cover
Contact Name
Andri Syafrianto
Contact Email
andrisyafrianto@gmail.com
Phone
+628127828138
Journal Mail Official
lp2m@stmikelrahma.ac.id
Editorial Address
Jl. Sisingamangaraja No. 76 Mergangsan, Yogyakarta
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Fahma : Jurnal Informatika Komputer, Bisnis dan Manajemen
ISSN : 16932277     EISSN : 27152944     DOI : https://doi.org/10.61805
Jurnal FAHMA adalah jurnal yang memuat naskah ilmiah dari peneliti, akademisi, maupun praktisi, berupa hasil penelitian, tinjauan pustaka ( literature review ) dan/atau bentuk karya tulis ilmiah lainnya, yang khusus mengkaji bidang Ilmu Komputer antara lain sebagai berikut : Kecerdasan Buatan, Pembelajaran Mesin, Penambangan Data, Sistem Pakar, Sistem Pendukung Keputusan, Pemrograman Web, Komputasi Bergerak, Jaringan Komputer, Sistem Informasi, Sistem Basis Data, Sistem Keamanan, Strategi Bisnis, Ánalisis Bisnis, Bisnis Digital, Etika Bisnis, Model Bisnis, Strategi Manajemen, Manajemen Proses Bisnis, Manajemen Hubungan Pelanggan, Aplikasi Enterprise, Pemasaran Digital
Articles 260 Documents
Integrasi Kecerdasan Buatan dan Strategi Bisnis dalam Transformasi Digital Maria Atik Sunarti Ekowati; Rousyati; Ahmad Fauzi; Pudji Widodo
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.208

Abstract

Digital transformation has become a critical driver of organizational competitiveness in today’s disruptive economic environment. This study examines the integration of Artificial Intelligence (AI) with digital business strategies across the e-commerce, fintech, education, healthcare, and manufacturing sectors. A multi-case quantitative approach was employed using 250 observations collected over a ten-month period from organizational information systems, customer satisfaction surveys, and operational performance indicators. Data analysis was conducted using Random Forest and Support Vector Machine (SVM) algorithms to predict business strategy effectiveness, while multiple regression analysis was used to examine relationships among key variables. The results indicate significant improvements in productivity (24.5%), operational efficiency (24.1%), customer satisfaction (24.2%), and return on investment (27.5%). The multiple regression model achieved an R² value of 0.82, while the Random Forest model attained a predictive accuracy of 91%. The study contributes by proposing an AI–business strategy integration framework that extends the Resource-Based View and Strategic Alignment perspectives. Practical implications include supporting managerial decision-making in AI investment allocation, enhancing data analytics capabilities, and developing predictive customer relationship management (CRM) systems. The novelty of this research lies in combining quantitative analysis, data simulation, and predictive modeling to support sustainable digital transformation.
Perbandingan Logistic Regression dan Random Forest untuk Prediksi Respon Pelanggan Asuransi Harliana Harliana; Tito Prabowo; Ady Alzhava Nuary
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.214

Abstract

Vehicle insurance companies increasingly rely on data-driven marketing strategies to identify prospective customers who are likely to respond positively to insurance offers. However, customer response prediction is challenging due to class imbalance, where non-responsive customers substantially outnumber responsive ones. This study aims to compare the performance of Logistic Regression and Random Forest models in predicting customer responses to vehicle insurance products using the Synthetic Minority Oversampling Technique (SMOTE). The analysis was conducted using the Vehicle Insurance dataset obtained from Kaggle. Experimental results indicate that Random Forest achieved the best overall performance, with an accuracy of 0.80, a positive-class F1-score of 0.59, and a ROC–AUC score of 0.88. In contrast, Logistic Regression produced a higher positive-class recall of 0.98 but a lower precision of 0.35, indicating a greater tendency to generate false-positive predictions. Feature importance analysis revealed that Previously_Insured, Vehicle_Damage, and Age were the most influential factors affecting customer responses. These findings suggest that the combination of Random Forest and SMOTE provides an effective approach for handling imbalanced data and improving customer response prediction in vehicle insurance marketing campaigns.
Analisis Bibliometrik dan Spasial Border Fiscal Cost Premium Menggunakan VOSviewer Sunaryono Sunaryono; Maria Christiana Iman Kalis; M Irfani Hendri
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.219

Abstract

Border regions often face higher public service delivery costs due to geographic isolation, limited accessibility, and inadequate infrastructure. Although research on fiscal equalization, regional inequality, and border studies has expanded significantly, existing studies remain fragmented and lack a comprehensive conceptual framework for understanding fiscal compensation needs in border areas. This study aims to analyze the development of the literature and propose the concept of Border Fiscal Cost Premium through a Systematic Literature Review (SLR) and bibliometric analysis using VOSviewer. The dataset consists of 82 peer-reviewed articles indexed in Scopus from 2001 to 2025. The results identify four major research clusters: Regional Economy and Border Relations, Infrastructure Investment and Economic Development, Fiscal Equalization and Public Finance, and Border Governance and Spatial Inequality. Temporal analysis reveals growing attention to themes such as accessibility, public services, demography, and territorial disadvantage. The literature synthesis indicates that additional fiscal costs in border regions are driven by geographic isolation, limited connectivity, institutional fragmentation, constrained fiscal capacity, and interregional coordination challenges. The proposed Border Fiscal Cost Premium serves as a conceptual framework integrating fiscal, spatial, and governance dimensions to support more adaptive, equitable, and place-based fiscal transfer policies for border regions.
Perancangan User Interface melalui Pengembangan Wireframe pada Pengelolaan Zakat dan Sedekah Digital Fata Nidaul Khasanah; Dhian Tyas Untari; Fauzan Natsir
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.221

Abstract

The rapid advancement of digital technology has transformed various public service sectors, including the management of zakat and charitable donations in mosques. However, many mosques still rely on conventional management practices, which often result in administrative inefficiencies, limited financial transparency, and suboptimal transaction data management. Therefore, a digital zakat and charity management system is needed to improve service quality and accountability. This study aims to design a wireframe as an initial step toward developing a comprehensive user interface for a digital zakat and charity management system based on user needs. A qualitative descriptive approach was employed, emphasizing user-centered requirements analysis. The research process involved understanding the user context and defining user requirements. The findings identified two primary user groups, namely donors (muzakki) and zakat management administrators, along with their respective pain points. Based on these findings, system requirements and proposed solutions were formulated, followed by the design of user flows and low-fidelity wireframes. The resulting wireframe includes key features such as a zakat and charity management dashboard, donation and zakat payment services, and financial reporting modules. These designs provide a foundation for developing a user-centered digital management system for mosque-based zakat and charity services.
Analisis Penentuan Jenis Melon Terbaik Menggunakan Metode AHP pada Jagasura Farm Tegal Shandy Ariffatulloh; Sri Lestari
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.222

Abstract

Selecting melon varieties that align with consumer preferences is essential for enhancing customer satisfaction and supporting purchasing decisions in the agribusiness sector. However, melon selection is often conducted subjectively because it involves multiple quality attributes, including sweetness, texture, appearance, size, and aroma. This study aims to identify the most preferred melon variety based on consumer preferences using the Analytical Hierarchy Process (AHP). The research was conducted at Jagasura Farm, Tegal, involving 30 consumers to assess the importance of selection criteria and three farm managers as experts to evaluate alternative melon varieties. Data were analyzed through pairwise comparisons, geometric mean calculations, matrix normalization, and consistency testing. The results indicate that sweetness was the most influential criterion with a priority weight of 0.355, followed by texture (0.204), appearance (0.187), size (0.172), and aroma (0.082). The ranking results show that Lavender melon achieved the highest global synthesis weight (0.303), followed by Sweet Net (0.281), Sweet Hami (0.233), and Inthanon (0.182). A Consistency Ratio (CR) of 0.033 confirms the reliability and consistency of the evaluations. These findings demonstrate that AHP is an effective decision-support method for selecting melon varieties based on consumer preferences.
A Comparative Analysis of Resource Utilization Efficiency and I/O Performance in MySQL and PostgreSQL Running in Docker Containers Indah Dwi Putri; Maria Yuliana Erni Artika; Rosalia Ningsi Feu Uskenat; Edhy Sutanta; Suparyanto
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.241

Abstract

The exponential growth of data demands highly efficient relational database management systems (RDBMS). This study evaluates resource utilization and input/output (I/O) performance differences between MySQL 8.0 and PostgreSQL 15 within a Docker container. A quantitative experiment was conducted using a constrained environment of 2 CPU cores and 2 GB RAM, utilizing a normalized sales schema with 100,000 records. Three query scenarios—a complex four-table join, an aggregation, and a single-table range filter—were each executed 30 times under cold and warm-start conditions, reporting statistical means, medians, standard deviations, and 95% confidence intervals. Memory was tracked via container-level resident memory (RSS) and engine-specific buffers (InnoDB buffer pool and PostgreSQL's shared_buffers), while I/O utilized precise before-after deltas. Under warm-start complex joins, PostgreSQL 15 averaged 0.0234 seconds compared to MySQL 8.0’s 0.0442 seconds. PostgreSQL maintained a significantly lower container RSS (~54 MiB versus MySQL’s ~533 MiB), though engine-specific buffer utilization remained closer (~27 MiB versus ~41 MiB). This indicates MySQL’s default settings over-allocate container memory. Ultimately, PostgreSQL 15 demonstrates superior execution speed and resource efficiency for complex queries in limited-resource Docker environments under the default configurations tested here.
Sistem Pakar Diagnosis Penyakit Gigi dan Mulut Menggunakan Metode Hybrid Certainty Factor dan k-Nearest Neighbors Herdiesel Santoso
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.213

Abstract

Dental and oral diseases are common health problems that require accurate diagnosis for appropriate treatment. Limited access to healthcare professionals highlights the need for a decision-support system that can assist in early diagnosis. This study aims to develop an expert system for diagnosing dental and oral diseases using a hybrid Certainty Factor (CF) and k-Nearest Neighbors (k-NN) method. CF is used to represent expert knowledge through rules with confidence values, while k-NN classifies diseases based on the similarity of case data. The dataset was constructed from dental and oral disease symptoms represented as binary data. System performance was evaluated using a confusion matrix, precision, recall, F1-score, and k-fold cross-validation. The results show that the hybrid method achieved an accuracy of 88%, outperforming CF at 78% and k-NN at 82%. The evaluation also indicates that the hybrid method provides more stable performance and improves diagnostic quality. Therefore, the developed expert system can provide more accurate diagnostic results and serve as a supporting tool for the early detection of dental and oral diseases.
Rancang Bangun Aplikasi FitOn sebagai Media Latihan Kebugaran Mandiri Berbasis Android Rachmad Sanuri; Ahmad Khoiruridho
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.220

Abstract

Technological developments encourage the use of mobile applications in various fields, including fitness. Independent training activities at home require media that is practical, easy to use, and able to assist users in carrying out and recording exercises in a structured manner. This research aims to design and build the FitOn application as an Android-based independent fitness training media. The development method uses a prototype method so that the design process is carried out in stages according to user needs. The application built has main features such as user authentication, a homepage with a summary of the last 7 days of activity, a training menu with training separation based on repetition and duration, training reports with date filters, and user profiles. The application implementation uses Flutter as a development framework and Firebase as a backend service for authentication and data storage. The results of the study show that the FitOn application is able to assist users in selecting exercises, running training sessions according to the type of movement, recording training results, and viewing activity reports in a more structured manner. Thus, this application can be an alternative independent fitness training media that is practical and can be accessed via Android devices.
Evaluasi Keberhasilan SIAKAD Berbasis Model DeLone And McLean Di Universitas Bangka Belitung Tri Ari Cahyono; Muhamad Fachri Akbar
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.223

Abstract

The Academic Information System (SIAKAD) is an essential component in supporting academic services in higher education institutions. The success of its implementation influences the effectiveness of academic processes and the quality of services provided to students. This study aims to evaluate the success of the Academic Information System at Universitas Bangka Belitung (UBB) using the DeLone and McLean Information Systems Success Model based on students’ perceptions. A quantitative approach with a survey method was employed involving 150 active students selected through purposive sampling. Data were collected using a questionnaire consisting of 24 items measuring six variables: System Quality, Information Quality, Service Quality, Use, User Satisfaction, and Net Benefits. Data analysis was conducted using Partial Least Squares–Structural Equation Modeling (PLS-SEM) with SmartPLS 4.0 software. The results indicate that all constructs demonstrate satisfactory validity and reliability. System Quality, Information Quality, and Service Quality have positive and significant effects on both Use and User Satisfaction. Furthermore, Use and User Satisfaction significantly contribute to the Net Benefits perceived by students. These findings confirm that the DeLone and McLean Model is effective for evaluating the success of SIAKAD and provides valuable insights for university management to continuously improve the quality of academic systems and services.
Perbandingan Naïve Bayes dan Support Vector Machine pada Klasifikasi Sentimen Tokopedia Di Playstore Igo Fiqi Nurwahid; Untung Subagyo
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.230

Abstract

Tokopedia is one of the largest e-commerce platforms in Indonesia, generating a growing number of user reviews that makes manual sentiment analysis inefficient. This study compares the performance of Naïve Bayes and Support Vector Machine (SVM) in classifying sentiment in Tokopedia application reviews. Data were collected using the google-play-scraper library and automatically labeled based on user ratings, with ratings of 1–2 classified as negative and 4–5 as positive. After preprocessing, including case folding, cleaning, tokenization, stopword removal, and stemming using Sastrawi, 1,212 reviews were obtained, comprising 609 negative and 603 positive reviews. Text features were extracted using TF-IDF, and the models were evaluated using 5-fold cross-validation. With default parameters, Naïve Bayes and SVM achieved accuracies of 75.99% and 74.83%, respectively. After GridSearchCV tuning, Naïve Bayes achieved 76.65% accuracy and 73.28% F1-score, while SVM achieved 77.81% accuracy and 76.51% F1-score. These results show that hyperparameter tuning affects model comparison, with tuned SVM slightly outperforming Naïve Bayes.