Articles
Comparison of Machine Learning Algorithms Using WEKA and Sci-Kit Learn in Classifying Online Shopper Intention
Christian, Yefta
JITE (JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING) Vol 3, No 1 (2019): EDISI JULI
Publisher : Universitas Medan Area
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (906.727 KB)
|
DOI: 10.31289/jite.v3i1.2599
The growth of online stores nowadays is very rapid. This is supported by faster and better internet infrastructure. The increasing growth of online stores makes the competition more difficult in this business field. It is necessary for online stores to have a website or an application that is able to measure and classify consumers? spending intentions, so that the consumers will have eyes on things on the sites and applications to make purchases eventually. Classification of online shoppers? intentions can be done by using several algorithms, such as Naïve Bayes, Multi-Layer Perceptron, Support Vector Machine, Random Forest and J48 Decision Trees. In this case, the comparison of algorithms is done with two tools, WEKA and Sci-Kit Learn by comparing the values of F1-Score, accuracy, Kappa Statistic and mean absolute error. There is a difference between the test results using WEKA and Sci-Kit Learn on the Support Vector Machine algorithm. Based on this research, the Random Forest algorithm is the most appropriate algorithm to be used as an algorithm for classifying online shoppers? intentions.
WEB-BASED CHATBOT WITH NATURAL LANGUAGE PROCESSING AND KNUTH-MORRIS-PRATT (CASE STUDY: UNIVERSITAS INTERNASIONAL BATAM)
Christian, Yefta;
Erline, Meiliverani
JST (Jurnal Sains dan Teknologi) Vol 11, No 1 (2022)
Publisher : Universitas Pendidikan Ganesha
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.23887/jst-undiksha.v11i1.43258
As an educational institution, there will be many people seeking information about Universitas Internasional Batam (UIB), whether the students, alumni, prospective students, colleagues, nor the wider community. Currently, information services at UIB are still carried out manually by humans or through the website which users need to take several steps by using the text-based search feature. Software Development Life Cycle with Waterfall methodology is used in developing the chatbot. This research uses Web Scraping technique to collect and extract the required data from the official website of UIB before being processed using Natural Language Processing approach and Knuth-Morris-Pratt algorithm. The chatbot was built using Python programming language with the expectation of having ability to answer questions correctly in real-time and ease users to obtain information without visiting college. The data set for chatbot training consists of 193 questions and statements which are grouped into 18 tags. Whilst Black Box Testing technique is implemented for chatbot testing using 100 questions. This web-based chatbot is successfully built with an 86% accuracy rate in answering user questions.
RANCANG BANGUN APLIKASI KURSUS ONLINE BERBASIS WEB DENGAN SISTEM REKOMENDASI METODE CONTENT-BASED FILTERING
Yefta Christian;
Kelvin Kelvin
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 7 No 1 (2022): Januari
Publisher : LPPM Universitas Abdurrab
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.36341/rabit.v7i1.2181
The Institute for Courses and Training is a non-formal education that provides various special training to educate students' skills. However, there are things that often become obstacles for prospective students, namely being confused about choosing courses according to their preferences. Therefore, the purpose of this research is to design an online course application with a recommendation system for the Content-based Filtering method. In addition, this research also applies the cosine similarity algorithm to determine courses that are similar to the course history that has been accessed by the user. The dataset used to run the recommendation system algorithm was taken from the Kaggle website entitled “Udemy Course” with a total of 3,682 records. The final result of this research is an online course application that can provide course recommendations based on the highest similarity value from the cosine similarity algorithm.
Comparison of Machine Learning Algorithms Using WEKA and Sci-Kit Learn in Classifying Online Shopper Intention
Yefta Christian
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 3, No 1 (2019): EDISI JULI
Publisher : Universitas Medan Area
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31289/jite.v3i1.2599
The growth of online stores nowadays is very rapid. This is supported by faster and better internet infrastructure. The increasing growth of online stores makes the competition more difficult in this business field. It is necessary for online stores to have a website or an application that is able to measure and classify consumers’ spending intentions, so that the consumers will have eyes on things on the sites and applications to make purchases eventually. Classification of online shoppers’ intentions can be done by using several algorithms, such as Naïve Bayes, Multi-Layer Perceptron, Support Vector Machine, Random Forest and J48 Decision Trees. In this case, the comparison of algorithms is done with two tools, WEKA and Sci-Kit Learn by comparing the values of F1-Score, accuracy, Kappa Statistic and mean absolute error. There is a difference between the test results using WEKA and Sci-Kit Learn on the Support Vector Machine algorithm. Based on this research, the Random Forest algorithm is the most appropriate algorithm to be used as an algorithm for classifying online shoppers’ intentions.
Application of K-Means Algorithm for Clustering the Quality of Lecturer Learning at Batam International University
Yefta Christian
IJISTECH (International Journal of Information System and Technology) Vol 3, No 2 (2020): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v3i2.49
The need to measure the quality of learning becomes very significant when the quality of learning is still low. This also applies to the quality of learning at the highest level. The quality of lecturer learning in class is often not in accordance with what it should be, one of the constraints of this low quality is that the quality of lecturer learning is not accurately measured. Data mining is used in this research to map the quality of lecturer learning based on its cluster, namely Clustering, It is hoped that universities can measure the quality of learning from their lecturers accurately. From this research, students with low social studies tend to value lecturers with low grades; conversely students with high social studies tend to judge lecturers with high enough grades. The k-Means algorithm is accurate enough to be used in clustering the quality of lecturer learning based on grades and results of student questionnaires.
Analisis Sistem Pengamanan Akses Autentikasi Jaringan dengan Metode Port Knocking dan Action Tarpit pada Router Mikrotik
Yefta Christian
Telcomatics Vol 4 No 1 (2019)
Publisher : Universitas Internasional Batam
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The use of mikrotik router in the process of forming a network system in a company both internally and externally is a common thing in the world of work, this is in line with the rapid development of technology today. In this study, researchers designed user permissions on ports using mikrotik routers as well as testing the security of port knocking methods and action tarpit firewalls. Port knocking method is a technique that temporarily closed port access. With the method of port knocking researchers can test the security of a port using a knocking port on the router mikrotik, so it can be known how safe port knocking method to protect certain ports. Port knocking used in mikrotik this router using winbox to see it, and also by using web service on winbox webfig already provided by party mikrotik router.
Perancangan Aplikasi Directory Berbasis Hybrid Dengan Metode Scrum (Case: Grand Batam Mall)
Yusuf;
Yefta Christian
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol 13 No 1 (2022): Maret
Publisher : UNIVERSITAS STEKOM
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (305.057 KB)
|
DOI: 10.51903/jtikp.v13i1.303
Pada kota besar, ukuran mal yang besar menyebabkan masyarakat kesulitan dalam mencari store yang ingin dituju sehingga dibutuhkannya sebuah aplikasi directory yang dapat diandalkan. Aplikasi directory dikembangkan berbasis hybrid dengan menggunakan metode scrum. Hybrid merupakan aplikasi yang dibangun menggunakan teknologi standar web seperti HTML, CSS, dan JavaScript. Untuk meningkatkan kualitas sistem, metode scrum dimanfaatkan sehingga mampu menghasilkan sistem yang bernilai maksimum. Tahapan yang dilakukan dalam merancang sistem dimulai dari pengumpulan data, mengidentifikasikan masalah, menganalisa kebutuhan user, melakukan perancangan aplikasi, dan implementasi sistem. Hasil dari penelitian menyimpulkan bahwa metode scrum dapat mempermudah dalam perancangan aplikasi dengan tepat waktu dan sasaran
Application of K-Means Algorithm for Clustering the Quality of Lecturer Learning at Batam International University
Yefta Christian
IJISTECH (International Journal of Information System and Technology) Vol 3, No 2 (2020): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1041.433 KB)
|
DOI: 10.30645/ijistech.v3i2.49
The need to measure the quality of learning becomes very significant when the quality of learning is still low. This also applies to the quality of learning at the highest level. The quality of lecturer learning in class is often not in accordance with what it should be, one of the constraints of this low quality is that the quality of lecturer learning is not accurately measured. Data mining is used in this research to map the quality of lecturer learning based on its cluster, namely Clustering, It is hoped that universities can measure the quality of learning from their lecturers accurately. From this research, students with low social studies tend to value lecturers with low grades; conversely students with high social studies tend to judge lecturers with high enough grades. The k-Means algorithm is accurate enough to be used in clustering the quality of lecturer learning based on grades and results of student questionnaires.
BELAJAR BAHASA INGGRIS DITENGAH ISU RASISME MELALUI MEDIA WEBSITE
Yefta Christian;
Robin Robin;
Lenny Julyanti;
Claudia Theophilia;
Ferdinand William;
Kevin Kevin;
Michelle Febri Soegianto;
Gracella Tandiono;
Jeslyn Teo;
Sani Kurnia;
Vincent Gonawan
National Conference for Community Service Project (NaCosPro) Vol 2 No 1 (2020): The 2nd National Conference of Community Service Project 2020 (Accepted Papers)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Internasional Batam
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37253/nacospro.v2i1.1205
Batam City is an archipelago that is directly adjacent to Singapore and Malaysia, so English is an important language to learn. Also, English language education during schooling is uneven. The result is that not all people who are looking for work in Batam City can speak English fluently and fluently. Some of them are affected by discrimination, they can meet the requirements, but constrained in English. This program is designed to learn English through online media. The method used is a website platform that contains materials with a 5 Whys approach. The survey results show that the inability to speak English has become part of the discrimination and subject job seekers to considerable difficulties. So, the English learning program through this website platform helps the learning process of English independently and improves competence in English.
Penerapan Pemasaran Digital Bagi Pengembangan Bisnis Umkm Ngombe Kopi Kota Batam
Yefta Christian;
Vira Vira;
Fiona Vinelia;
Germent Basri;
Lusiana Lusiana;
Julia Christini;
Felix Filbert;
Jeny Jeny
National Conference for Community Service Project (NaCosPro) Vol 3 No 1 (2021): The 3rd National Conference of Community Service Project 2021
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Internasional Batam
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37253/nacospro.v3i1.5957
Seluruh negara di dunia sedang menghadapi pandemi Covid-19, termasuk Indonesia. Hal tersebut memberi dampak negatif pada keseluruhan sektor, terutama bidang ekonomi. Kondisi dunia seperti itu membatasi aktivitas masyarakat seluruh dunia termasuk Kota Batam hanya dalam rumah. Dengan adanya perkembangan dalam inovasi teknologi digital dalam beberapa tahun terakhir, kegiatan keseharian manusia mulai terbantu oleh teknologi-teknologi tersebut. Salah satu kegiatan tersebut adalah bidang pemasaran yang diterapkan oleh UMKM. Kegiatan ini membahas tentang penerapan pemasaran digital bagi UMKM Ngombe Kopi untuk meningkatkan pencapaian impresi pada masyarakat umum melalui sosial media dan mencapai peningkatan penjualan. Metode penelitian yang digunakan dalam penelitian ini adalah dengan pendekatan metode deskriptif kuantitatif. Hasil pelaksanaan kegiatan ini mencakup pengoptimalan media sosial (Instagram) melalui penerapan konten inovatif dengan kreasi company profile, post dan story feeds, penambahan fasilitas Board Games, melakukan Rebranding dan mengikuti tren terkini