Along with the rapid development of technology, individuals today are required to align every aspect of their lives with the technological developments of the industrial revolution 4.0, consisting of artificial intelligence, the internet of things, and big data presented in society. Notably, it was related to education, including Islamic education, which frequently stereotyped about delays in responding to globalization's challenges. This preliminary study aims to encourage empirical research that is still lacking by exploring the role of big data in Islamic education and combining data from general education that has similar core. The study focused on using the scoping review method as a part of a literature review. As a result of this study, there are four impacted factors for strengthening the usage of big data: the performance and behavior factors of learning; the storage of education data; the update in the education system; and the use of big data in the education curriculum. Future studies should begin empirical research to elaborate more on these four impacted factors practically.
{"title":"Preliminary Study of the Integration of Big Data to Answer the Challenges of Islamic Education in the Technological Age","authors":"Sarah Adilah Wandansari","doi":"10.14421/ijid.2021.3319","DOIUrl":"https://doi.org/10.14421/ijid.2021.3319","url":null,"abstract":"Along with the rapid development of technology, individuals today are required to align every aspect of their lives with the technological developments of the industrial revolution 4.0, consisting of artificial intelligence, the internet of things, and big data presented in society. Notably, it was related to education, including Islamic education, which frequently stereotyped about delays in responding to globalization's challenges. This preliminary study aims to encourage empirical research that is still lacking by exploring the role of big data in Islamic education and combining data from general education that has similar core. The study focused on using the scoping review method as a part of a literature review. As a result of this study, there are four impacted factors for strengthening the usage of big data: the performance and behavior factors of learning; the storage of education data; the update in the education system; and the use of big data in the education curriculum. Future studies should begin empirical research to elaborate more on these four impacted factors practically. ","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44920167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The visibility of a university’s website on the search engine becomes an essential factor to reach a wider audience. One way to improve the visibility of a website is through Search Engine Optimization (SEO). University’s website development with SEO is inseparable from the data model because SEO supporting factors are parts of the consideration in the components and structure of the data model. This study aims to build a data model for a university website accompanied by SEO. The relational data model is used in this study based on the performance and maturity in defining schema-based design. This study was conducted through four sequential stages: literature review, planning, implementation, and evaluation. The resulting relational data model is one that has accommodated four supporting factors for SEO, namely Meta description, Meta keywords, URL structure, and image description. This study has succeeded in building a relational data model at the abstraction level of conceptual and logical. In the conceptual data model, one entity and 11 attributes are formed. The logical data model was implemented in independent work environments using RelaX and operational requirements can be fulfilled by representing each table or relationship in the schema using relational algebra.
{"title":"Relational Data Model on The University Website with Search Engine Optimization","authors":"M. R. Alifi, Hashri Hayati, M. G. Wonoseto","doi":"10.14421/ijid.2021.3223","DOIUrl":"https://doi.org/10.14421/ijid.2021.3223","url":null,"abstract":"The visibility of a university’s website on the search engine becomes an essential factor to reach a wider audience. One way to improve the visibility of a website is through Search Engine Optimization (SEO). University’s website development with SEO is inseparable from the data model because SEO supporting factors are parts of the consideration in the components and structure of the data model. This study aims to build a data model for a university website accompanied by SEO. The relational data model is used in this study based on the performance and maturity in defining schema-based design. This study was conducted through four sequential stages: literature review, planning, implementation, and evaluation. The resulting relational data model is one that has accommodated four supporting factors for SEO, namely Meta description, Meta keywords, URL structure, and image description. This study has succeeded in building a relational data model at the abstraction level of conceptual and logical. In the conceptual data model, one entity and 11 attributes are formed. The logical data model was implemented in independent work environments using RelaX and operational requirements can be fulfilled by representing each table or relationship in the schema using relational algebra.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44932485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The security hole in the android operating system sometimes not realized by users such as malware and exploitation by third parties to remote access. This study conducted to identify the vulnerabilities of android operating system by using Ghost Framework. The vulnerability of the android smartphone are found by using the Android Debug Bridge (ADB) with the exploitation method as well as to analyze the test results and identify remote access Trojan attacks. The exploitation method with several steps from preparing the tools and connecting to the testing commands to the testing device have been conducted. The result shows that android version 9 can be remote access by entering the exploit via ADB. Some information has been obtained by third parties, enter and change the contents of the system directory can be remote access like an authorized to do any activities on the device such as opening lock screen, entering the directory system, changing the system, etc.
{"title":"Analysis of Remote Access Trojan Attack using Android Debug Bridge","authors":"Deco Aprilliansyah, I. Riadi, Sunardi","doi":"10.14421/ijid.2021.2839","DOIUrl":"https://doi.org/10.14421/ijid.2021.2839","url":null,"abstract":"The security hole in the android operating system sometimes not realized by users such as malware and exploitation by third parties to remote access. This study conducted to identify the vulnerabilities of android operating system by using Ghost Framework. The vulnerability of the android smartphone are found by using the Android Debug Bridge (ADB) with the exploitation method as well as to analyze the test results and identify remote access Trojan attacks. The exploitation method with several steps from preparing the tools and connecting to the testing commands to the testing device have been conducted. The result shows that android version 9 can be remote access by entering the exploit via ADB. Some information has been obtained by third parties, enter and change the contents of the system directory can be remote access like an authorized to do any activities on the device such as opening lock screen, entering the directory system, changing the system, etc.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45032159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The barrier between the hearing and the deaf communities in Kenya is a major challenge leading to a major gap in the communication sector where the deaf community is left out leading to inequality. The study used primary and secondary data sources to obtain information about this problem, which included online books, articles, conference materials, research reports, and journals on sign language and hand gesture recognition systems. To tackle the problem, CNN was used. Naturally captured hand gesture images were converted into grayscale and used to train a classification model that is able to identify the English alphabets from A-Z. Then identified letters are used to construct sentences. This will be the first step into breaking the communication barrier and the inequality. A sign language recognition model will assist in bridging the exchange of information between the deaf and hearing people in Kenya. The model was trained and tested on various matrices where we achieved an accuracy score of a 99% value when run on epoch of 10, the log loss metric returning a value of 0 meaning that it predicts the actual hand gesture images. The AUC and ROC curves achieved a 0.99 value which is excellent.
{"title":"Sign Language Prediction Model using Convolution Neural Network.","authors":"Rebeccah Ndungi, Samuel Karuga","doi":"10.14421/ijid.2021.3284","DOIUrl":"https://doi.org/10.14421/ijid.2021.3284","url":null,"abstract":"The barrier between the hearing and the deaf communities in Kenya is a major challenge leading to a major gap in the communication sector where the deaf community is left out leading to inequality. The study used primary and secondary data sources to obtain information about this problem, which included online books, articles, conference materials, research reports, and journals on sign language and hand gesture recognition systems. To tackle the problem, CNN was used. Naturally captured hand gesture images were converted into grayscale and used to train a classification model that is able to identify the English alphabets from A-Z. Then identified letters are used to construct sentences. This will be the first step into breaking the communication barrier and the inequality. A sign language recognition model will assist in bridging the exchange of information between the deaf and hearing people in Kenya. The model was trained and tested on various matrices where we achieved an accuracy score of a 99% value when run on epoch of 10, the log loss metric returning a value of 0 meaning that it predicts the actual hand gesture images. The AUC and ROC curves achieved a 0.99 value which is excellent.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48829590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Indonesian government launched the Prakerja (pre-employment) card in the midst of the COVID-19 pandemic, andthe local citizens have voiced their opinions about this controversial program through social media such as Twitter. People’scomments on it can be useful information, and this research tries to analyze the sentiment regarding the Prakerja Card programusing the Convolutional Neural Network and Naive Bayes methods. The main task in this sentiment analysis is analyzing the dataand then classifying them into one of the following classes: positive, negative or neutral. Naive Bayes is an algorithm that is often usedin sentiment analysis research, and the results have been very good. Convolutional neural network (CNN) is a deep learning algorithmthat uses one or more layers commonly used for pattern recognition and image recognition. Having applied these methods, thisresearch found that the CNN model with the GlobalMaxPooling layer is the best model of the other two CNN models. Sentimentanalysis has the best accuracy of 78.5% on the CNN method, and NBC of 76.2% accuracy. The best accuracy result in K-fold withfive classes is 85.4% on the CNN model with a learning rate optimization of 0.00158. While the average accuracy on NBC only reached75.3%
{"title":"Sentiment Analysis of Tweets on Prakerja Card using Convolutional Neural Network and Naive Bayes","authors":"Pahlevi Wahyu Hardjita, Nurochman, Rahmat Hidayat","doi":"10.14421/ijid.2021.3007","DOIUrl":"https://doi.org/10.14421/ijid.2021.3007","url":null,"abstract":"The Indonesian government launched the Prakerja (pre-employment) card in the midst of the COVID-19 pandemic, andthe local citizens have voiced their opinions about this controversial program through social media such as Twitter. People’scomments on it can be useful information, and this research tries to analyze the sentiment regarding the Prakerja Card programusing the Convolutional Neural Network and Naive Bayes methods. The main task in this sentiment analysis is analyzing the dataand then classifying them into one of the following classes: positive, negative or neutral. Naive Bayes is an algorithm that is often usedin sentiment analysis research, and the results have been very good. Convolutional neural network (CNN) is a deep learning algorithmthat uses one or more layers commonly used for pattern recognition and image recognition. Having applied these methods, thisresearch found that the CNN model with the GlobalMaxPooling layer is the best model of the other two CNN models. Sentimentanalysis has the best accuracy of 78.5% on the CNN method, and NBC of 76.2% accuracy. The best accuracy result in K-fold withfive classes is 85.4% on the CNN model with a learning rate optimization of 0.00158. While the average accuracy on NBC only reached75.3%","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46852157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As an effort to prevent the spread of the Covid-19, various countries have implemented health protocol policies such as work-from-home, social distancing, and face mask-wearing in public places. However, monitoring compliance with the policy is still difficult, especially for the face mask policy. It is still managed by humans and is costly. Thus, this research proposes a face mask-wearing detection using a soft-margin Support Vector Machine (SVM). There are three main stages: feature selection and preprocessing, model training, and evaluation. During the first stage, the dataset of 3833 images (1915 images with face masks and 1918 images without face masks) was prepared to be used in the training stage. The training stage was conducted using SVM added with the soft-margin objective to overcome images that could not be separated linearly. At the final stage, evaluation was conducted using a confusion matrix with 10 folds cross-validation. Based on the experiments, the proposed method shows a performance accuracy of 91.7%, a precision of 90.3%, recall of 93.5%, and an F-measure of 91.8%. Our method also worked fast, taking only 0.025 seconds to process a new image. It is 7.12 times faster than Deep Learning which requires 0.18 seconds for one classification.
{"title":"Face Mask Wearing Detection Using Support Vector Machine (SVM)","authors":"Muhammad Nur Yasir Utomo, Fajrin Violita","doi":"10.14421/ijid.2021.3038","DOIUrl":"https://doi.org/10.14421/ijid.2021.3038","url":null,"abstract":"As an effort to prevent the spread of the Covid-19, various countries have implemented health protocol policies such as work-from-home, social distancing, and face mask-wearing in public places. However, monitoring compliance with the policy is still difficult, especially for the face mask policy. It is still managed by humans and is costly. Thus, this research proposes a face mask-wearing detection using a soft-margin Support Vector Machine (SVM). There are three main stages: feature selection and preprocessing, model training, and evaluation. During the first stage, the dataset of 3833 images (1915 images with face masks and 1918 images without face masks) was prepared to be used in the training stage. The training stage was conducted using SVM added with the soft-margin objective to overcome images that could not be separated linearly. At the final stage, evaluation was conducted using a confusion matrix with 10 folds cross-validation. Based on the experiments, the proposed method shows a performance accuracy of 91.7%, a precision of 90.3%, recall of 93.5%, and an F-measure of 91.8%. Our method also worked fast, taking only 0.025 seconds to process a new image. It is 7.12 times faster than Deep Learning which requires 0.18 seconds for one classification.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44606399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fitriyatul Qomariyah, Fitri Utaminingrum, M. Muchlas
The recognition of Arabic handwriting is a challenging problem to solve. The similarity among the fonts appears as a problem in the recognition processing. Various styles, shapes, and sizes which are personal and different across individuals make the Arabic handwriting recognition process even harder. In this paper, the data used are Arabic handwritten images with 101 sample characters, each of which is written by 15 different handwritten characters (total sample 101x15) with the same size (81x81 pixels). A well-chosen feature is crucial for making good recognition results. In this study, the researcher proposed a method of new features extraction to recognize Arabic handwriting. The features extraction was done by grabbing the value of similar features among various types of font writing, to be used as a new feature of the font. Then, City Block was used to compare the obtained feature to other features of the sample for classification. The Average accuracy value obtained in this study was up to 82%.
{"title":"Handwriting Arabic Character Recognition Using Features Combination","authors":"Fitriyatul Qomariyah, Fitri Utaminingrum, M. Muchlas","doi":"10.14421/ijid.2021.2360","DOIUrl":"https://doi.org/10.14421/ijid.2021.2360","url":null,"abstract":"The recognition of Arabic handwriting is a challenging problem to solve. The similarity among the fonts appears as a problem in the recognition processing. Various styles, shapes, and sizes which are personal and different across individuals make the Arabic handwriting recognition process even harder. In this paper, the data used are Arabic handwritten images with 101 sample characters, each of which is written by 15 different handwritten characters (total sample 101x15) with the same size (81x81 pixels). A well-chosen feature is crucial for making good recognition results. In this study, the researcher proposed a method of new features extraction to recognize Arabic handwriting. The features extraction was done by grabbing the value of similar features among various types of font writing, to be used as a new feature of the font. Then, City Block was used to compare the obtained feature to other features of the sample for classification. The Average accuracy value obtained in this study was up to 82%.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49288129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
DHCP Server as part of the network infrastructure in charge of distributing host configurations to all devices has the potential to be controlled. If the DHCP Server is successfully controlled, all network devices connected to the server can potentially be controlled. From the observations made at PT. Rekayasa Engineering found a vulnerability in the DHCP Server that has the potential to experience DHCP Rogue or DHCP Spoofing, where the client will fail to communicate with the authorized DHCP Server, as well as open the door for attackers to enter the network. For this reason, DHCP Snooping and DHCP Alert methods are implemented. DHCP Snooping will ensure that every data traffic has been filtered and directed to the registered interface. Meanwhile, the use of DHCP Alert is required in monitoring data traffic during the Discover, Offer, Request, and Acknowledge (DORA) process. In the tests performed, DHCP Snooping and DHCP Alert managed to anticipate attacks that tried to placed DHCP Rogue on the network infrastructure. DHCP Alert, configured on the proxy router, ensures that the DORA process can only occur between an authorized DHCP server and a client. DHCP Snooping test also shows that communication from clients can only be replied to by Trusted DHCP Server. The existence of DHCP Snooping and DHCP Alert makes the host configuration fully controlled by the authorized DHCP Server.
{"title":"The DHCP Snooping and DHCP Alert Method in Securing DHCP Server from DHCP Rogue Attack","authors":"Dio Aditya Pradana, Ade Surya Budiman","doi":"10.14421/ijid.2021.2287","DOIUrl":"https://doi.org/10.14421/ijid.2021.2287","url":null,"abstract":"DHCP Server as part of the network infrastructure in charge of distributing host configurations to all devices has the potential to be controlled. If the DHCP Server is successfully controlled, all network devices connected to the server can potentially be controlled. From the observations made at PT. Rekayasa Engineering found a vulnerability in the DHCP Server that has the potential to experience DHCP Rogue or DHCP Spoofing, where the client will fail to communicate with the authorized DHCP Server, as well as open the door for attackers to enter the network. For this reason, DHCP Snooping and DHCP Alert methods are implemented. DHCP Snooping will ensure that every data traffic has been filtered and directed to the registered interface. Meanwhile, the use of DHCP Alert is required in monitoring data traffic during the Discover, Offer, Request, and Acknowledge (DORA) process. In the tests performed, DHCP Snooping and DHCP Alert managed to anticipate attacks that tried to placed DHCP Rogue on the network infrastructure. DHCP Alert, configured on the proxy router, ensures that the DORA process can only occur between an authorized DHCP server and a client. DHCP Snooping test also shows that communication from clients can only be replied to by Trusted DHCP Server. The existence of DHCP Snooping and DHCP Alert makes the host configuration fully controlled by the authorized DHCP Server.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43529189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ransomware viruses have become a dangerous threat increasing rapidly in recent years. One of the variants is Conti ransomware that can spread infection and encrypt data simultaneously. Attacks become a severe threat and damage the system, namely by encrypting data on the victim's computer, spreading it to other computers on the same computer network, and demanding a ransom. The working principle of this Ransomware acts by utilizing Registry Query, which covers all forms of behavior in accessing, deleting, creating, manipulating data, and communicating with C2 (Command and Control) servers. This study analyzes the Conti virus attack through a network forensic process based on network behavior logs. The research process consists of three stages, the first stage is simulating attacks on the host computer, the second stage is carrying network forensics by using live forensics methods, and the third stage is analysing malware by using statistical and dynamic analysis. The results of this study provide forensic data and virus behavior when running on RAM and computer networks so that the data obtained makes it possible to identify ransomware traffic on the network and deal with zero-day, especially ransomware threats. It is possible to do so because the analysis is an initial step in generating virus signatures based on network indicators.
{"title":"Analysis of Conti Ransomware Attack on Computer Network with Live Forensic Method","authors":"R. Umar, I. Riadi, Ridho Surya Kusuma","doi":"10.14421/ijid.2021.2423","DOIUrl":"https://doi.org/10.14421/ijid.2021.2423","url":null,"abstract":"Ransomware viruses have become a dangerous threat increasing rapidly in recent years. One of the variants is Conti ransomware that can spread infection and encrypt data simultaneously. Attacks become a severe threat and damage the system, namely by encrypting data on the victim's computer, spreading it to other computers on the same computer network, and demanding a ransom. The working principle of this Ransomware acts by utilizing Registry Query, which covers all forms of behavior in accessing, deleting, creating, manipulating data, and communicating with C2 (Command and Control) servers. This study analyzes the Conti virus attack through a network forensic process based on network behavior logs. The research process consists of three stages, the first stage is simulating attacks on the host computer, the second stage is carrying network forensics by using live forensics methods, and the third stage is analysing malware by using statistical and dynamic analysis. The results of this study provide forensic data and virus behavior when running on RAM and computer networks so that the data obtained makes it possible to identify ransomware traffic on the network and deal with zero-day, especially ransomware threats. It is possible to do so because the analysis is an initial step in generating virus signatures based on network indicators.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45443392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pulung Hendro Prastyo, Septian Eko Prasetyo, S. Arti
Credit scoring is a model commonly used in the decision-making process to refuse or accept loan requests. The credit score model depends on the type of loan or credit and is complemented by various credit factors. At present, there is no accurate model for determining which creditors are eligible for loans. Therefore, an accurate and automatic model is needed to make it easier for banks to determine appropriate creditors. To address the problem, we propose a new approach using the combination of a machine learning algorithm (Naïve Bayes), Information Gain (IG), and discretization in classifying creditors. This research work employed an experimental method using the Weka application. Australian Credit Approval data was used as a dataset, which contains 690 instances of data. In this study, Information Gain is employed as a feature selection to select relevant features so that the Naïve Bayes algorithm can work optimally. The confusion matrix is used as an evaluator and 10-fold cross-validation as a validator. Based on experimental results, our proposed method could improve the classification performance, which reached the highest performance in average accuracy, precision, recall, and f-measure with the value of 86.29%, 86.33%, 86.29%, 86.30%, and 91.52%, respectively. Besides, the proposed method also obtains 91.52% of the ROC area. It indicates that our proposed method can be classified as an excellent classification.
{"title":"A Machine Learning Framework for Improving Classification Performance on Credit Approval","authors":"Pulung Hendro Prastyo, Septian Eko Prasetyo, S. Arti","doi":"10.14421/ijid.2021.2384","DOIUrl":"https://doi.org/10.14421/ijid.2021.2384","url":null,"abstract":"Credit scoring is a model commonly used in the decision-making process to refuse or accept loan requests. The credit score model depends on the type of loan or credit and is complemented by various credit factors. At present, there is no accurate model for determining which creditors are eligible for loans. Therefore, an accurate and automatic model is needed to make it easier for banks to determine appropriate creditors. To address the problem, we propose a new approach using the combination of a machine learning algorithm (Naïve Bayes), Information Gain (IG), and discretization in classifying creditors. This research work employed an experimental method using the Weka application. Australian Credit Approval data was used as a dataset, which contains 690 instances of data. In this study, Information Gain is employed as a feature selection to select relevant features so that the Naïve Bayes algorithm can work optimally. The confusion matrix is used as an evaluator and 10-fold cross-validation as a validator. Based on experimental results, our proposed method could improve the classification performance, which reached the highest performance in average accuracy, precision, recall, and f-measure with the value of 86.29%, 86.33%, 86.29%, 86.30%, and 91.52%, respectively. Besides, the proposed method also obtains 91.52% of the ROC area. It indicates that our proposed method can be classified as an excellent classification.","PeriodicalId":33558,"journal":{"name":"IJID International Journal on Informatics for Development","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48536260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：