Data mining algorithm for development of a predictive model for mitigating loan risk in Nigerian banks

The focus of this paper is on the development of data mining algorithm for developing of predictive loan risk model for Nigerian banks. The model classifies and predicts the risk involved in granting loans to customers as either good or bad loan by collecting data based on J48 decision tree, BayesNet and Naïve Bayes algorithms for a period of ten (10) years (2010 2019) from using structured questionnaire. The formulation and simulation of the predictive model were carried out using Waikato Environment for Knowledge Analysis (WEKA) software. The performance of the three algorithms for predicting loan risk was done based on accuracy and error rate metrics. The study revealed that J48 decision tree model is the most efficient of all the three models.

Network Software Vulnerability Identifier using J48 decision tree algorithm

Software vulnerabilities are the primary causes of different security issues in the modern era. When vulnerability is exploited by malicious assaults, it substantially jeopardizes the system's security and may potentially result in catastrophic losses. As a result, automatic classification methods are useful for successfully managing software vulnerabilities, improving system security performance, and lowering the chance of the system being attacked and destroyed. In the software industry and in the field of cyber security, the ever-increasing number of publicly reported security flaws has become a major source of concern. Because software security flaws play such a significant part in cyber security attacks, relevant security experts are conducting an increasing number of vulnerability classification studies, this project can predict the software vulnerability means the software's in the device are authorized or not and who scan the system multiple times, to identify the vulnerability j48 decision tree algorithm was used. Keywords: Malicious assaults, catastrophic losses, Security flaws, Cyber security, Vulnerability Classifications.

CAN DEEP LEARNING PREDICT LABORATORY VALUES IN COVID-19?

Aims: Laboratory findings in COVID-19 patients vary according to the severity of the disease. This study aimed at defining a system of formulas that may predict the presence of thoracic CT involvement, the extent of such involvement and the need for intensive care stay on the basis of patient laboratory data using the Waikato Environment for Knowledge Analysis (WEKA) software. Methods: This study was conducted with 508 patients whose SARS-CoV-2 RT-PCR test was positive. These patients were divided into 2 groups, with and without thoracic CT involvement typical for COVID-19. Then, those patients who had signs of typical involvement for COVID-19 in their thoracic CT were divided into 3 groups depending on the extent of their lesions. J48 Decision Tree classification and Linear Regression methods were used on the WEKA software. The codes implemented in the Python programming language were used at the estimation, classification and testing stages. Results: Thoracic CT scans showed that lung involvement was absent in 93 of the patients, mild in 114, moderate in 115, and severe in 159. The success rates of WEKA Linear Regression Formulas calculated using laboratory values and demographic data, respectively 78.92%, 71.69% and 91%. The success rate of the J48 Decision Tree formula used to predict the presence of involvement in thoracic CT was found to be 95.95%. The success rate of the J48 Decision Tree, which was used to predict the degree of involvement in thoracic CT, was 84.39%. The success rate of the J48 Decision Tree used to predict the need for intensive care was found to be 93.06%. Conclusion: The results of this study will facilitate revealing the presence of lung involvement and identification of critical patients in the COVID-19 pandemic and particularly under circumstances and can be used effectively to ensure triage.

Analysis of Students' Misconducts in Higher Education using Decision Tree and ANN Algorithms

A major problem that the Higher Education Institutions (HEIs) face is the misconduct of students’ behavior. The objective of this study is to decrease these misconducts by identifying the factors which cause them on college campuses. CRISP-DM Methodology has been applied to manage the process of data mining and two data mining techniques: J48 Decision Tree (DT) and Artificial Neural Networks (ANNs) have been used to build classification models and to generate rules to classify and predict students' behavior and the location of misconduct in college campuses. They take into consideration seven factors: Student Major, Student Level, Gender, GPA Cumulative, Local Address, Ethnicity, and time of misconduct by month. Both techniques were evaluated and compared. The accuracy results were high for both classification models, whereas the J48 Decision Tree gave higher accuracy.

Performance of Hoeffding Tree and C4.5 Algorithms to Envisage an Occurrence of Hepatitis–A Liver Disease

Premature forecasting of hepatitis is extremely imperative to save an individual years and take appropriate steps to control the ailment. Decision Tree algorithms have been effectively useful in a variety of fields particularly in medicinal discipline. This manuscript investigates the premature forecasting of hepatitis by means of a variety of decision tree algorithms. In this manuscript, we build up a Hepatitis prediction model that can aid medical experts in envisaging Hepatitis condition supported on the medicinal data of patients. At the outset, we have chosen 19 imperative medicinal attributes viz., age, sex, antivirals, steroid, fatigue, anorexia, malaise, spleen palpable, etc., in addition to one target class. Secondly, we build up a prediction model using Pruned C4.5-J48 Decision Tree, Unpruned C4.5-J48, Reduced Error Pruned C4.5-J48 and Hoeffding Tree algorithms classifier for classifying Hepatitis based on these clinical attributes. Lastly, the precision of Pruned J48 decision tree approach proves to be more superior then the other approaches. Outcome acquired illustrates that Albumin and Ascites are the foremost predictive attributes which provides enhanced classification in opposition to the supplementary attributes.

Classifying the Level of Energy-Environmental Efficiency Rating of Brazilian Ethanol

The present study aimed to assess and classify energy-environmental efficiency levels to reduce greenhouse gas emissions in the production, commercialization, and use of biofuels certified by the Brazilian National Biofuel Policy (RenovaBio). The parameters of the level of energy-environmental efficiency were standardized and categorized according to the Energy-Environmental Efficiency Rating (E-EER). The rating scale varied between lower efficiency (D) and high efficiency + (highest efficiency A+). The classification method with the J48 decision tree and naive Bayes algorithms was used to predict the models. The classification of the E-EER scores using a decision tree using the J48 algorithm and Bayesian classifiers using the naive Bayes algorithm produced decision tree models efficient at estimating the efficiency level of Brazilian ethanol producers and importers certified by the RenovaBio. The rules generated by the models can assess the level classes (efficiency scores) according to the scale discretized into high efficiency (Classification A), average efficiency (Classification B), and standard efficiency (Classification C). These results might generate an ethanol energy-environmental efficiency label for the end consumers and resellers of the product, to assist in making a purchase decision concerning its performance. The best classification model was naive Bayes, compared to the J48 decision tree. The classification of the Energy Efficiency Note levels using the naive Bayes algorithm produced a model capable of estimating the efficiency level of Brazilian ethanol to create labels.