative, and neutral sentiments is not balanced. To overcome this problem, three different techniques are used, namely SMOTE, undersampling, and a combination of oversampling and undersampling. The results of this study indicate that the SMOTE technique provides better results in overcoming data imbalances and increasing prediction accuracy. With an accuracy of 0.88. the SMOTE technique can provide more accurate sentiment predictions than the undersampling technique and the combination of oversampling and undersampling. This is because SMOTE can synthetically expand the number of minority samples, thereby preventing the loss of information and maintaining variation in the dataset. In conclusion, sentiment analysis on the Shopee Food application on Google Play using the Decision Tree C4.5 algorithm and the SMOTE technique can overcome data imbalances with a prediction accuracy of 0.88. This technique is more efficient than the undersampling technique and the combination of oversampling and undersampling. These results can provide developers with valuable insights to improve app quality and user satisfaction.

Hybrid Decision Tree Method and C4.5 Algorithm for a Recommendation System in Determining Recipients of Direct Cash Assistance (BLT)

Development of a recommendation system to determine recipients of Direct Cash Assistance (BLT) using the C4.5 algorithm hybrid method and decision tree. In the current era of digitalization, the BLT program is a solution for the Indonesian government to help people affected by the COVID-19 pandemic. In this study, we propose a recommendation system that combines the C4.5 algorithm and a decision tree to increase accuracy and efficiency in determining BLT beneficiaries. Primary data was obtained through interviews and observations, while secondary data was obtained from the village administration, written reports, journals, theses and previous research. The results showed that the C4.5 algorithm and decision tree hybrid method gave good performance in determining BLT recipients. The C4.5 algorithm is used to calculate the accuracy of the training data and testing data with a ratio of 80% : 20%, while the decision tree is used to create a decision tree that classifies prospective BLT recipients. This research fills in the previous research gap regarding the recommendation system for determining BLT beneficiaries. The results of this study are expected to provide useful information for the government in making decisions regarding the BLT program, especially at the village or sub-district level. With an accurate and efficient recommendation system, financial assistance can be provided to those who really need it, helping to meet the basic daily needs of affected communities.

Classification of Stunting in Children Using the C4.5 Algorithm

Stunting is a disease caused by malnutrition in children, which results in slow growth. Generally, stunting is characterized by a lack of weight and height in young children. This study aims to classify stunting in children aged 0-60 months using the Decision Tree C4.5 method based on z-score calculations with a sample size of 224 records, consisting of 4 attributes and 1 label, namely Gender, Age, Weight, Height, and Nutritional Status. The results of the study obtained a C4.5 decision tree where the Age variable influenced the classification of stunting with the highest Gain Ratio of 0.185016337. Meanwhile, the evaluation of the model using the Confusion matrix resulted in the highest accuracy of 61.82% and AUC of 0.584.

Machine learning-based processing of unbalanced data sets for computer algorithms

Abstract The rapid development of technology allows people to obtain a large amount of data, which contains important information and various noises. How to obtain useful knowledge from data is the most important thing at this stage of machine learning (ML). The problem of unbalanced classification is currently an important topic in the field of data mining and ML. At present, this problem has attracted more and more attention and is a relatively new challenge for academia and industry. The problem of unbalanced classification involves classifying data when there is insufficient data or severe category distribution deviations. Due to the inherent complexity of unbalanced data sets, more new algorithms and tools are needed to effectively convert a large amount of raw data into useful information and knowledge. Unbalanced data set is a special case of classification problem, in which the distribution between classes is uneven, and it is difficult to classify data accurately. This article mainly introduces the research on the processing method of computer algorithms based on the processing method of unbalanced data sets based on ML, aiming to provide some ideas and directions for the processing of computer algorithms based on unbalanced data sets based on ML. This article proposes a research strategy for processing unbalanced data sets based on ML, including data preprocessing, decision tree data classification algorithm, and C4.5 algorithm, which are used to conduct research experiments on processing methods for unbalanced data sets based on ML. The experimental results in this article show that the accuracy rate of the decision tree C4.5 algorithm based on ML is 94.80%, which can be better used for processing unbalanced data sets based on ML.

Application Of The C4.5 Algorithm to Determine Security Guard Work Schedules

All agencies, companies, and public spaces must employ security guards to maintain security. The problem with the security guard's schedule is that there is an imbalance in disciplinary issues, poor performance because there is no seniority that is emulated so that the guard is not optimal which results in the problem of losing employee items, working time is not according to the rules and there is a vacancy in personnel due to personnel not coming to work, suing With the existence of a policy in the placement and distribution of the right employee work schedule, it is hoped that it can synergize all elements in the institution so that the quantity and quality of the security guard's work can increase and be completed on time. One of the techniques in data mining is classification. By applying classification techniques to security guard data and work schedules, the Decision Tree method and C4.5 algorithm are developed. The results of data processing form the root node of the gender tree as the root, that those who get schedule A are men while those who get schedule B with high school and junior level education are women, besides that they get schedule A. The accuracy of all classifications of the correct number is 61, 53%.

Improved Accuracy In Data Mining Decision Tree Classification Using Adaptive Boosting (Adaboost)

The Decision Tree algorithm is a data mining method algorithm that is often applied as a solution to a problem for a classification. The Decision Tree C5.0 algorithm has several weaknesses, including: the C5.0 algorithm and several other decision tree methods are often biased towards modeling whose features have many levels, some problems for the model can occur such as over-fit or under-fit challenges, big changes to decision logic can result in small changes to data training, C5.0 can experience modeling inconvenience, data imbalance causes low accuracy in C5.0 algorithm. The boosting algorithm is an iterative algorithm that gives different weights to the distribution of training data in each iteration. Each iteration of boosting adds weight to examples of misclassification and decreases weight to examples of correct classification, thereby effectively changing the distribution of the training data. One example of a boosting algorithm is adaboost. The purpose of this research is to improve the performance of the Decision Tree C5.0 classification method using adaptive boosting (adaboost) to predict hepatitis disease using the Confusion matrix. Tests that have been carried out with the Confusion Matrix use the Hepatitis dataset in the Decision Tree C5.0 classification which has an accuracy rate of 80.58% with a classification error rate of 19.15%. Whereas in the Decision Tree C5.0 classification Adaboost has a higher accuracy rate of 82.98%, a classification error rate of 17.02%. This difference is caused by the adaboost algorithm, because the adaboost algorithm is able to change a weak classifier into a strong classifier by increasing the weight of the observations, and adaboost is also able to reduce the classifier error rate.

DECISION TREE SIMPLIFICATION THROUGH FEATURE SELECTION APPROACH IN SELECTING FISH FEED SELLERS

Feed is a crucial variable because it can determine the success of fish farming. Breeders can use two types of artificial feed, namely alternative feed and pellets. Many cultivators need pellets as the main consumption for the fish they are cultivating because the pellets contain a composition that has been adjusted to their needs based on the type and age of the fish. However, currently, cultivators are facing a problem, namely the high price of fish pellets on the market. Therefore, an analysis of the classification of the selection of fish feed sellers is needed that is adjusted to several criteria like the number of types of feed, price, order, delivery, and availability of discounts. This study conducted a classification analysis of simplification of characteristics in selecting fish feed sellers in Kendal Regency that would then be compared with a model without feature selection by utilizing the Decision Tree C4.5 method. The results of this study are the decision tree with the best performance where C4.5 with the application of the selected feature has an accuracy value of 92%, while C4.5 without the selection feature has an accuracy of 86.8%. The results of this study indicate that the C4.5 method with the application of selection features is better than C4.5 without selection features so that it can be applied to the selection of freshwater fish feed sellers in Kendal Regency.

Analisis Pengaruh Komposisi Data Training dan Data Testing pada Penggunaan PCA dan Algoritma Decision Tree untuk Klasifikasi Penderita Penyakit Liver

Liver disease is one of the diseases that is difficult to detect and becomes the largest contributor to deaths because it is considered a silent killer without symptoms. Liver disease can be detected based on abnormalities in the number of contents in the human body. The Indian Liver Patient Dataset (ILPD) dataset has many variables related to content in the body of liver patient data which are used as parameters in the classification of liver disease patients. Previous studies have shown that only two variables influence the ILPD dataset. The purpose of this study is to examine the use of the Principal Component Analysis (PCA) method to determine the optimal number of features in the context of classification of liver disease and examine the percentage distribution of data training and data testing which produces the best accuracy. The ILPD dataset was obtained from the UCI Machine Learning website with a total of 583 rows of data and 11 features. The percentage of training data and testing data used is 50%:50%, 60%:40%, 70%:30%, 73%:27%, 75%:25%, 80%:20%, 83%:17%, 85%:15% and 90%:10%. The use of different training and testing data percentages serves to find the best accuracy. The PCA result feature is used as input for the Decision Tree C4.5 classification algorithm. The experimental results show that using the training and testing data distribution percentage of 90%:10% and after the application of PCA produces the highest accuracy, namely 78.40% which is obtained for the number of PCA components n = 8.

Comparison of C4.5 and Naive Bayes Algorithm Methods in Prediction of Student Graduation on Time (Case Study: Information Systems Study Program)

In tertiary institutions, students become one of the important parameters in the evaluation of study program organizers. Prediction of student graduation is a special concern to know, early identification for students is needed as an important action. Information processing to predict student graduation is by implementing data mining. The implementation of data mining can be applied if a university, especially a study program, does not yet have an early classification in achieving student graduation on time. The ITTP Information System study program is one of the study programs that does not have an early identification of student graduation on time. Determination of graduation for SI ITTP Study Program students includes GPA, TOEFL scores, and total credits. The purpose of this research is to find out which attributes have the most influence in predicting graduation of ITTP IS Study Program students. The method used in this prediction is by using the classification of the C4.5 Algorithm and Naïve Bayes. The classification is used to determine which attributes have an effect on predicting student graduation on time and to compare the two classification methods. The results obtained are the training set size 70% which has the best accuracy when compared to other training set sizes. Comparing the accuracy between the two methods, it is known that the C4.5 algorithm has good accuracy when training set size is 70% and Naïve Bayes has higher accuracy when training set size is 75%. Decision tree C4.5 interprets that the most influential attribute is the GPA as the root of the decision tree to predict student graduation on time. The research is expected to be used as a reference for the ITTP IS Study Program in formulating student graduation policies on time and as a reference for further researchers in predicting in the same field.

Reduced Peripheral Blood Mitochondrial DNA Copy Number as Identification Biomarker of Suspected Arsenic-Induced Liver Damage.

Arsenic (As) can cause liver damage and liver cancer and is capable of seriously affecting human health. Therefore, it is important to identify biomarkers of arsenic-induced liver damage. Mitochondria are key targets of hepatotoxicity caused by arsenic. The mitochondrial DNA copy number (mtDNAcn) is the number of mitochondrial DNA (mtDNA) copies in the genome. mtDNA is vulnerable to exogenous chemical attacks, thus causing mtDNAcn to change after exposure to environmental pollutants. Therefore, mtDNAcn can serve as a potential marker to identify and assess the risk of diseases caused by exposure to environmental pollutants. In this study, we selected 272 arsenicosis patients (155 cases without liver damage and 117 cases with liver damage) and 218 participants not exposed to arsenic (155 cases without liver damage and 63 cases with liver damage) as subjects to investigate the correlation between peripheral blood mtDNAcn and arsenic-induced liver damage, as well as the ability of peripheral blood mtDNAcn to identify and assess the risk of arsenic-induced liver damage. Peripheral blood mtDNAcn in patients with arsenic-induced liver damage is significantly decreased and negatively correlated with serum ALT, AST, and GGT levels. The decrease of peripheral blood mtDNAcn was associated with an increased risk of arsenic-induced liver damage. The receiver operating characteristic (ROC) curve analysis indicated that peripheral blood mtDNAcn could specifically identify patients with liver damage in the arsenicosis group. The decision tree C5.0 model was established to identify arsenicosis in all patients with liver damage. Peripheral blood mtDNAcn was included in the model and played the most important role in the identification of arsenic-induced liver damage. This study provided a basis for the identification and evaluation of arsenic-induced liver damage by peripheral blood mtDNAcn, indicating that peripheral blood mtDNAcn is expected to be a potential biomarker of arsenic-induced liver damage, and provides clues for exploring the mechanism of arsenic-induced liver damage from mitochondria damage.

Financial Distress Prediction: A Hybrid Tracking Model Approach

The purpose of this study was to build a highly accurate corporate financial distress tracking and prediction model based on hybrid machine learning technology. The research data were from Taiwan Economic Journal, and the research subjects were enterprises with financial distress risk announced in September 2022. In consideration of enterprise features, this study excluded the finance and insurance industries. The research period was three years (2019, 2020, and 2021) before the distress announcement. This study matched enterprises with financial distress and enterprises without financial distress (normal enterprises) at a ratio of 1:1 for each year. The sample size for each year included 374 enterprises with financial distress and 374 enterprises without financial distress. This study applied several machine learning technologies. At first, important variables were screened by applying artificial neural networks (ANNs). Next, prediction models were built based on decision tree C5.0 and random forest (RF) and were compared. According to the empirical result, the ANN-RF model provided a higher accuracy.

Prediction model of teacher candidate student graduation status: Decision Tree C4.5, Naive Bayes, and k-NN

This study aims to determine the prediction model of the graduation status of prospective teacher students at IAIN Bone in terms of attributes, accuracy levels, and differences in the level of accuracy produced in the attributes of decision tree C4.5, Naïve Bayes, and k-NN data mining algorithms. This research uses a quantitative approach by adopting the Data Mining method. This research was conducted at IAIN Bone. The data collection process in this study used documentation techniques in the form of data on alumni of the Tarbiyah Faculty of IAIN Bone. The data analysis used was a descriptive analysis using decision tree C4.5, Naive Bayes, and k-NN data mining algorithms assisted by the RapidMiner application. The results of this study show that (1) model prediction of the graduation status of prospective teacher students in IAIN Bone in terms of attributes generated in the Decision Tree C4.5 and Naïve Bayes data mining algorithms consist of gender, age, Semester 1 IP, Semester 2 IP, Semester 3 IP, Semester 4 IP, and GPA, while the attributes produced in k-NN data mining algorithm consists of gender, regional origin, number of siblings, age, IP Semester 1, IP Semester 2, IP Semester 3, IP Semester 4, and GPA; (2) model prediction of graduation status of iain bone teacher candidate students in terms of the accuracy rate generated in the Decision Tree C4.5 data mining algorithm of 93.90%, Naïve Bayes by 90.24%, and k-NN of 92.07%; and (3) there was no significant difference between the accuracy rate produced by decision tree's data mining algorithm. C4.5 and Naïve Bayes (p-value = 1.00); Decision Tree C4.5 and k-NN (p-value = 1.00); as well as Naïve Bayes and k-NN (p-value = 1.00) in predicting the graduation status of iain bone teacher candidate students.

Kombinasi Analytical Hierarchy Process, C4.5, dan Particle Swarm Optimization pada Klasifikasi Pegawai

Decision Tree C4.5 is widely implemented in various research fields in determining classification, but there are still weaknesses in Decision Tree C4.5, one of which is that it cannot rank each alternative. In this study, to overcome the weakness of Decision Tree C4.5, a combination of Analytical Hierarchy Process (AHP) methods, Decision Tree C4.5, and Particle Swarm Optimization (PSO) methods is proposed in the case study of employee classification for promotion recommendations. The research begins by determining the criteria and weighting criteria from the interview results which are then processed with AHP to produce employee ratings and eligibility labels for the classification process. The classification process uses the Decision Tree C4.5 method which is optimized with the PSO algorithm so as to produce employee eligibility data for promotions. The results of the combined research of AHP, Decision Tree C4.5, and PSO methods show that AHP can produce employee ratings based on performance and potential criteria, and Decision Tree C4.5 classification and optimization with PSO have better accuracy results, namely 95.80% compared to Decision Tree C4.5 method without PSO optimization is 93.40%. Based on the results of the ranking and classification of this research can be used as a basis for promotion of employees.