Journal of Software Engineering and Information System (SEIS)

PENERAPAN WATERFALL SDLC PADA PERANCANGAN SISTEM PENGELOLAAN IZIN KELUAR KANTOR DI KANREG VI BKN MEDAN

Nasrul Mahruf Aznawi — 2026-01-31

The handling of office leavepermits at the Regional Office VI of the State Civil Service Agency (BKN) in Medan is still done manually, causing various problems such as delays in approval, lack of transparency, potential data manipulation, and the unavailability of well-documented employee permit histories. This condition has a direct impact on work effectiveness and the accuracy of personnel administration. This study aims to design and develop a web-based office leave management system to improve the efficiency and transparency of the administrative process. The system development method used is the Software Development Life Cycle (SDLC) with the Waterfall model, which includes the stages of requirements analysis, system design, implementation, testing, and maintenance. Data collection was carried out through observation and interviews to ensure that the system meets user needs. The results of the study show that the developed system is capable of managing the process of submitting, approving, and recording office leave digitally and in an integrated manner. System testing using the Black Box Testing method showed that all main functions ran according to system requirements. This system is capable of increasing the speed of the service process, reducing administrative errors, and providing a well-documented history of permits.

IMPLEMENTASI K-MEANS MENGUKUR KEPUASAN SISWA TERHADAP PELAYANAN PADA SMKS PELITA RAYA JAMBI

Vanji Saputra — 2026-01-31

Education plays a strategic role in improving the quality of human resources; therefore, the quality of educational services must be continuously evaluated. Student satisfaction is an important indicator in assessing school service quality, as students actas the primary customers of educational services. SMK Swasta Terpadu Pelita Raya Jambi needs to measure student satisfaction to enhance service quality and institutional competitiveness.This study applies a data mining approach using the K-Means Clustering algorithm to analyze student satisfaction with school services. Data were collected through questionnaires distributed to 319 students using a Likert scale. The measurement of student satisfaction was based on five service quality dimensions: tangibles,reliability, responsiveness, assurance, and empathy. The research stages included data collection, data cleaning, data transformation, and data processing using both manual calculations and SPSS software.The results indicate that student satisfaction data were grouped into three clusters. The first cluster consisted of 183 students who were satisfied with school services, the second cluster included 30 students who were moderately satisfied, and the third cluster comprised 106 students who were dissatisfied. The clustering results obtained using SPSS showed a similar pattern, although slight differences in cluster membership occurred due to random centroid initialization.In conclusion, the K-Means algorithm effectively clusters student satisfaction levelsand provides valuable insights for school management. The clustering results can serve as a basis for evaluating and improving service quality to enhance student satisfaction at SMK Swasta Terpadu Pelita Raya Jambi

PENERAPAN E-COMMERCE DENGAN METODE CRM BERBASIS WEBSITE PADA TOKO BATAVIA COLLECTION

Iriene Putri Mulyadi — 2026-01-31

Website-based e-commerce is a crucial strategy for increasing transaction efficiency and fostering stronger relationships with customers, especially in the fashion sector. Among the fashion brands, Batavia Collection uses digital systems with Customer Relationship Management (CRM) integration to make it easier for customers to access product information, conduct online transactions, and communicate wirelessly with customers. The waterfall method is used to build the system, covering the phases of requirement analysis, system design, implementation, and pengujian. CRM integration is useful for managing customer data, supporting sales activities, and expanding personal services. According to the study's findings, operational efficiency has increased, customer satisfaction, and the potential for more extensive market expansion. This system also aids in more systematic promotion and pelaporan processes. The implementation of CRM-based e-commerce can increase Batavia Collection's sales and service quality.

IMPLEMENTASI SISTEM PERPUSTAKAAN MANDIRI DIGITAL DENGAN TEKNOLOGI BARCODE DAN FINGERPRINT DALAM UPAYA MENINGKATKAN EFISIENSI LAYANAN

Alexander Fernando Kawas Sibero — 2026-01-31

A library information system is a computerized system for managing books and other library collections. It handles transactions such as borrowing, returning, renewing, and so on. The user of a library information system is generally an administrator who is solely responsible for managing the system. Library members simply select library collections and present their membership cards to complete transactions. The concept of an independent library information system is based on the system's high dependence on administrators, so that in certain situations, officers may not be able to provide services to members. Furthermore, transaction processing time can also be improved by using an independent system. Barcode technology is used to read library collection data, and fingerprint technology is efficient in identifying and verifying member data. The increasingly fast service time illustrates the benefits of implementing fingerprints and barcodes in library information systems. Likewise, increasing user satisfaction indicates that fingerprint and barcode technology have a significant impact on the research location. The results of the evaluation of service time and user satisfaction in this study are expected to open up further research opportunities in the field of library information systems.

PREDIKSI HARGA EMAS MENGGUNAKAN ALGORITMA LONG SHORT TERM MEMORY (LSTM) & GATED RECURRENT UNIT (GRU)

Zana Vania Hendra — 2026-01-31

Gold is an asset that has a hedge against inflation and global economic volatility, making it interesting to analyze as an investment instrument. This study aims to compare the performance of Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) models in predicting gold prices using historical data from 2013 to 2022. The data used includes daily gold prices and goes through a preprocessing stage before being divided into training (80%) and testing (20%) data. LSTM and GRU models were trained with epoch and batch size variations, then evaluated using MAE, RMSE, MSE, and MAPE metrics. The results showed that the GRU model with 50 epochs performed best, with MAE 0.0145, RMSE 0.0186, MSE 0.0003, and MAPE 1.9209%, better than LSTM which produced higher errors. The residual graph also shows that GRU produces stable predictions with a random error distribution that is close to zero. These findings confirm that GRU is more accurate and efficient in modeling gold price time series, and has the potential to be implemented in artificial intelligence-based commodity price prediction systems.

PERANCANGAN SISTEM INFORMASI LAYANAN SERVICE AC PADA PT.TEKNINDO ABADI PRATAMA BERBASIS WEB

Elsi Titasari Br Bangun — 2026-01-31

The development of information technology plays an important role in improving the efficiency of business processes, including in the service sector. PT Teknindo Abadi Pratama, as an air conditioning (AC) service provider, faces obstacles in manual recording, managing technician schedules, and preparing transaction reports that are not yet optimal. Therefore, this study aims to design a web-based AC service information system that is able to manage customer data, simplify technician scheduling, and present transaction reports in a structured manner. The system development method used is the Waterfall model through the stages of needs analysis, system design, implementation, and testing. The results of the study are in the form of a web-based system prototype that can improve service speed, data recording accuracy, and technician schedule management efficiency. With this system, the operational processes of PT Teknindo Abadi Pratama become more computerized, thus supporting improved service quality to customers and more accurate managerial decision making.

Perkembangan teknologi informasi berperan penting dalam meningkatkan efisiensi proses bisnis, termasuk pada sektor pelayanan jasa. PT Teknindo Abadi Pratama sebagai penyedia jasa service pendingin udara (AC) menghadapi kendala dalam pencatatan manual, pengelolaan jadwal teknisi, serta penyusunan laporan transaksi yang belum optimal. Oleh karena itu, penelitian ini bertujuan merancang sistem informasi layanan service AC berbasis web yang mampu mengelola data pelanggan, mempermudah penjadwalan teknisi, dan menyajikan laporan transaksi secara terstruktur. Metode pengembangan sistem yang digunakan adalah dengan model Waterfall melalui tahapan analisis kebutuhan, perancangan sistem, implementasi, dan pengujian. Hasil penelitian berupa prototipe sistem berbasis web yang dapat meningkatkan kecepatan pelayanan, akurasi pencatatan data, serta efisiensi manajemen jadwal teknisi. Dengan adanya sistem ini, proses operasional perusahaan PT Teknindo Abadi Pratama menjadi lebih terkomputerisasi, sehingga mendukung peningkatan kualitas layanan kepada pelanggan dan pengambilan keputusan manajerial secara lebih tepat.

MODEL PREDIKSI PENERIMA BANTUAN SOSIAL BERBASIS ALGORITMA RANDOM FOREST

Siti Hatmara Sukma — 2026-01-31

Inaccurate targeting of social assistance beneficiaries remains a critical issue at the village level due to subjective and inconsistent manual verification processes. This study aims to develop a predictive model for determining social assistance eligibility using the Random Forest algorithm based on 2021 SDGs Village microdata from Cibeureum Village. The research involves data preprocessing, model training, and hyperparameter optimization, with performance evaluation using accuracy, precision, recall, and F1-score metrics. The proposed model achieved an accuracy of 94.34%, indicating strong and stable classification performance. Feature importance analysis shows that housing conditions, access to clean water, and asset ownership are the most influential socioeconomic indicators. These findings demonstrate that Random Forest can effectively support data-driven decision-making and improve the accuracy of social assistance distribution at the village level.

OPTIMASI MODEL XGBOOST UNTUK PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN OPTUNA

Yasni Optarina — 2026-01-31

Heart disease is one of the leading causes of mortality worldwide, emphasizing the need for accurate early detection systems. Machine learning models such as XGBoost have demonstrated strong performance in medical classification tasks; however, their effectiveness is highly dependent on optimal hyperparameter configurations. This study aims to improve the performance of XGBoost for heart disease classification by applying hyperparameter optimization using the Optuna framework with the Tree-structured Parzen Estimator (TPE) algorithm. The UCI Heart Disease dataset, consisting of 918 records, is used in this study. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied to the training data. Model performance is evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The experimental results show that the optimized XGBoost model achieves an accuracy of 89.13%, outperforming the baseline model with 87.50%, and improves recall from 87.50% to 89.10%. In addition, the optimized model attains a higher ROC-AUC value of 0.9319, indicating improved classification stability. These findings demonstrate that Optuna-based hyperparameter optimization effectively enhances the performance and reliability of XGBoost, making it suitable for supporting early heart disease diagnosis in medical decision support systems.

Analisis Pengaruh Ketidakseimbangan Data terhadap Kinerja Model Klasifikasi Penyakit Jantung

Maulana Samodro — 2026-02-04

Heart disease remains one of the leading causes of mortality, highlighting the importance of data-driven predictive models for risk analysis. However, medical datasets commonly suffer from class imbalance and weak predictive signals, which can limit model performance. This study aims to evaluate the performance of a Logistic Regression model for heart attack prediction by comparing imbalanced and balanced datasets using different train–test split ratios of 80:20 and 90:10. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix. The experimental results show that models trained on imbalanced data achieved higher accuracy but exhibited biased performance, particularly low recall for the minority class. After applying data balancing techniques, accuracy decreased; however, the model demonstrated more balanced performance with improved recall and F1-score for the minority class. These findings indicate that accuracy alone does not adequately represent model performance on imbalanced medical datasets. Moreover, the results suggest that the relationship between the medical attributes and heart attack occurrence in the dataset is relatively weak, limiting the model’s ability to establish clear decision boundaries. Therefore, appropriate evaluation metrics and representative clinical datasets are essential for developing reliable heart disease risk prediction models.

ANALISIS KUALITAS LAYANAN WEBSITE WIRAUSAHA MERDEKA UNIVERSITAS RIAU TERHADAP KEPUASAN PENGGUNA MENGGUNAKAN METODE WEBQUAL 4.0

Syahril — 2026-02-27

Perkembangan teknologi informasi mendorong perguruan tinggi untuk menyediakan sistem informasi berbasis web yang mampu mendukung efektivitas layanan akademik dan non-akademik. Salah satu implementasinya adalah website Wirausaha Merdeka Universitas Riau (WMK UNRI) yang digunakan sebagai media pengelolaan dan pelaksanaan program Wirausaha Merdeka. Namun, dalam implementasinya masih ditemukan beberapa kendala teknis yang berpotensi memengaruhi kepuasan pengguna. Penelitian ini bertujuan untuk menganalisis pengaruh kualitas layanan website terhadap kepuasan pengguna menggunakan metode Webqual 4.0, yang mencakup dimensi Usability, Information Quality, dan Service Interaction Quality. Penelitian ini menggunakan pendekatan kuantitatif dengan metode survei terhadap 200 responden peserta WMK UNRI Batch II Tahun 2023. Data dikumpulkan melalui kuesioner skala Likert dan dianalisis menggunakan regresi linier berganda dengan bantuan perangkat lunak SPSS. Hasil penelitian menunjukkan bahwa secara simultan ketiga variabel independen berpengaruh signifikan terhadap kepuasan pengguna. Namun, secara parsial hanya variabel Service Interaction Quality yang berpengaruh positif dan signifikan terhadap User Satisfaction, sedangkan Usability dan Information Quality tidak berpengaruh signifikan. Nilai koefisien determinasi (R²) sebesar 0,760 menunjukkan bahwa model penelitian mampu menjelaskan 76% variasi kepuasan pengguna. Hasil penelitian ini menegaskan bahwa kualitas interaksi layanan merupakan faktor dominan dalam meningkatkan kepuasan pengguna website WMK UNRI. Oleh karena itu, pengelola website disarankan untuk memprioritaskan peningkatan aspek interaksi layanan guna mendukung keberhasilan implementasi sistem informasi secara berkelanjutan.