Garuda - Garba Rujukan Digital

Perancangan Sistem Penerimaan Material Barang Masuk Berbasis Power Apps Pada Situs Crop Science Manufaktur Erick Harlest Budi R
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 1 (2026): Januari
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i1.441

Abstrak: Penelitian ini membahas perancangan sistem penerimaan material barang masuk pada situs Crop Science manufaktur dengan memanfaatkan teknologi Power Apps sebagai platform pengembangan aplikasi yang menyediakan komponen visual dan low code untuk integrasi otomatis. Tujuan utama penelitian adalah membangun sistem informasi yang mampu meningkatkan akurasi pencatatan, mempercepat proses verifikasi, serta mempermudah integrasi data dengan unit operasional terkait. Metode yang digunakan meliputi analisis kebutuhan, perancangan model sistem, dan implementasi prototipe berbasis aplikasi. Hasil perancangan menunjukkan bahwa sistem mampu mengurangi kesalahan pencatatan dan mempercepat alur persetujuan material masuk. Kesimpulannya, penerapan sistem informasi berbasis Power App dapat mendukung efisiensi operasional manufaktur dan menjadi solusi praktis untuk pengelolaan material di lokasi produksi.Kata kunci: Perancangan Sistem, Sistem Informasi, manufaktur, Power AppAbstract: This study discusses the design of a material receiving system for incoming goods at the Crop Science manufacturing site by utilizing Power Apps technology as an application development platform that provides visual components and low-code capabilities for automatic integration. The main objective of the research is to build an information system that can improve recording accuracy, accelerate the verification process, and facilitate data integration with related operational units. The methods used include needs analysis, system model design, and application-based prototype implementation. The design results show that the system can reduce recording errors and speed up the approval flow of incoming materials. In conclusion, the implementation of a Power Apps–based information system can support manufacturing operational efficiency and serve as a practical solution for material management at the production site.Keywords: System Design, Information System, Manufacturing, Power App

Implementasi Bayesian Optimization untuk Meningkatkan Akurasi Prediksi Penjualan Menggunakan Algoritma XGBoost (Studi Kasus: CV XYZ) Nendi Setiawan; Hadi Zakaria
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 1 (2026): Januari
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i1.410

Abstrak: CV. XYZ merupakan perusahaan percetakan daring yang menghadapi tantangan dalam memprediksi penjualan akibat fluktuasi permintaan dan keterbatasan metode analisis yang digunakan. Prediksi penjualan yang tidak akurat dapat menyebabkan ketidakseimbangan produksi dan menurunkan efisiensi operasional. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi penjualan dengan mengimplementasikan model Extreme Gradient Boosting (XGBoost) yang dioptimalkan menggunakan Bayesian Optimization. XGBoost dipilih karena kemampuannya dalam menangani data kompleks dan nonlinier, sedangkan Bayesian Optimization digunakan untuk menyempurnakan pemilihan hiperparameter secara efisien. Kebaruan penelitian ini terletak pada integrasi Bayesian Optimization sebagai strategi tuning hiperparameter XGBoost untuk prediksi penjualan pada sektor percetakan digital. Data historis penjualan dianalisis menggunakan bahasa pemrograman Python dengan SQLite sebagai basis penyimpanan data. Hasil eksperimen menunjukkan bahwa kombinasi kedua metode tersebut mampu meningkatkan performa prediksi secara signifikan, dengan nilai RMSE sebesar 8.366,6, MAE sebesar 8.000, dan skor R² sebesar 0,9748. Pendekatan ini memberikan solusi praktis bagi CV. XYZ dalam meningkatkan perencanaan produksi serta pengambilan keputusan berbasis data di sektor percetakan digital.Kata kunci: prediksi penjualan, XGBoost, Bayesian Optimization, Machine LearningAbstract: CV. XYZ is an online printing company that faces challenges in predicting sales due to demand fluctuations and limitations in the analytical methods employed. Inaccurate sales predictions can lead to production imbalances and reduced operational efficiency. This study aims to improve sales prediction accuracy by implementing an Extreme Gradient Boosting (XGBoost) model optimized using Bayesian Optimization. XGBoost is selected for its capability to handle complex and non-linear data, while Bayesian Optimization is employed to efficiently optimize hyperparameter selection. The novelty of this study lies in the integration of Bayesian Optimization as a hyperparameter tuning strategy for the XGBoost model in sales prediction within the digital printing sector. Historical sales data are analyzed using Python, with SQLite utilized as the data storage system. Experimental results demonstrate that the proposed approach significantly improves prediction performance, achieving an RMSE of 8,366.6, an MAE of 8,000, and an R² score of 0.9748. This approach provides a practical solution for CV. XYZ in enhancing production planning and data-driven decision-making in the digital printing industry.Keywords: sales forecasting, XGBoost, Bayesian Optimization, Machine Learning

Prediksi Kecepatan Angin Menggunakan Gated Recurrent Unit (GRU) dengan Estimasi Ketidakpastian Monte Carlo Dropout pada Data BMKG Tanjung Perak Alvino Hadiyan Pradipta; Muhammad Rafli Feandika Nugroho; Maretta Fairuz Luthfia Winoto Putri; Alfan Rizaldy Pratama; Shindi Shella May Wara; Muhammad Nasrudin
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.491

Abstrak: Keterbatasan metode prediksi konvensional dalam memodelkan dependensi temporal dan ketidakpastian prediksi mendorong pengembangan pendekatan berbasis deep learning. Penelitian ini bertujuan mengembangkan model prediksi kecepatan angin menggunakan metode Gated Recurrent Unit (GRU) pada data meteorologi yang berasal dari stasiun pengamatan BMKG Tanjung Perak. Penelitian ini dilakukan karena metode prediksi sebelumnya masih memiliki keterbatasan dalam menangkap pola temporal dan dependensi jangka panjang pada data time series, serta umumnya belum mengakomodasi ketidakpastian hasil prediksi. GRU dipilih karena mampu memodelkan dependensi temporal secara efisien, sedangkan simulasi Monte Carlo digunakan untuk menghasilkan beberapa skenario prediksi dan mengestimasi interval kepercayaan. Data yang digunakan mencakup parameter kecepatan angin dengan interval waktu tertentu. Hasil evaluasi menunjukkan bahwa model menunjukkan performa yang baik untuk memprediksi kecepatan angin secara akurat, dengan nilai MAE sebesar 0,37, RMSE sebesar 0,50, MAPE sebesar 5,78%, dan R² sebesar 0,986. Dengan demikian, model yang dikembangkan dapat menjadi solusi dalam analisis dan peramalan data time series meteorologi secara komprehensif.Kata kunci: Prediksi Kecepatan Angin, Analisis Time Series, Gated Recurrent Unit (GRU), Simulasi Monte Carlo, Data MeteorologiAbstract: The limitations of conventional forecasting methods in modeling temporal dependencies and forecast uncertainty have driven the development of deep learning-based approaches. This study aims to develop a wind speed forecasting model using the Gated Recurrent Unit (GRU) method on meteorological data from the BMKG Tanjung Perak observation station. This study was conducted because previous prediction methods still have limitations in capturing temporal patterns and long-term dependencies in time series data, and generally do not accommodate the uncertainty of prediction results. GRU was chosen because it is capable of modeling temporal dependencies efficiently, while Monte Carlo simulation was used to generate several prediction scenarios and estimate confidence intervals. The data used includes wind speed parameters at specific time intervals. The evaluation results show that the model shows good performance in predicting wind speed accurately, with an MAE of 0.37, an RMSE of 0.50, a MAPE of 5.78%, and an R² of 0.986. Thus, the developed model can serve as a solution for comprehensive analysis and forecasting of meteorological time series data.Keywords: Wind Speed Prediction, Time Series Analysis, Gated Recurrent Unit (GRU), Monte Carlo Simulation, Meteorological Data

Peran Machine Learning Dalam E-Commerce: Tinjauan Literatur Sistematis Terhadap Penerapan Dan Tantangan Sri Murdiawati; Amri Reza Wahyudin; Juan Adi Putra; Ryan Randy Suryono
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.448

Abstrak: Perkembangan e-commerce menghasilkan banyak data yang besar dan rumit, sehingga membutuhkan teknologi canggih untuk membantu pengambilan keputusan dan meningkatkan pelayanan. Machine learning menjadi cara utama yang digunakan karena kemampuannya untuk mempelajari pola perilaku pengguna dan transaksi secara otomatis. Penelitian ini menganalisis penerapan machine learning dalam e-commerce dengan menggunakan metode Systematic Literature Review (SLR) terhadap 20 artikel jurnal dari dalam dan luar negeri. Kebaruan penelitian ini terletak pada sistesis yang menggabungkan berbagai aspek seperti bidang penerapan, metode algoritma, cara mengukur kinerja, tantangan teknis, serta dampak bisnis dalam satu kerangka analisis yang terstruktur. Hasil penelitian menunjukkan bahwa machine learning memiliki peran penting dalam sistem rekomendasi, analisis sentimen, mendeteksi penipuan, serta memprediksi penjualan, meskipun masih menghadapi tantangan seperti kualitas data, kebutuhan komputasi yang besar, dan kemampuan menjelaskan hasil.Kata Kunci: e-commerce; machine learning; systematic literature review; sistem rekomendasi.Abstract: The development of e-commerce has generated large amounts of complex data, requiring advanced technology to aid decision-making and improve services. Machine learning has become the primary method used due to its ability to automatically learn patterns of user behavior and transactions. This study analyzes the application of machine learning in e-commerce using the Systematic Literature Review (SLR) method on 20 journal articles from within and outside the country. The novelty of this research lies in its synthesis, which combines various aspects such as fields of application, algorithm methods, performance measurement methods, technical challenges, and business impacts into a single structured analytical framework. The results show that machine learning plays an important role in recommendation systems, sentiment analysis, fraud detection, and sales prediction, despite still facing challenges such as data quality, large computational requirements, and the ability to explain results.Keywords: e-commerce; machine learning; systematic literature review; recommendation system

Sentiment Analysis of BPJS Kesehatan Application Reviews Using Optimized XGBoost and Support Vector Machine Muhammad Syafiq; Chandra Kirana; Delpiah Wahyuningsih
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.480

This study addresses a critical gap in automated public service evaluation by systematically comparing the performance of XGBoost and Support Vector Machine (SVM) for sentiment classification of BPJS Kesehatan application reviews. Unlike prior research that predominantly relies on default model configurations or single-algorithm frameworks, this study introduces a rigorously optimized comparative pipeline using GridSearchCV with k-fold cross-validation, specifically designed to address hyperparameter sensitivity and class imbalance in Indonesian digital health feedback. User reviews were extracted from the Google Play Store, preprocessed using a standardized NLP pipeline, and vectorized via TF-IDF. Analytical results reveal that while SVM achieves marginally higher overall accuracy (90.5%) through optimal hyperplane separation, it completely fails to classify neutral sentiments (F1-score = 0.00), highlighting its vulnerability to minority-class underrepresentation. In contrast, XGBoost (89.75% accuracy) demonstrates superior multi-class equilibrium, leveraging ensemble regularization to effectively capture ambiguous and neutral expressions. The systematic integration of GridSearchCV significantly improves generalization, validating hyperparameter optimization as a critical determinant of model robustness in real-world textual data. Scientifically, this study advances methodological understanding by demonstrating the trade-offs between margin-based strictness and ensemble adaptability under exhaustive optimization, providing a reproducible framework for imbalanced sentiment classification. Practically, it offers public health administrators a scalable, data-driven mechanism for real-time service quality monitoring and user satisfaction analytics.Keywords: Sentiment Analysis; XGBoost; Support Vector Machine

Evaluasi Kinerja Algoritma Naive Bayes, Decision Tree, dan Random Forest untuk Prediksi Risiko Default Nasabah Kartu Kreditult Nasabah Kartu Kredit Turlia Indah Sapitri; Tia Dwi Anggra Yani; Jelna Anggreni; Erliyan Redi Susanto
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.449

Abstrak: Prediksi risiko gagal bayar (default) nasabah kartu kredit merupakan aspek penting dalam manajemen risiko kredit pada lembaga keuangan. Berbagai penelitian telah menerapkan algoritma klasifikasi untuk prediksi risiko kredit, namun sebagian besar penelitian hanya berfokus pada satu atau dua algoritma sehingga hasil perbandingan performa antar metode masih terbatas. Penelitian ini bertujuan untuk mengevaluasi dan membandingkan kinerja algoritma Naive Bayes, Decision Tree, dan Random Forest dalam memprediksi risiko default nasabah kartu kredit. Dataset yang digunakan merupakan data sekunder dari platform Kaggle yang terdiri dari 30.000 data nasabah. Tahapan penelitian meliputi preprocessing data, pembagian training dan testing dengan rasio 80:20, pembangunan model klasifikasi, serta evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Kontribusi penelitian ini terletak pada evaluasi komparatif tiga algoritma klasifikasi dalam satu kerangka eksperimen yang sama menggunakan pendekatan evaluasi multi-metrik. Hasil penelitian menunjukkan bahwa Random Forest menghasilkan kinerja terbaik berdasarkan nilai accuracy sebesar 0,813500 dan precision sebesar 0,630027. Sementara itu, Naive Bayes memperoleh nilai recall tertinggi sebesar 0,651181 dan F1-score sebesar 0,494363. Temuan penelitian menunjukkan bahwa Random Forest lebih unggul dalam ketepatan klasifikasi, sedangkan Naive Bayes lebih efektif dalam mendeteksi nasabah yang berpotensi mengalami gagal bayar.Kata kunci: Credit Risk Assessment, Kartu Kredit, Prediksi Risiko Kredit, Naive Bayes, Decision Tree, Random ForestAbstract: Credit card default risk prediction is an important aspect of credit risk management in financial institutions. Although various classification algorithms have been applied to credit risk prediction, most previous studies have focused on only one or two algorithms, resulting in limited comparative insights into their performance. This study aims to evaluate and com-pare the performance of Naive Bayes, Decision Tree, and Random Forest algorithms in pre-dicting credit card customer default risk. The dataset used in this study is secondary data ob-tained from Kaggle, consisting of 30,000 customer records. The research process includes data preprocessing, dataset splitting into training and testing sets with an 80:20 ratio, clas-sification model development, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The contribution of this study lies in the comparative evaluation of three classification algorithms within the same experimental framework using a multi-metric evaluation approach. The results indicate that Random Forest achieved the best overall per-formance with an accuracy of 0.813500 and a precision of 0.630027. Meanwhile, Naive Bayes obtained the highest recall of 0.651181 and the highest F1-score of 0.494363. These findings suggest that Random Forest is more effective in overall classification performance, whereas Naive Bayes is better at identifying customers with a higher likelihood of default.Keywords: Credit Risk Assessment, Credit Card, Credit Risk Prediction, Naive Bayes, Decision Tree, Random Forest

Sistem Pendukung Keputusan Evaluasi Kepuasan Peserta Pelatihan E-Commerce Berbasis TOPSIS Kumara Davin Valerian; Wahyu Hadikristanto; Nanang Tedi Kurniadi
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.474

Abstrak: Perkembangan teknologi digital, khususnya e-commerce, menuntut peningkatan kompetensi sumber daya manusia melalui pelatihan yang terarah dan berkualitas. Selain aspek pelaksanaan, keberhasilan pelatihan perlu diukur melalui evaluasi kepuasan peserta secara objektif berdasarkan berbagai kriteria penilaian. Meskipun metode sistem pendukung keputusan telah banyak diterapkan pada berbagai bidang evaluasi, penerapannya pada evaluasi kepuasan peserta pelatihan e-commerce masih relatif terbatas. Penelitian ini bertujuan untuk mengevaluasi kepuasan peserta pelatihan e-commerce menggunakan metode TOPSIS. Kebaruan penelitian ini terletak pada penerapan evaluasi kepuasan berbasis multi-kriteria menggunakan skala likert dan metode TOPSIS pada konteks pelatihan e-commerce, yang belum banyak dibahas pada penelitian sebelumnya. Data diperoleh melalui observasi, studi literatur, dan penyebaran kuesioner kepada 56 responden. Hasil pengolahan menunjukkan nilai preferensi berada pada rentang 0,28 hingga 1,00. Sebanyak 13 alternatif memperoleh nilai preferensi tertinggi sebesar 1,00, sedangkan alternatif ke-51 memperoleh nilai terendah sebesar 0,28. Hasil penelitian menunjukkan bahwa model evaluasi berbasis TOPSIS mampu menghasilkan pemeringkatan kepuasan peserta secara objektif dan terukur, sehingga berkontribusi dalam meningkatkan akurasi pengambilan keputusan pada evaluasi pelatihan e-commerce.Kata kunci: Sistem Pendukung Keputusan, Kepuasan Peserta, Pelatihan E-Commerce, TOPSIS, KuesionerAbstract: The development of digital technology, particularly e-commerce, demands increased human resource competency through targeted and quality training. In addition to implementation aspects, training success needs to be measured through objective participant satisfaction evaluation based on various assessment criteria. Although decision support system methods have been widely applied in various evaluation fields, their application to e-commerce training participant satisfaction evaluation is still relatively limited. This study aims to evaluate e-commerce training participant satisfaction using the TOPSIS method. The novelty of this study lies in the application of multi-criteria-based satisfaction evaluation using a Likert scale and the TOPSIS method in the context of e-commerce training, which has not been widely discussed in previous studies. Data were obtained through observation, literature review, and questionnaire distribution to 56 respondents. The results showed that preference values ranged from 0.28 to 1.00. A total of 13 alternatives obtained the highest preference value of 1.00, while the 51st alternative obtained the lowest value of 0.28. The results show that the TOPSIS-based evaluation model is able to produce objective and measurable participant satisfaction rankings, thus contributing to improving the accuracy of decision-making in e-commerce training evaluation.Keywords: Decision Support System, Participant Satisfaction, E-Commerce Training, TOPSIS, Questionnaire

XGBoost-Based Sentiment Analysis for Evaluating Customer Satisfaction at Hotel Puri Ansel Thalia Puspita Sari; Chandra Kirana; Delpiah Wahyuningsih
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.484

While sentiment analysis is increasingly applied in hospitality research, existing studies predominantly rely on large, balanced datasets from global platforms or computationally intensive deep learning models that lack interpretability for local hotel management. A critical research gap remains in deploying lightweight, interpretable machine learning frameworks on small, highly imbalanced Indonesian hotel reviews while translating sentiment outputs into actionable operational insights. To address this gap, this study evaluates customer satisfaction at Hotel Puri Ansel using an XGBoost-based sentiment classification pipeline optimized for real-world data constraints. Google Reviews were processed through comprehensive Indonesian text preprocessing and TF-IDF feature extraction, then partitioned into 80% training and 20% testing sets. The XGBoost model achieved 84% accuracy and a 0.83 weighted F1-score, demonstrating exceptional positive sentiment recall (97%). Lexical analysis identified “cleanliness” and “comfort” as primary satisfaction drivers, whereas “hygiene issues” and “slow service” dominated negative feedback. Although the model exhibited limitations with ambiguous and sarcastic expressions, its novelty lies in bridging technical classification performance with interpretable business intelligence. This study contributes a reproducible, resource-efficient framework that enables local hospitality operators to leverage unstructured review data for targeted service improvements, prioritizing practical deployment validity over artificial data balancing.Keywords: Sentiment Analysis, XGBoost, Hotel Service Quality

Pembangunan Game Edukasi Numerasi Berbasis Android Menggunakan Algoritma Fisher-Yates Shuffle Fahmi Abdullah; Renzi Thalia; Aisya Khotimatul Aula
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.475

Abstrak: Kemampuan numerasi menjadi salah satu kompetensi dasar yang dibutuhkan siswa dalam menghadapi kehidupan sehari-hari. Namun, berdasarkan Programme for International Student Assessment (PISA) 2022, kemampuan numerasi siswa di Indonesia masih rendah. Kondisi serupa terjadi di SDN Toblong 2, di mana pembelajaran masih menggunakan metode konvensional dengan soal yang monoton sehingga menurunkan motivasi belajar siswa. Penelitian ini bertujuan menghadirkan solusi berbasis teknologi berupa media pembelajaran ke dalam game edukasi berbasis Android menggunakan algoritma Fisher-Yates Shuffle untuk menghasilkan variasi soal secara acak sekaligus meningkatkan keterlibatan siswa melalui gamifikasi. Metode yang digunakan adalah Game Development Life Cycle (GDLC) dengan materi bilangan, aljabar, geometri, dan pengukuran untuk siswa kelas 5. Pengujian dilakukan melalui kuesioner dan wawancara. Hasil menunjukkan aplikasi efektif membantu pemahaman siswa dengan tingkat persetujuan 89,06%, meningkatkan tantangan belajar sebesar 87,33%, serta meningkatkan motivasi siswa sebesar 90,00%. Berdasarkan hasil tersebut bahwa game edukasi menggunakan algoritma shuffle menjadi media pembelajaran alternatif yang lebih efektif, tidak mudah bosan, dan memotivasi siswa.Kata kunci: Game Edukasi, Numerasi, Android, Algoritma Fisher Yates Shuffle, Gamifikasi.Abstract: Numeracy skills are one of the core competencies students need to navigate daily life. However, according to the Programme for International Student Assessment (PISA) 2022, students’ numeracy skills in Indonesia remain low. A similar situation exists at SDN Toblong 2, where instruction still relies on conventional methods with monotonous problems, thereby reducing students’ motivation to learn. This study aims to provide a technology-based solution in the form of educational content integrated into an Android-based educational game using the Fisher-Yates Shuffle algorithm to generate random variations of questions while enhancing student engagement through gamification. The method used is the Game Development Life Cycle (GDLC) with content covering numbers, algebra, geometry, and measurement for 5th-grade students. Testing was conducted via questionnaires and interviews. The results show that the application effectively aids student understanding with an approval rate of 89.06%, increases the challenge of learning by 87.33%, and boosts student motivation by 90.00%. Based on these results, educational games using the shuffle algorithm serve as a more effective alternative learning medium that is less likely to cause boredom and motivates students.Keywords: Educational Games, Numeracy, Android, Fisher-Yates Shuffle Algorithm, Gamification

Prediksi Risiko Penyakit Stroke Menggunakan Logistic Regression Dengan Dashboard Interaktif Aldillah Aldillah; Khairunnas .; Irma Eryanti Putri
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 2 (2026): Juli
Publisher : Institut Teknologi Gamalama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i2.485

Abstrak: Stroke merupakan salah satu penyebab utama kematian dan kecacatan jangka panjang di dunia. Peningkatan kasus stroke mendorong pemanfaatan teknologi machine learning untuk membantu prediksi risiko penyakit secara cepat dan akurat. Penelitian sebelumnya telah menggunakan algoritma seperti Support Vector Machine dan Random Forest, namun sebagian besar masih berfokus pada performa model dan belum mengintegrasikan hasil prediksi dalam media visual yang interaktif. Penelitian ini bertujuan membangun model prediksi risiko stroke menggunakan algoritma Logistic Regression serta mengimplementasikannya dalam dashboard interaktif. Dataset yang digunakan berasal dari Kaggle dengan jumlah data sebanyak 5110. Tahapan penelitian meliputi preprocessing data, pembagian data latih 80% dan data uji 20%, serta pelatihan model menggunakan Logistic Regression. Hasil penelitian menunjukkan model memperoleh akurasi sebesar 92% dan ROC-AUC sebesar 84%. Dashboard interaktif yang dikembangkan mampu menampilkan probabilitas risiko stroke dan variabel yang berpengaruh sehingga membantu pengguna memahami hasil prediksi secara lebih efektif.Kata kunci: Data Mining; Logistic Regression; StrokeAbstract: Stroke is one of the leading causes of death and long-term disability worldwide. The rise in stroke cases has driven the use of machine learning technology to help predict disease risk quickly and accurately. Previous research has employed algorithms such as Support Vector Machines and Random Forests; however, most studies have focused primarily on model performance and have not integrated prediction results into interactive visual media. This study aims to build a stroke risk prediction model using the Logistic Regression algorithm and implement it in an interactive dashboard. The dataset used comes from Kaggle, containing 5,110 data points. The research stages include data preprocessing, splitting the data into an 80% training set and a 20% test set, and training the model using Logistic Regression. The results show that the model achieved an accuracy of 92% and an ROC-AUC of 84%. The developed interactive dashboard displays stroke risk probabilities and influencing variables, helping users understand the prediction results more effectively..Keywords: Data Mining, Logistic Regression, Stroke

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
muhdar

Contact Email
jilkominfo.aikom@gmail.com

Phone
-

Journal Mail Official
jilkominfo.aikom@gmail.com

Editorial Address
-

Location
Kota ternate,

Maluku utara

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name muhdar

Contact Email jilkominfo.aikom@gmail.com

Phone -

Journal Mail Official jilkominfo.aikom@gmail.com

Editorial Address -

Location Kota ternate, Maluku utara INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
muhdar

Contact Email
jilkominfo.aikom@gmail.com

Phone
-

Journal Mail Official
jilkominfo.aikom@gmail.com

Editorial Address
-

Location
Kota ternate,

Maluku utara

INDONESIA