Claim Missing Document
Check
Articles

Found 24 Documents
Search

PENGEMBANGAN APLIKASI PENJADWALAN KONTEN INSTAGRAM OTOMATIS BAGI PELAKU UMKM DENGAN FLUTTER FRAMEWORK Chrystian Dwi Putra Yunus; Muhamad Bahrul Ulum
JURNAL ILMIAH INFORMATIKA Vol 11 No 02 (2023): Jurnal Ilmiah Informatika (JIF)
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/jif.v11i02.8038

Abstract

The actors Micro, Small, and Medium Business (MSMEs) which are dominated by the elderly, still rely on conventional marketing (mouth to mouth), resulting in a small market. In this condition, digital marketing is here to be a solution, where MSMEs have great potential to develop their market without any geographical restrictions. However, most of these MSMEs are not young anymore, making it difficult for them to adapt to digital technology. One of them is Instagram (social media) which has great potential in digital marketing. Therefore, in this study, an application will be developed using Flutter Framework that can help MSME actors to be able to automatically generate an Instagram content schedule according to the intensity level of Instagram promotions and features they want to use. So that it can help them in optimizing digital marketing without the need to adapt to social media that tends to make it difficult for them.
MENGINTEGRASIKAN PENDEKATAN ILMIAH YANG BERPUSAT PADA MALL (MOBILE ASSISTED LANGUAGE LEARNING) DALAM PEMBELAJARAN MENULIS BAHASA INGGRIS Irma Savitri Sadikin; Oktian Fajar Nugroho; Muhamad Bahrul Ulum
ELTIN Journal Vol 12 No 1 (2024): VOLUME 12, ISSUE 1, APRIL 2024
Publisher : STKIP Siliwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Writing has often been considered a challenging skill to master. The purpose of this research is to investigate the effect of a scientific approach based on Mobile Assisted Language Learning (MALL) on enhancing students' descriptive writing abilities. This investigation employed classroom action research with twenty-four ninth-grade junior high school students in West Jakarta as participants. The research was conducted in two cycles, utilizing observation, interviews, and a series of writing tests to collect data. The results indicated that students' writing improved as a consequence of the use of a scientific approach based on MALL. By engaging them in a number of practices at each meeting, working with websites and applications, and seeking feedback from both students and teachers, MALL tended to enhance students' writing abilities. Implementing a scientific approach supported by MALL has shown potential in helping learners enhance their ideas in writing. They demonstrated their ability to create lengthy paragraphs supplemented with relevant details. Students boosted their vocabulary learning by using digital dictionaries and watching videos. Regular feedback from peers and teachers were crucial in helping students understand the significance of punctuation and spelling accuracy in their written work. Therefore, it is advised to conduct additional scholarly research to examine the effectiveness of the scientific approach based on MALL, covering not just writing skills but also extending to reading, speaking, or listening skills.
Implementation of Design Thinking Method in UI/UX Redesign of Public Complaint Application (Case Study: Go Siaga App) Rafi Kurnia Pangestu; Muhamad Bahrul Ulum
JURNAL TEKNIK INFORMATIKA Vol 16, No 2 (2023): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v16i2.27416

Abstract

Go Siaga App is a mobile-based application by Tangerang Sub-district Police Office that provides special community services for the Tangerang sub-district community which provides features in the form of reports of disturbances in public security and reports of loss or damage. Since it is a new application released in March 2021 on Google Playstore, there are several things that need to be considered to maintain the usability of the application. This research aims to redesign the user interface and user experience (UI/UX) of the Go Siaga application using Design Thinking Method in the design process. Some of the supporting aspects for testing the user satisfaction such as effectiveness, efficiency, usefulness, satisfaction, and learnability are met in the usability testing. The results showed that the percentage of all the aspects in usability from the redesigned version were all higher than the current one with 80% of effectiveness, 80% of efficiency, 80% of usefulness, 86.67% of satisfaction, and 73.33% of learnability. Therefore, based on the research results, the redesign of Go Siaga is more effective, more efficient, more useful, more satisfying, and also easy to learn.
APPLICATION OF MACHINE LEARNING MODELS FOR FRAUD DETECTION IN SYNTHETIC MOBILE FINANCIAL TRANSACTIONS Imam Mulyana; Muhamad Bahrul Ulum
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 4 (2025): JITK Issue May 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i4.6420

Abstract

The financial industry faces challenges in detecting fraud. The 2023 Basel Anti-Money Laundering (AML) Index report shows a worsening money laundering risk trend over the last five years in 107 countries. And according to the Financial Action Task Force (FATF) in 2023, this is exacerbated by financial institutions which have problems with low reporting of suspicious financial transactions (Suspicious Transaction Report). Limited access to confidential financial transaction data is an obstacle in developing machine learning-based fraud detection models. To overcome this challenge, the research uses PaySim synthetic datasets that mimic real financial transaction patterns. The CRISP-DM approach is used, including the Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation and Deployment stages. The algorithms used are Decision Tree, Random Forest, and XGBoost. Model evaluation is carried out using accuracy, precision, recall, F1-score, specificity, cross-validation and ROC-AUC metrics. The results show that the Random Forest algorithm has the best performance with 99% accuracy, followed by XGBoost (98.9%) and Decision Tree (97%). Data analysis shows that cash-out and transfer transactions have the highest risk of fraud. This model has proven effective in detecting suspicious financial transactions with a high level of accuracy. This research makes a significant contribution to mitigating financial risks, supporting anti-fraud policies, and encouraging innovation in fraud detection using synthetic data.