cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dwi Puji Hastuti
Contact Email
dwi.dsu@bsi.ac.id
Phone
+6289666044452
Journal Mail Official
ejournal@bsi.ac.id
Editorial Address
https://jurnal.bsi.ac.id/index.php/evolusi/about/editorialHistory
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
EVOLUSI : Jurnal Sains dan Manajemen
Published by Universitas Bina Sarana Informatika
ISSN : 23388161     EISSN : 26570793     DOI : https://doi.org/10.31294/evolusi
Core Subject : Science,
Computer Science & IT
volusi : Jurnal Sains dan Manajemen is a journal published by LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas. Evolusi is issued two times a year (March and September) in electronic form. The electronic pdf version is accessible on the internet free of charge. We encourage all interested contributors to submit their work for consideration. The Journal covers the whole spectrum of applied informatics and computing, which includes, but is not limited to: [1] Soft computing, [2] Information Systems and Technologies, [3] Human Computer Interaction, [4] Soft Computing and Intelligent System, [5] Information Retrieval, [6] Knowledge Engineering, [7] Decision Support System, [8] Fuzzy Systems, [9] Data Mining, [10] Big Data Analysis, [11] Information Security, etc. Submitted papers must be written in Indonesian or English for initial review stage by editors and further review process by minimum two reviewers.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 26 Documents
 1   2   3 
Perancangan Sistem Informasi Penjualan Paket Internet Berbasis Website Untuk Peningkatan Layanan Pada PT Telekomunikasi Seluler Purwokerto Vembria Rose Handayani Vembria; Indriyanti; Sutrisno; Suripah
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 1 (2025): Periode Maret 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i1.8376

Abstract

The development of information technology has had a significant impact on various sectors, including telecommunications. PT Telekomunikasi Seluler Purwokerto is one of the companies engaged in telecommunications services, especially the sale of internet packages. Currently, the sales process still faces obstacles, such as lack of efficiency in transactions and limited information that can be accessed by customers. This study aims to design a website-based internet package sales information system that can make it easier for customers to purchase internet packages, while increasing the efficiency of the company's services. The methodology used in this study is the prototype system development method, which includes the stages of needs analysis, mockup design, and prototype testing. In addition, the data model and process flow are designed using Entity Relationship Diagram (ERD) and Unified Modeling Language (UML) to describe the data structure and system workflow in detail. The results of the study show that the designed system is able to provide easy access to information for customers, simplify the internet package purchase transaction process, increase the company's operational efficiency, and provide fast and accurate transaction reports. In addition, this system can also improve service quality, sales turnover, and expand market reach. Perkembangan teknologi informasi telah memberikan pengaruh signifikan pada berbagai sektor, termasuk telekomunikasi. PT Telekomunikasi Seluler Purwokerto merupakan salah satu perusahaan yang bergerak di bidang layanan telekomunikasi, khususnya penjualan paket internet. Saat ini, proses penjualan masih menghadapi kendala, seperti kurangnya efisiensi dalam transaksi dan keterbatasan informasi yang dapat diakses oleh pelanggan. Penelitian ini bertujuan untuk merancang sistem informasi penjualan paket internet berbasis website yang dapat mempermudah pelanggan dalam melakukan pembelian paket internet, sekaligus meningkatkan efisiensi pelayanan perusahaan. Metodologi yang digunakan dalam penelitian ini adalah metode pengembangan sistem prototype, yang meliputi tahapan analisis kebutuhan, desain mockup, serta pengujian prototype. Selain itu, model data dan alur proses dirancang menggunakan Entity Relationship Diagram (ERD) dan Unified Modeling Language (UML) untuk menggambarkan struktur data dan alur kerja sistem secara terperinci. Hasil penelitian menunjukkan bahwa sistem yang dirancang mampu memberikan kemudahan akses informasi bagi pelanggan, mempermudah proses transaksi pembelian paket internet, meningkatkan efisiensi operasional perusahaan, serta menyediakan laporan transaksi secara cepat dan akurat. Selain itu, sistem ini juga dapat meningkatkan kualitas layanan, omzet penjualan, dan memperluas jangkauan pasar.
Implementasi Framework Cobit 5 pada Audit Sistem Informasi Persediaan PT Kawat Lancar Sejahtera Murni Narti Narti; Hariani; Fuad Nur Hasan; Rangga Pebrianto
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9664

Abstract

Abstract - PT Kawat Lancar Sejahtera Murni has implemented the use of technology to support the storage system of goods in the warehouse, but PT Kawat Lancar Sejahtera Murni has never conducted an persediaan information technology audit to determine whether the system is effective and efficient. PT Kawat Lancar Sejahtera Murni does not have maximum IT control causing losses to the company including loss of goods, inaccuracy due to errors in data processing, so that data integrity is in doubt. Therefore, the analysis and design of the information system audit using the Cobit 5 framework to formulate IT performance and process maturity levels is the basis for making research. The subdomains selected in this study are EDM01, EDM02, EDM03, EDM04, EDM 05, DSS01, DSS03 and DSS04. Based on the calculation results of the EDM01 subdomain 1.01, the EDM02 subdomain has a distance of 0.30, the EDM03 subdomain has a distance of 0.83, the EDM04 subdomain has a distance of 0.33, the EDM05 subdomain has a distance of 0.83, the DSS01 subdomain has a distance of 0.70, the DSS03 subdomain has a distance of 0.63 and in the DSS04 subdomain there is a distance of 0.60. Based on the results of the analysis, several suggestions can be submitted, namely PT Kawat Lancar Sejahtera is advised to consider and implement the recommendations that have been put forward in each subdomain in this study.
Penerapan Algoritma XGBoost Dalam Menganalisa Keberlanjutan Pelanggan Tour dan Travel Ratih Yulia Hayuningtyas; Wina Yusnaeni; Ida Darwati
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9748

Abstract

Customer churn is a term used to describe customer loss in the business world. Customer churn is a major challenge in the business world, impacting every company. One example is the tour and travel industry, the impact of customer churn in tour and travel businesses can include decreased profits and increased operational costs because acquiring tour and travel customers is more expensive than retaining them. Every company has a strategy for customer retention, one of which is implementing machine learning. This study uses public data to determine customer churn using the XGBoost algorithm. Extreme Gradient Boost (XGBoost) works by gradually building a model to improve prediction accuracy. In this study, the XGBoost model works through several stages: data processing, dataset division, algorithm testing, which ultimately results in model accuracy, evaluation, and ROC and AUC curves. The results of this study with the XGBoost model produced an accuracy of 87.7%, precision of 74.4%, recall of 74.4%, F1-Score of 74.4%, and an AUC value of 0.95. In addition, this study also produced an application to predict customers who do not yet have a label
Perancangan Sistem Antrian Online Berbasis Mobile Dengan Notifikasi Real-Time Pada Kantor Kecamatan Wangon Menggunakan Metode Prototype Vembria Rose Handayani Vembria; Galuh Dwi Hanasti; Eva Argarini Pratama
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9751

Abstract

Antrian manual yang panjang dan tidak teratur masih menjadi kendala utama dalam pelayanan publik di berbagai instansi pemerintahan, termasuk di Kantor Kecamatan Wangon. Kondisi ini seringkali menimbulkan ketidaknyamanan, ketidakpastian waktu tunggu, penumpukan antrian, dan penurunan kualitas pelayanan. Penelitian ini bertujuan untuk merancang sebuah sistem antrian online berbasis mobile yang dilengkapi dengan notifikasi real-time yang dapat memudahkan masyarakat dalam melakukan pendaftaran dan memantau antrian secara real-time. Sistem informasi ini dirancang menggunakan metode Prototype, yang memungkinkan pengembangan sistem secara bertahap dan fleksibel sesuai kebutuhan pengguna. Untuk mendeskripsikan alur dan fungsional dalam sistem, digunakan pendekatan pemodelan melalui UML (Unified Modelling Language). Hasil dari perancangan ini menunjukkan bahwa sistem informasi yang dikembangkan dapat mendukung digitalisasi pelayanan publik serta meminimalisir antrain di lokasi pelayanan. Kontribusi utama dari penelitian adalah dengan diterapkannya sistem ini, diharapkan proses pelayanan di Kantor Kecamatan Wangon menjadi lebih tertib, tepat waktu, dapat meningkatkan efisiensi dan kenyamanan pelayanan, serta kualitas pelayanan.
Sistem Manajemen Keuangan Berbasis Website Dengan Metode Agile Endang Retnoningsih; Yunus Fadhillah Soleman; M. Dicky Nur Setya Azi
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9826

Abstract

Every company has regulations in formulating policies related to financial decisions. To minimize risks, financial management must be carried out carefully and thoroughly. Therefore, companies require a dedicated financial management system to support decision-making processes. At PT. Awang Sejahtera Permai (ASP), financial management is currently conducted using Ms. Excel and Zahir application. However, as the company expands and manages multiple business units, there is a need for a financial management system that can accommodate the company’s growing requirements. Hence, this research develops a web-based system to manage cash flow, sales, and financial reports. The system development was carried out using the Agile method. The results of the study indicate that the implementation of the web-based financial management system has a positive impact by integrating cash flow data, sales, and company financial reports.
Evaluasi Metode Naive Bayes dan K-Nearest Neighbors untuk Analisis Sentimen pada Review Aplikasi Duolingo Joko Dwi Mulyanto; Dany Pratmanto; Aprih Widayanto; Pijar Sukma Prayogo; Andi Yoko Satrio
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9937

Abstract

Sentiment analysis is a valuable method for understanding user opinions on digital applications. This study evaluates the performance of the Naive Bayes and K-Nearest Neighbors (KNN) algorithms in classifying sentiments from user reviews of the Duolingo application obtained from the Google Play Store. The dataset consists of 2,000 reviews, comprising 1,000 negative (1-star) and 1,000 positive (5-star) reviews. Preprocessing was conducted in RapidMiner through several stages, including case transformation, tokenization, stopword removal, and stemming, with features represented using TF-IDF. The experimental results show that Naive Bayes achieved an accuracy of 79.96%, recall of 87.76%, precision of 77.21%, and an AUC of 96.40%. Meanwhile, KNN achieved an accuracy of 78.34%, recall of 75.32%, precision of 81.06%, and an AUC of 92.20%. These findings suggest that Naive Bayes outperforms KNN overall, particularly in sensitivity and class separation, while KNN produces more precise positive predictions. Therefore, the choice of algorithm should depend on analysis objectives, whether emphasizing broader sentiment detection or higher precision in positive sentiment classification.
Implementasi Algoritma Model Random Forest, SVM Dan Naive Bayes Untuk Sentimen Analisis Aplikasi Gojek Di Playstore Ai Ilah Warnilah AIW; Melisa Winda Pertiwi MWP; Bambang Kelana Simpony BKY; Vincent Christian VCR; Muhammad Dhafa Alfareza MDA
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.10050

Abstract

Aplikasi Gojek merupakan  satu platform layanan tranfortasi terkemuka di Indonesia. Aplikasi gojek yang mulai berkembang sejak tahun 2010 banyak sekali menerima ulasan dari pengalaman  konsumen (pengguna) terkait dari penggunaan aplikasi ini. Ulasan ini mencerminkan kepuasan terkait penggunaan aplikasi ini berdasarkan hasil dari pengalaman pengguna. Penelitian ini bertujuan untuk mengevaluasi sentiment pengguna terhadap aplikasi Gojek yang sudah diunggah di Playstore dengan menerapkan model mesin learning Random Forest, Support Vector Machine (SVM), dan Naive Bayes. Dataset yang diolah sebanyak 10.000 data yang dianalisis dari tahun 2018 sampai dengan 2025. Dalam periode tahun 2018 hingga 2024, jumlah ulasan pelanggan menunjukkan peningkatan setiap tahunnya. Pada tahun 2025, tercatat sebanyak 2.474 ulasan negatif, 387 ulasan netral, dan 1.502 ulasan positif. SVM menghasilkan nilai akurasi tertinggi 0.7676666666666667 diikuti oleh Random Forest 0. 0.7466666666667 dan Naïve Bayes dengan akurasi 0.7377777723789 Dari hasil nilai akurasi tersebut  menunjukkan bahwa Random Forest memiliki kinerja paling efektif untuk  mengklasifikasikan ulasan sentimen dibandingkan dua model lainnya. Efektivitas model pembelajaran mesin Random Forest, SVM dan Naïve Bayes yang digunakan dalam penelitian ini memberikan wawasan penting terkait kepuasan pengguna terhadap aplikasi Gojek. Informasi ini dapat dimanfaatkan untuk pengambilan keputusan strategis dalam meningkatkan kualitas layanan aplikasi. Dengan menganalisis ulasan , penelitian ini diharapkan dapat memberikan kontribusi dalam mengembangkan inovasi layanan aplikasi gojek yang lebih responsif terhadap kebutuhan dan harapan konsumen
Pemodelan Sistem Informasi Pengaduan Masyarakat (SIPEKA) Berbasis Website dengan Pelacakan Status Laporan untuk Meningkatkan Transparansi Layanan Publik di Kelurahan Arcawinangu yustina Mei Sella; Debita Nur Fitriani; Suripah; Rachmawati Darma Astuti
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.10080

Abstract

Transformasi digital dalam sektor pemerintahan mengharuskan optimalisasi layanan publik, khususnya dalam mengatasi limitasi sistem pengaduan konvensional di Kelurahan Arcawinangun yang bergantung pada kotak saran fisik dengan permasalahan aksesibilitas terbatas, risiko kehilangan dokumen, dan minimnya transparansi progres penanganan. Penelitian ini mengembangkan SIPEKA (Sistem Informasi Pengaduan Masyarakat) sebagai solusi digital berbasis web menggunakan pendekatan prototyping melalui empat fase: analisis kebutuhan stakeholder, konstruksi prototype interface dengan dashboard submission dan modul tracking status, validasi melalui feedback pengguna, dan finalisasi sistem definitif. Platform yang dihasilkan mengakomodasi submission pengaduan online dengan fitur real-time status monitoring, memfasilitasi akses tanpa batasan geografis-temporal sambil menyediakan visibilitas penuh progres penanganan bagi masyarakat dan tools manajemen sistematis bagi administrator. Deployment SIPEKA menghasilkan peningkatan signifikan transparansi dan responsivitas layanan publik melalui digitalisasi workflow pengaduan, dengan integrasi monitoring status yang berkontribusi substansial terhadap penguatan kepercayaan masyarakat pada institusi pelayanan publik Kelurahan Arcawinangun.
Aplikasi Prediksi Diabetes Berbasis Android Menggunakan Algoritma Random Forest dengan SMOTE dan Feature Selection Vadlya Maarif Vadlya; Sardiarinto; Eko Saputro
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.10100

Abstract

Diabetes mellitus merupakan penyakit kronis dengan prevalensi yang terus meningkat secara global, sehingga deteksi dini menjadi aspek penting untuk mencegah komplikasi lebih lanjut. Perkembangan machine learning memberikan peluang signifikan dalam mendukung pengambilan keputusan medis melalui prediksi yang lebih akurat. Penelitian ini bertujuan mengembangkan model prediksi diabetes berbasis algoritma Random Forest yang dipadukan dengan Synthetic Minority Oversampling Technique (SMOTE) serta metode seleksi fitur. Dataset yang digunakan adalah Pima Indians Diabetes Database yang terdiri atas 768 sampel dengan delapan atribut prediktor. Tahapan penelitian meliputi pra-pengolahan data, penerapan SMOTE untuk mengatasi ketidakseimbangan kelas, seleksi fitur berbasis Information Gain, serta evaluasi model menggunakan skema 10-fold cross-validation. Hasil eksperimen menunjukkan bahwa integrasi SMOTE dan seleksi fitur mampu meningkatkan kinerja model dibandingkan baseline, dengan akurasi sebesar 87,93%, nilai recall 91,3% untuk kelas positif, dan area ROC 0,949. Model terbaik kemudian diimplementasikan dalam aplikasi Android berbasis standalone yang memungkinkan pengguna melakukan prediksi risiko diabetes secara mandiri melalui input tujuh atribut utama, yaitu Glucose, Pregnancies, Age, BMI, Insulin, Diabetes Pedigree Function, dan Blood Pressure. Aplikasi ini menghasilkan prediksi yang cepat, mudah diakses, serta berpotensi menjadi solusi praktis untuk mendukung upaya deteksi dini diabetes.
Sistem Pakar untuk Deteksi Penyakit Jantung dengan Optimasi Parameter Metode Klasifikasi C4.5 Hidayat Muhammad Nur; Elly Muningsih; Sutrisno
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.11260

Abstract

Heart disease is the leading cause of death worldwide and a chronic disease with significant risks. According to the 2022 Basic Health Research (Riskesdas), heart disease cases in Indonesia reached more than 15 million. Many patients are unaware of the early symptoms of heart disease until serious complications such as heart attacks or heart failure develop. To facilitate early detection, a system capable of predicting heart disease risk quickly and accurately is needed. The aim of this research is to create an expert system that can identify heart disease using the Decision Tree (C4.5) classification summary and optimize parameters to achieve the highest level of accuracy. Several important C4.5 algorithm parameters, including criteria, maximum depth, and pruning, as well as the number of folds in Cross-Validation, were optimized. The Kaggle Heart Disease dataset, which has 500 entries and seven characteristics (including one unique attribute), served as the source dataset. Data preprocessing, model training, and accuracy measurements both before and after optimization are all steps in the research process. Comparing the accuracy figures obtained before and after optimization is how the evaluation is conducted. The research shows that the accuracy value was around 70.00% before optimization and increased to 78.00% after optimization.

Page 2 of 3 | Total Record : 26

 1   2   3 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 1 (2026): Periode Maret 2026 Vol. 13 No. 2 (2025): Periode September 2025 Vol. 13 No. 1 (2025): Periode Maret 2025