Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:Masalah pengelolaan parkir di Politeknik Jambi sering menyebabkan ketidakefisienan akibat sistem penghitungan manual yang rentan human error. Penelitian ini bertujuan merancang sistem penghitungan kendaraan otomatis berbasis…
asis pengolahan citra digital. Metode yang digunakan adalah Background Subtraction dengan algoritma MOG2 dan OpenCV menggunakan video kamera smartphone. Sistem mengintegrasikan proses preprocessing citra, operasi morfologi, dan Euclidean Distance Tracker untuk melacak serta menghitung kendaraan secara real-time. Hasil penelitian menunjukkan sistem mampu membedakan kendaraan yang bergerak dengan objek statis secara akurat melalui Virtual Counting Line. Dengan beban komputasi yang ringan dan biaya rendah, sistem ini efektif menjadi solusi otomatisasi manajemen parkir di lingkungan kampus.
Parking management issues at Politeknik Jambi often lead to inefficiencies due to manual counting systems prone to human error. This study aims to design an automatic vehicle counting system based on digital image processing. The method utilizes Background Subtraction with the MOG2 algorithm and OpenCV using smartphone video input. The system integrates image preprocessing, morphological operations, and Euclidean Distance Tracker to track and count vehicles in real-time. The results demonstrate that the system can accurately distinguish between moving vehicles and static objects via a Virtual Counting Line. With low computational requirements and cost-effectiveness, this system offers an efficient automation solution for campus parking management.
Abstract:Emas merupakan salah satu jenis komoditi yang paling banyak diminati untuk tujuan investasi, karena dipandang sebagai instrumen yang lebih aman dibandingkan saham serta memiliki nilai jual yang selalu bergerak mengikuti…
kondisi pasar. PT Victoeria Vici, sebagai pelaku usaha perhiasan emas custom, menghadapi kendala dalam menentukan estimasi harga jual kepada pelanggan, sebab proses pengerjaan pesanan custom membutuhkan waktu hingga 14 hari, sementara harga emas bergerak fluktuatif dan tidak terstruktur setiap harinya sehingga estimasi harga menjadi tidak akurat dan tidak efektif. Berdasarkan permasalahan tersebut, penelitian ini menerapkan konsep Data Mining dengan algoritma Trend Moment untuk mengestimasi harga emas pada rentang waktu tertentu. Data yang digunakan merupakan data historis harga emas per gram pada PT Victoeria Vici periode Agustus–Oktober 2021 sebanyak 92 data. Tahapan penelitian meliputi pengumpulan data, penentuan variabel X dan Y, eliminasi untuk memperoleh nilai konstanta a dan slope b, serta penerapan persamaan Y = a + bX untuk memperoleh nilai estimasi. Hasil perhitungan menunjukkan nilai a = 720.871,725 dan b = 3,108 sehingga model estimasi mampu menghasilkan proyeksi harga emas yang mendekati pola data historis. Model ini kemudian diimplementasikan ke dalam aplikasi berbasis desktop menggunakan Microsoft Visual Basic 2010 dan basis data Microsoft Access, dilengkapi Crystal Report untuk pencetakan laporan hasil estimasi. Hasil penelitian menunjukkan bahwa algoritma Trend Moment dapat membantu PT Victoeria Vici dalam memperoleh estimasi harga emas secara lebih cepat, konsisten, dan terdokumentasi.
Gold is one of the most sought-after commodities for investment purposes, as it is regarded as a safer instrument compared to stocks and has a selling value that constantly fluctuates with market conditions. PT Victoeria Vici, a custom gold jewelry business, faces difficulty in determining the estimated selling price offered to customers because the production process for custom orders takes up to 14 days, while gold prices move in an unstructured and fluctuating manner every day, making manual price estimation inaccurate and ineffective. Based on this problem, this study applies the concept of Data Mining using the Trend Moment algorithm to estimate gold prices over a certain period of time. The data used is historical daily gold price data per gram from PT Victoeria Vici for the period of August–October 2021, consisting of 92 records. The research stages include data collection, determination of the X and Y variables, elimination to obtain the constant value a and the slope b, and the application of the equation Y = a + bX to obtain the estimated value. The calculation results show a value of a = 720,871.725 and b = 3.108, so that the estimation model is able to produce gold price projections that closely follow the pattern of historical data. This model was then implemented into a desktop-based application using Microsoft Visual Basic 2010 and a Microsoft Access database, equipped with Crystal Report for printing estimation result reports. The results show that the Trend Moment algorithm can help PT Victoeria Vici obtain gold price estimations more quickly, consistently, and in a well-documented manner.
Abstract:Promosi penerimaan mahasiswa baru (PMB) merupakan salah satu faktor penting dalam meningkatkan jumlah dan kualitas calon mahasiswa. Namun, strategi promosi yang belum memanfaatkan data historis secara optimal dapat menyebabkan…
babkan kegiatan promosi kurang tepat sasaran. Penelitian ini bertujuan untuk menganalisis data historis PMB sebagai dasar dalam menyusun strategi promosi yang lebih efektif pada Jurusan Teknologi Informasi dan Komputer Politeknik Negeri Lhokseumawe. Penelitian menggunakan pendekatan kuantitatif deskriptif dengan memanfaatkan data sekunder PMB periode 2023–2025. Analisis dilakukan melalui tahapan data cleaning, transformasi data, statistik deskriptif, segmentasi calon mahasiswa, dan visualisasi data menggunakan dashboard analitik. Variabel yang dianalisis meliputi program studi, asal sekolah, jurusan asal sekolah, kecamatan, kabupaten/kota, provinsi, jalur masuk, dan sumber informasi pendaftar. Hasil penelitian menunjukkan bahwa sebagian besar pendaftar berasal dari Provinsi Aceh, khususnya Kabupaten Aceh Utara dan Kota Lhokseumawe, dengan dominasi lulusan jurusan IPA serta peminat terbesar pada Program Studi Teknik Informatika. Instagram dan website menjadi sumber informasi utama bagi calon mahasiswa. Pemanfaatan data historis melalui visualisasi data mampu memberikan informasi yang lebih komprehensif mengenai karakteristik calon mahasiswa sehingga dapat mendukung pengambilan keputusan dalam penyusunan strategi promosi PMB yang lebih terarah, efektif, dan berbasis data.
New student admissions (PMB) promotion is an important factor in increasing the number and quality of prospective students. However, promotional strategies that do not optimally utilize historical data can result in less targeted promotional activities. This study aims to analyze historical PMB data as a basis for developing a more effective promotional strategy in the Information and Computer Technology Department of the Lhokseumawe State Polytechnic. The study uses a descriptive quantitative approach utilizing secondary PMB data for the 2023–2025 period. The analysis was carried out through the stages of data cleaning, data transformation, descriptive statistics, prospective student segmentation, and data visualization using an analytical dashboard. The variables analyzed included study program, school of origin, major of origin of school, sub-district, regency/city, province, admission route, and applicant information sources. The results show that most applicants come from Aceh Province, especially North Aceh Regency and Lhokseumawe City, with a predominance of science graduates and the greatest interest in the Informatics Engineering Study Program. Instagram and websites are the main sources of information for prospective students. The use of historical data through data visualization can provide more comprehensive information regarding the characteristics of prospective students so that it can support decision-making in developing more targeted, effective, and data-based PMB promotion strategies.
Abstract:Artikel ini meninjau perkembangan riset terkini di Indonesia terkait topik penelitian jurnal ini, mengevaluasi metodologi yang digunakan, dan merumuskan rekomendasi praktis.
Abstract:Penelitian ini bertujuan untuk menganalisis dan mengimplementasikan metode optimal dalam pengembangan riset berkelanjutan. Hasil penelitian menunjukkan efisiensi sebesar 85%.
Abstract:Artikel ini meninjau perkembangan riset terkini di Indonesia terkait topik penelitian jurnal ini, mengevaluasi metodologi yang digunakan, dan merumuskan rekomendasi praktis.
Abstract:Penelitian ini bertujuan untuk menganalisis dan mengimplementasikan metode optimal dalam pengembangan riset berkelanjutan. Hasil penelitian menunjukkan efisiensi sebesar 85%.
Abstract:The rapid growth of the hotel industry requires hotels to improve operational planning, one of which is by forecasting room reservations. Inaccurate forecasting may cause an imbalance between room availability and customer…
er demand. This study aims to compare the Weighted Moving Average and Single Exponential Smoothing algorithms in forecasting room reservations at Raz Hotel and Convention Medan using historical data from January 2025 to May 2026. The research method consisted of data collection, forecasting using both algorithms, and accuracy evaluation through Mean Absolute Deviation, Mean Squared Error, and Mean Absolute Percentage Error. The results indicate that the Single Exponential Smoothing algorithm achieved a Mean Absolute Percentage Error of 15.24%, which is lower than the 15.63% obtained by the Weighted Moving Average algorithm. Furthermore, the Single Exponential Smoothing algorithm predicted 835.90 room reservations for June 2026. Therefore, it can be concluded that the Single Exponential Smoothing algorithm provides better forecasting accuracy and is more suitable for predicting room reservations at Raz Hotel and Convention Medan.
Abstract:Sales forecasting is a crucial component of operational strategy and inventory management in the culinary industry, particularly for businesses dealing with raw materials that have short shelf lives. The Sate Padang Hapis…
s business faces the challenge of unpredictable monthly fluctuations in consumer demand, which often lead to supply imbalances, overproduction, or lost profit opportunities due to stockouts. This study aims to implement and analyze the accuracy of the Single Moving Average (SMA) quantitative forecasting method in predicting Sate Padang Hapis sales volumes for June 2026. Model performance was evaluated by assessing mathematical accuracy across two time-interval variations: 3-month and 5-month moving averages. Projection error rates were rigorously measured using Mean Absolute Deviation (MAD), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE) parameters. The analysis reveals that the Single Moving Average model with a 5-month interval yields projections closest to actual data, achieving the lowest error rates (MAD: 28.00; MSE: 1,304.00; MAPE: 2.28%). Implementing this forecasting model provides management with an objective basis for decision-making, enabling the effective and efficient optimization of raw material logistics and supply management.