Jurnal Ilmu Komputer, Teknologi Dan Informasi

Analisis Faktor Penerimaan TikTok Go sebagai Layanan E-voucher Berbasis Modifikasi UTAUT2 dengan Metode PLS-SEM

Amira Aurelia Salsabila, Daniel Arsa, Miranty Yudistira — Fri, 17 Jul 2026 00:00:00 +0000

TikTok, as the fastest-growing social media platform in Indonesia, launched the TikTok Go service in February 2025. However, despite TikTok's massive user base in Indonesia, the market penetration of TikTok Go remains very low, at approximately 0.4% compared to 20% in the Chinese market. This low adoption rate potentially hinders service development, reduces platform revenue potential, limits incentives for content creators, and threatens the sustainability of partnerships with merchants. This phenomenon is supported by user review findings regarding various operational issues, such as technical glitches where barcodes fail to appear, data inconsistencies in product availability between merchants and the platform, and limited purchasing features in certain locations. This study aims to analyze the factors influencing user acceptance of TikTok Go by integrating a modified UTAUT 2 model. Data were collected through questionnaires from 180 respondents in Indonesia who have made at least two e-voucher purchases. The analysis was conducted using Partial Least Squares-Structural Equation Modeling (PLS-SEM) to test the structural and measurement models. The results indicate that Facilitating Conditions and Price Value significantly influence Purchase Intention. Furthermore, Habit and Purchase Intention significantly affect Use Behavior, while Social Commerce Construct plays a crucial role in enhancing User Trust. These findings confirm that strengthening facility support, optimizing pricing strategies, and fostering user habits are key drivers for increasing service adoption. Consequently, this study provides strategic recommendations for platform management to optimize facility support, pricing strategies, and engagement programs to enhance TikTok Go service adoption in Indonesia.

Implementasi Autoregressive Integrated Moving Average untuk Prediksi Pasien Rumah Sakit Berbasis Dashboard Interaktif

Amelia amel Contesa — Fri, 17 Jul 2026 00:00:00 +0000

A major challenge in healthcare service management is the uncertainty of patient arrivals during each service period. Fluctuations in patient visits can affect the effectiveness of human resource planning, healthcare facility allocation, pharmaceutical inventory management, and the overall quality of services provided to the community. Therefore, an approach capable of accurately predicting the number of patients is required to support more effective decision-making processes. This study aims to implement the Autoregressive Integrated Moving Average (ARIMA) method to predict hospital patient visits and integrate the forecasting results into a web-based interactive dashboard. The dataset used in this study was obtained from a Kaggle repository containing daily patient visit records from healthcare facilities in India. The daily data were transformed into monthly data through a temporal aggregation process to generate a more stable time series suitable for forecasting modeling. The forecasting model employed was ARIMA (2,1,0), while the system was developed using Google Apps Script as the development platform and Chart.js as the data visualization component. The results indicate that the total number of patient visits during the observation period reached 11,934 patients, with an average of 442 patients per month. The ARIMA model predicted 727 patient visits for the subsequent period, indicating an increasing trend. The main contribution of this study lies in the integration of a forecasting model and an interactive dashboard within a single system capable of presenting statistical information, trend visualizations, and forecasting results in real time to support decision-making in healthcare management. The findings demonstrate that the proposed approach can serve as an effective data-driven tool for hospital operational planning and resource management.

Penerapan Algoritma Naive Bayes Untuk Klasifikasi Kelayakan Penerima Beasiswa Berdasarkan Data Sosial Ekonomi Mahasiswa

Kevin Rasi Dauly, Jaya Tata Hardinata, Togi Lumbantobing, Rahul Sinurat — Fri, 17 Jul 2026 00:00:00 +0000

Scholarship programs are one of the efforts made by universities to improve educational quality while supporting students with limited economic conditions. The scholarship selection process generally considers various socio-economic factors, including parents' income, number of family dependents, Grade Point Average (GPA), ownership of the Indonesia Smart Card (KIP), and housing status. In practice, the selection process is still largely performed manually, which is time-consuming, prone to recording errors, and potentially less objective because it depends on the subjective judgment of the staff involved. This condition highlights the need for a computational approach that can support faster, more consistent, and measurable decision-making. This study aims to implement the Naive Bayes algorithm, a probability-based classification method that works based on Bayes' Theorem with the assumption of conditional independence among attributes, to classify scholarship eligibility based on students' socio-economic data. The research method consists of five main stages: data collection, data preprocessing (handling missing values, duplicate records, and categorical attribute transformation), dataset splitting using the Hold-Out Validation method with a composition of 80% training data and 20% testing data, model training using the Naive Bayes algorithm implemented with the Scikit-learn library, and performance evaluation using a Confusion Matrix. The dataset consists of 200 student records with seven attributes, namely parents' income, number of dependents, GPA, housing status, KIP ownership, semester level, and eligibility status. The results show that the Naive Bayes algorithm is able to classify scholarship eligibility with an Accuracy of 92.50%, Precision of 95.65%, Recall of 91.67%, and F1-Score of 93.62%. These results confirm that the Naive Bayes algorithm can be used as a decision support method to make the scholarship selection process faster, more objective, and more efficient than manual selection.

Perancangan Sistem Informasi Administrasi Rukun Tetangga Berbasis Web Menggunakan Metode Scrum

Fri, 17 Jul 2026 00:00:00 +0000

The manual management of population administration at the Rukun Tetangga (RT) level causes significant inefficiencies, including slow data retrieval, physical document duplication, and a lack of transparency in social assistance distribution. This study aims to design and implement a web-based RT administration information system named BISAKELOLA at RT 14, Kenali Asam, Jambi City, which integrates resident data management and social assistance management into a single platform. The system was developed using the Scrum method through three iterative sprints, with data collected through direct observation, interviews, and literature review, and validated using Black Box Testing based on the Equivalence Partitioning technique. BISAKELOLA successfully centralized resident data, accelerated information retrieval, eliminated physical document duplication of family cards and identity cards, and digitalized the social assistance submission process into a more transparent workflow. All test scenarios across four main modules, namely authentication, resident data, social assistance, and account management, performed as expected without critical errors. Sprint reviews conducted at the end of each sprint proved effective in adaptively accommodating user requirement changes, resulting in a system that is functionally aligned with real community needs. BISAKELOLA proves to be an effective digital solution for modernizing RT administrative services and improving social assistance transparency, and is expected to serve as a replicable model for community-level digitalization across other RT/RW environments in Jambi City.

Perbandingan Kinerja Random Forest, Decision Tree, dan Naive Bayes Menggunakan Metode 10-Fold Cross Validation untuk Prediksi Status Akademik Mahasiswa

Jeprinus Purba, Rahul Sinurat — Fri, 24 Jul 2026 00:00:00 +0000

Predicting students' academic status is an important effort that higher education institutions can undertake to identify students who are at risk of experiencing academic decline, delayed graduation, or dropout. Early identification enables institutions to provide appropriate academic and non-academic interventions, thereby improving student retention and graduation rates. This study aims to compare the performance of the Random Forest, Decision Tree, and Naive Bayes algorithms in predicting students' academic status using the Predict Students Dropout and Academic Success dataset obtained from the UCI Machine Learning Repository. The dataset consists of 4,424 student records with 36 predictor attributes and three target classes: Dropout, Enrolled, and Graduate. The research methodology includes data exploration, feature selection, model development using Orange Data Mining, and model evaluation through the 10-Fold Cross Validation method. Model performance was assessed using Accuracy, Precision, Recall, F1-Score, Area Under the Curve (AUC), Matthews Correlation Coefficient (MCC), Confusion Matrix, and ROC Curve. The experimental results indicate that the Random Forest algorithm achieved the best performance, with an Accuracy of 77.4%, Precision of 0.760, Recall of 0.774, F1-Score of 0.759, AUC of 0.897, and MCC of 0.624, outperforming both Decision Tree and Naive Bayes. This study contributes a comparative evaluation of three widely used classification algorithms on a publicly available higher education dataset and demonstrates that Random Forest is the most effective algorithm for supporting accurate and reliable student academic status prediction systems.

Analisis Klasifikasi Penyakit Ginjal Kronis Menggunakan Algoritma K-Nearest Neighbor dan Random Forest Berbasis Orange Data Mining

Rahul Sinurat, Kevin Rasi Dauly Pardede, Jeprinus Purba — Fri, 24 Jul 2026 00:00:00 +0000

Chronic Kidney Disease (CKD) is a global health problem with morbidity rates that continue to increase from year to year. The main challenge in the medical management of CKD is delayed diagnosis due to early symptoms that are often unnoticed by patients, thereby requiring rapid, objective, and accurate detection methods. This study aims to analyze and compare the performance of two popular classification algorithms, K-Nearest Neighbor (kNN) and Random Forest, in classifying chronic kidney disease status. Experiments were conducted using Orange Data Mining software by utilizing a patient clinical medical record dataset. The model evaluation was rigorously tested using the 10-Fold Cross Validation method to ensure the validity of the results. The main contribution of this study is to present an in-depth comparative analysis regarding the evaluation metrics of ensemble trees compared to distance-based approaches to minimize the risk of missed diagnosis in clinical decisions. The results showed that the Random Forest algorithm produced the best and superior performance with an accuracy rate (Accuracy) reaching 99.0%, a Precision value of 99.3%, and an AUC value of 0.999. Conversely, the K-Nearest Neighbor algorithm obtained a lower accuracy rate of 96.0% with an AUC of 0.994. These findings indicate that the ensemble tree approach is more adaptive in handling clinical data characteristics, and has great potential to be integrated as a clinical decision support system for medical personnel in hospitals.

Prediksi Risiko Penyalahgunaan Narkoba pada Remaja Menggunakan Algoritma Random Forest Berdasarkan Faktor Sosial, Demografis, dan Lingkungan

Bryan Yohan Manalu — Fri, 24 Jul 2026 00:00:00 +0000

Drug abuse among adolescents is a highly complex social and public health problem, influenced by multifactorial interactions between social, demographic, psychological, and environmental factors. Current prevention efforts are generally generalist and educational in nature, thus significantly limiting their ability to identify individuals with specific risk vulnerabilities early. Furthermore, existing predictive models often rely on costly and time-consuming clinical measurement instruments, making them difficult to implement on a large scale in schools. To address these challenges, this study aims to develop and evaluate a predictive model for the risk of drug abuse in adolescents using the Random Forest algorithm. This approach focuses on utilizing social, demographic, and environmental variables in a more practical and accessible manner. The dataset used comprises 10,000 respondents, with methodological steps including data preprocessing, feature engineering for classification of three risk classes (Low, Medium, High) using a quantile approach, and dividing the dataset into 80% training data and 20% testing data. The model was comprehensively evaluated using accuracy, precision, recall, F1-score, and confusion matrix metrics. The results showed that the Random Forest model achieved an accuracy rate of 33% in the multi-class classification scheme, and significantly increased to 51.95% in the binary classification scheme. Furthermore, feature importance analysis revealed that smoking prevalence, peer influence, and family background conditions were the predictors with the most dominant contribution in mapping adolescent vulnerability. The main contribution of this study is the design of a more granular risk categorization scheme and providing an initial foundation for the development of an adaptive, practical, and highly scalable machine learning-based early warning system to support preventive interventions in educational institutions.

Prediksi Harga Beras Tingkat Perdagangan Besar Menggunakan Algoritma Extreme Gradient Boosting Berbasis Indikator Ekonomi Makro

Josua Jhon Radho Hutahaean — Fri, 24 Jul 2026 00:00:00 +0000

Wholesale rice prices are an important indicator for food-price monitoring because their movements affect supply chains, distribution actors, and household purchasing power. This study develops an Indonesian wholesale rice-price forecasting model using Extreme Gradient Boosting (XGBoost) with macroeconomic indicators and temporal features. Official secondary data from Statistics Indonesia were collected from January 2018 to May 2026, comprising 101 monthly observations. The predictor variables include general inflation, rice production, harvested area, Farmers’ Terms of Trade for food crops, population, and the food Consumer Price Index. In addition, lag-1, lag-3, and a three-month moving-average feature were constructed from historical rice-price observations. The dataset was divided chronologically into 84 training observations and 17 testing observations. Hyperparameter optimization was performed using Grid Search with TimeSeriesSplit on the training data. XGBoost performance was compared with ARIMA(1,1,1) and Random Forest Regression using RMSE, MAE, MAPE, and R². The test results show that XGBoost achieved an RMSE of IDR 234.17/kg, an MAE of IDR 189.43/kg, a MAPE of 1.63%, and an R² of 0.9621. These results outperform ARIMA and Random Forest on the same test set. Feature-importance analysis indicates that the lag-1 price, three-month moving average, and Farmers’ Terms of Trade provide the largest predictive contributions. The findings indicate that multivariate XGBoost has potential as a prototype for data-driven wholesale rice-price monitoring.

Penerapan Algoritma Navi Bayes dalam Memprediksi Tingkat Resiko Penyakit Stroke Menggunakan Data Kesehatan

Angel Ariski Simatupang — Wed, 29 Jul 2026 00:00:00 +0000

Stroke is a non-communicable disease and one of the leading causes of death and long-term disability worldwide, making early detection essential through intelligent computational systems that can assist healthcare professionals in clinical decision-making. The main challenge addressed in this study is the complexity of multifactorial stroke risk factors and the imbalance of medical record datasets, which may affect the performance of classification models. This study implements the Gaussian Naive Bayes algorithm as the classification method, supported by comprehensive data preprocessing stages, including mean value imputation for missing data, label encoding to transform categorical variables into numerical values, Min-Max Scaling normalization, and classification modeling using RapidMiner. The objective of this research is to accurately predict the level of stroke risk based on patients' medical records in order to support clinical decision support systems for preventive healthcare and early intervention. The experimental results demonstrate that the proposed model achieved an overall accuracy of 90.70%, a precision of 72.08%, a recall of 78.89%, and an F1-score of 75.33%. Furthermore, the model successfully classified posterior probabilities into hierarchical risk categories, providing more interpretable information for identifying high-risk patients and supporting more effective and efficient clinical decision-making processes in preventive stroke management.

Analisis Sentimen Ulasan Pengguna Aplikasi Gojek di Google Play Store Menggunakan Metode Multinomial Naive Bayes dan Logistic Regression

Nurul Hidayanah, Siska Fitriani, Icha Winadya Permadani, Ryan Randy Suryono — Wed, 29 Jul 2026 00:00:00 +0000

The Gojek application has become one of the largest platforms providing transportation, food delivery, and digital payment services in Indonesia. Every day, thousands of users provide reviews in the form of criticisms, complaints, and compliments through the Google Play Store. However, the massive volume and unstructured nature of these reviews pose challenges for management in monitoring user satisfaction manually, objectively, and rapidly. The primary issue in analyzing this review data is the high level of class imbalance between the number of positive and negative reviews, where positive reviews frequently dominate significantly. This data imbalance becomes crucial as it tends to bias standard classification models and reduce their predictive accuracy toward the minority class (negative reviews), even though these negative reviews contain vital complaints necessary for system improvement. Therefore, this study aims to analyze the sentiment of Gojek users by comparing the performance of the Multinomial Naïve Bayes (MNB) and Logistic Regression (LR) classification algorithms, while simultaneously addressing the data imbalance issue. The research process encompasses text preprocessing stages, including cleansing, case folding, stopword removal, and stemming. Feature extraction is performed using Term Frequency-Inverse Document Frequency (TF-IDF) and Count Vectorizer methods based on Unigram and Bigram schemes. Data splitting utilizes a proportion of 80% training data and 20% testing data, where the Synthetic Minority Over-sampling Technique (SMOTE) is applied specifically to the training data to resolve the text category imbalance. The evaluation results are measured based on accuracy, precision, recall, and F1-score metrics. This research is expected to provide recommendations for the best algorithm for large-scale review text classification, as well as data-driven insights for Gojek developers to enhance service quality based on genuine user sentiments.

Analisis Perbandingan Algoritma Random Forest dan Support Vector Machine pada Prediksi Customer Churn Menggunakan IBM Telco Customer Churn Dataset

Thu, 30 Jul 2026 00:00:00 +0000

Customer churn is a condition in which customers decide to discontinue the services provided by a company. In the telecommunications industry, a high customer churn rate can reduce company revenue and customer loyalty. Therefore, an accurate prediction method is needed to identify customers who are likely to churn so that preventive strategies can be implemented at an early stage. This study aims to compare the performance of the Random Forest and Support Vector Machine (SVM) algorithms in predicting customer churn using the IBM Telco Customer Churn Dataset. The research stages include data collection, data preprocessing, model development using Orange Data Mining, model evaluation through Test and Score, Confusion matrix, and Receiver operating characteristic (ROC), as well as data visualization using Microsoft Power BI. The results indicate that both algorithms are capable of classifying customer data; however, the Random Forest algorithm achieves better performance than the Support Vector Machine based on the evaluation metrics obtained. Furthermore, data visualization using Microsoft Power BI provides a clearer understanding of customer characteristics and supports the interpretation of the research findings. Therefore, Random Forest is recommended as a more effective algorithm for customer churn prediction in the telecommunications sector.

Komparasi Algoritma Naive Bayes, Random Forest, dan Decision Tree untuk Prediksi Penyakit Stroke Menggunakan Orange Data Mining

Fri, 31 Jul 2026 00:00:00 +0000

Stroke is one of the leading causes of death and long-term disability worldwide, making accurate prediction methods essential to support early detection and clinical decision-making. The problem addressed in this study is the lack of evidence regarding which classification algorithm provides the best performance for predicting stroke using the Healthcare Stroke Dataset. This study aims to compare the performance of the Naive Bayes, Random Forest, and Decision Tree algorithms using Orange Data Mining to identify the most effective predictive model. A quantitative approach with a comparative experimental design was employed. The dataset used in this research was the Healthcare Stroke Dataset obtained from Kaggle, consisting of 5,110 records with 12 attributes. The research process included data preprocessing using the Impute widget, feature selection using the Rank widget, classification model development, and model evaluation through 10-fold cross-validation. Performance was assessed using Accuracy, Area Under the Curve (AUC), Precision, Recall, F1-Score, Matthews Correlation Coefficient (MCC), Confusion Matrix, and Receiver Operating Characteristic (ROC) analysis. The results indicate that the Decision Tree algorithm achieved the highest accuracy of 95.1%, followed by Random Forest with 94.8%, while Naive Bayes achieved 92.4%. However, Naive Bayes obtained the highest AUC value of 0.804, demonstrating superior class discrimination capability on an imbalanced dataset. These findings suggest that algorithm selection should not rely solely on accuracy but also consider the model's ability to distinguish between classes consistently. This study contributes to providing recommendations for selecting appropriate classification algorithms to support the development of machine learning-based early stroke prediction systems