Abstract:Abstract: The rapid growth of the cosmetics industry on e-commerce platforms has intensified competition, creating a critical need for effective, data-driven marketing strategies. This study aims to conduct a comparative…
analysis of machine learning algorithms to predict the sales categories (High, Medium, Low) of cosmetic products on the Tokopedia marketplace. Four classification models; Random Forest, XGBoost, Logistic Regression, and Naive Bayes were trained and evaluated on data collected via web scraping. The methodology incorporates the Synthetic Minority Over-sampling Technique (SMOTE) to address significant class imbalance and GridSearchCV for hyperparameter optimization to ensure a fair and robust comparison. The experimental results conclusively show that the Random Forest model achieved the best performance, yielding the highest F1-Score Macro Average of 0.75 and an accuracy of 85.3%. The superior model was subsequently implemented in a simple recommendation system to simulate optimal discount strategies, demonstrating its practical utility in providing actionable insights for business decisions.
Keywords: classification; comparative analysis; machine learning; sales prediction; SMOTE
Abstrak: Pertumbuhan pesat industri kosmetik pada platform e-commerce telah membuat persaingan ketat, sehingga menciptakan kebutuhan krusial akan strategi pemasaran yang efektif dan berbasis data. Penelitian ini bertujuan untuk melakukan analisis komparatif terhadap algoritma machine learning untuk memprediksi kategori penjualan (Tinggi, Sedang, Rendah) produk kosmetik di marketplace Tokopedia. Empat model klasifikasi, yaitu Random Forest, XGBoost, Regresi Logistik, dan Naive Bayes, dilatih dan dievaluasi menggunakan data yang dikumpulkan melalui web scraping. Metodologi penelitian ini menerapkan Synthetic Minority Over-sampling Technique (SMOTE) untuk mengatasi ketidakseimbangan kelas yang signifikan dan GridSearchCV untuk optimisasi hyperparameter guna memastikan perbandingan yang adil. Hasil eksperimen menunjukkan bahwa model Random Forest mencapai performa terbaik, dengan menghasilkan F1-Score Macro Average tertinggi sebesar 0,75 dan akurasi 85,3%. Model unggul ini kemudian diimplementasikan dalam sebuah sistem rekomendasi sederhana untuk menyimulasikan strategi diskon yang optimal, yang menunjukkan kegunaan praktisnya dalam memberikan wawasan yang dapat ditindaklanjuti untuk pengambilan keputusan bisnis.
Kata kunci: analisis komparatif; klasifikasi; machine learning; prediksi penjualan; SMOTE
Abstract:Abstract: MBG is a strategic program of the Prabowo-Gibran administration. This program has become a widely discussed issue in the public. To better understand public perception of this program, sentiment analysis is necessary.…
essary. This study aims to compare the performance of algorithms machine learning SVM, RF, And BERT with preprocessing data analyzing public sentiment of the MBG program in media X. The total dataset for this study was 39,858 out of 42,465 successfully crawled tweets. The research methods included data collection, preprocessing data (cleaning, case folding, word normalization, stopword removal and stemming), feature extraction, model training (fine-tuning), handling class imbalance with SMOTE, and evaluation using accuracy, precision, recall, and f1-score. The research results show that without SMOTE, the best performing models are BERT with 89% accuracy, SVM 87%, and RF 78.4%. After SMOTE, the best algorithms were SVM with 92.94%, BERT with 88.3%, and RF with 86.59%. The results confirmed that SVM is the best algorithm if at leastclass imbalance. BERT is the best algorithm before and after SMOTE, because BERT is more effective in capturing the nuances of language on social media, so BERT is the most recommended in MBG sentiment analysis.
Keywords: sentiment analysis; machine learning; SVM, RF, and BERT
Abstrak: MBG merupakan program strategis pemerintahan Prabowo - Gibran. Program ini menjadi isu yang banyak diperbincangkan publik. Untuk mengetahui lebih dalam persepsi masyrakat tentang program ini, perlu dilakukan analisis sentiment. Penelitian ini bertujuan membandingkan kinerja algoritma machine learning SVM, RF, dan BERT dengan preprocessing data menganalisis sentiment public program MBG di media X. Total dataset penelitian ini adalah 39.858 dari 42.465 tweet yang berhasil di crawling. Metode penelitian mencakup pengumpulan data, preprocessing data (cleaning, case folding, normalisasi kata, stopword removal dan stemming), ekstraksi fitur, pelatihan model (fine-tuning), penanganan class imbalance dengan SMOTE, dan evaluasi menggunakan akurasi, presisi, recall, dan f1-score. Hasil peneltian menunjukkan, tanpa SMOTE model dengan kinerja terbaik adalah BERT dengan akurasi 89%, SVM 87%, dan RF 78,4%. Setelah SMOTE algoritma terbaik adalah SVM 92,94%, BERT 88,3% dan RF 86,59%. Hasil penelitian menegaskan bahwa SVM adalah algoritma terbaik jika minimal class imbalance. BERT adalah algoritma terbaik sebelum dan sesudah SMOTE, karena BERT lebih efektif dalam menangkap nuansa bahasa pada media sosial, sehingga BERT paling di rekomendasikan dalam analisis sentimen MBG.
Kata kunci: analisis sentimen; machine learning; SVM, RF, dan BERT
Abstract:Abstract: Higher education plays an essential role in improving human resource quality, one of which is through the institution’s ability to monitor and predict student graduation outcomes. This study does not focus on a…
a specific university but utilizes the publicly available Students Performance in Exams dataset from Kaggle, consisting of 1,000 student records containing mathematics, reading, and writing scores, along with demographic attributes such as gender, parental education level, lunch type, and test preparation participation. The data were processed through a feature engineering stage by adding an average score variable as an early indicator of graduation status. A predictive model was developed using the Random Forest Classifier, achieving an accuracy of 94.5%. The final model was integrated into a Streamlit-based web application to provide an accessible tool for academic stakeholders. The results indicate that the proposed model can serve as an effective decision-support tool for early evaluation of students’ likelihood of graduation.
Keywords: prediction; random forest classifier, streamlit, student graduation.
Abstrak: Pendidikan tinggi memegang peran penting dalam peningkatan kualitas sumber daya manusia, salah satunya melalui kemampuan institusi dalam memantau dan memprediksi tingkat kelulusan mahasiswa. Penelitian ini tidak berfokus pada perguruan tinggi tertentu, melainkan menggunakan dataset publik Students Performance in Exams dari Kaggle yang berisi 1.000 data mahasiswa, terdiri atas nilai matematika, membaca, menulis, serta atribut demografis seperti gender, tingkat pendidikan orang tua, jenis makan siang, dan partisipasi kursus persiapan. Data diolah melalui tahap feature engineering dengan menambahkan variabel average score sebagai indikator awal kelulusan. Model prediksi dibangun menggunakan algoritma Random Forest Classifier, yang menghasilkan tingkat akurasi sebesar 94,5%. Model ini kemudian diimplementasikan ke dalam aplikasi web berbasis Streamlit untuk memberikan layanan prediksi yang mudah diakses oleh pihak akademik. Hasil penelitian menunjukkan bahwa model mampu digunakan sebagai alat pendukung keputusan untuk melakukan evaluasi dini terhadap potensi kelulusan mahasiswa.
Kata kunci: kelulusan mahasiswa; prediksi; random forest classifier; streamlit.
Abstract:Abstract: The rice plant, Oryza sativa, is a major food source in Indonesia. This plant is processed into rice, a staple food for the Indonesian people. Rice growth is crucial to ensure the rice produced is of good quality.…
ty. One part of the rice plant that is susceptible to disease is the leaves, which can inhibit growth and reduce rice quality. Therefore, early detection and accurate classification of rice diseases are crucial to minimize these negative impacts. This has driven the development of a Deep Learning model capable of high-performance automatic classification. This study aims to create a rice leaf classification model using the CNN algorithm and several transfer learning architectures such as ResNet101, VGG16, and Xception. A dataset of 859 rice leaf images collected from the Kaggle website was then processed using augmentation techniques to a total of 2,439 images, plus 215 smartphone photos for external data validation. Thus, the total dataset increased to 2,656 images, covering four categories: leafblast, brownspot, healthy, and hispa. The model was processed in two stages: on the initial dataset (Non-Augmented Dataset) and the Augmented Dataset. The best experimental results were obtained using the ResNet architecture, with a training accuracy of 96.17% and a validation accuracy of 95.22%. Based on the research results, the rice plant disease classification model using deep learning demonstrated good performance.
Keywords: convolutional neural network; deep learning; fine-tuning; image classification; resnet; rice plant
Abstract:Abstract: Posyandu cadres play an important role in supporting community health services at the village and sub-district levels. However, the selection process for the best cadres is often carried out subjectively without…
t clear and standardized criteria. This condition can lead to a decline in service quality and reduced cadre motivation. Therefore, a decision support system is needed to provide assessments that are objective, measurable, and accountable. This study aims to optimize the Posyandu cadre selection process in Lubuk Kilangan District through the development of a decision support system based on a hybrid method: Analytical Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The AHP method is applied to determine the weight of each selection criterion based on its level of importance through pairwise comparisons. Subsequently, TOPSIS is used to rank candidates according to their proximity to the ideal solution. The methodology includes a literature review, primary data collection through interviews and questionnaires with stakeholders (community health centers, cadres, and village officials), as well as the implementation and testing of the AHP–TOPSIS–based system.
Keywords: Posyandu, Cadre, AHP, TOPSIS, Decision Support System
Abstrak: Kader Posyandu memiliki peran penting dalam mendukung layanan kesehatan masyarakat di tingkat desa dan kelurahan. Namun, proses pemilihan kader terbaik masih sering dilakukan secara subjektif tanpa acuan kriteria yang jelas dan terstandarisasi. Kondisi ini dapat mengakibatkan penurunan kualitas pelayanan serta rendahnya motivasi kader. Oleh karena itu, dibutuhkan suatu sistem penunjang keputusan yang mampu memberikan hasil penilaian yang objektif, terukur, dan dapat dipertanggungjawabkan. Penelitian ini bertujuan untuk mengoptimalkan proses pemilihan kader Posyandu di Kecamatan Lubuk Kilangan melalui pengembangan sistem penunjang keputusan berbasis metode hybrid Analytical Hierarchy Process (AHP) dan Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Metode AHP digunakan untuk menetapkan bobot masing-masing kriteria pemilihan kader berdasarkan tingkat kepentingan melalui perbandingan berpasangan. Selanjutnya, metode TOPSIS digunakan untuk melakukan pemeringkatan calon kader berdasarkan kedekatannya terhadap solusi ideal. Metode yang digunakan dalam penelitian ini mencakup studi literatur, pengumpulan data primer melalui wawancara dan kuesioner kepada stakeholder terkait (puskesmas, kader, dan perangkat desa), serta implementasi dan pengujian sistem berbasis AHP-TOPSIS.
Kata kunci: Posyandu, Kader, AHP, TOPSIS, Sistem Pendukung Keputusan
Abstract:Abstract: The inability to accurately monitor the lifespan of motorcycle batteries can lead to sudden failures, disrupt user activities, and increase maintenance costs. This issue is exacerbated by the absence of a predictive…
ctive system that can assist users and workshops in planning maintenance and managing battery inventory effectively. This study aims to develop a battery lifespan prediction model for motorcycles using the Double Moving Average (DMA) method. The model is built based on historical data from 12 motorcycle units, including usage frequency, duration, terrain conditions, and maintenance habits. Forecasting is conducted through two stages of moving averages followed by trend parameter calculations. Evaluation results show that the model has a high level of accuracy, with MAPE = 0.10, MAD = 1.68, and RMSE = 2.14, indicating very low prediction errors. In addition, DMA is also used to forecast product demand at PT Anugerah Karya Abiwara Kisaran to prevent stock shortages. The system is developed using Visual Studio 2010 and Microsoft Access and has proven effective in supporting maintenance planning and inventory control. With its high accuracy and efficiency, the results of this study provide tangible contributions to decision-making in battery maintenance and inventory management.
Keywords: battery; DMA; motorcycle; prediction.
Abstrak: Ketidakmampuan dalam memantau usia pakai aki sepeda motor secara akurat dapat menyebabkan kerusakan mendadak, mengganggu aktivitas pengguna, serta meningkatkan biaya perawatan. Permasalahan ini diperburuk oleh tidak tersedianya sistem prediktif yang membantu pengguna dan bengkel dalam merencanakan perawatan serta mengelola persediaan aki secara efisien. Penelitian ini bertujuan untuk mengembangkan model prediksi usia pemakaian aki sepeda motor dengan menggunakan metode Double Moving Average (DMA). Model dibangun berdasarkan data historis dari 12 unit sepeda motor yang mencakup frekuensi penggunaan, durasi, kondisi medan dan kebiasaan perawatan. Proses peramalan dilakukan melalui dua tahap perataan bergerak, yang kemudian diikuti dengan perhitungan parameter tren. Hasil evaluasi menunjukkan bahwa model ini memiliki tingkat akurasi yang tinggi, dengan nilai MAPE sebesar 0,10, MAD sebesar 1,68, dan RMSE sebesar 2,14, yang mengindikasikan tingkat kesalahan prediksi yang sangat rendah. Selain itu, metode DMA juga diterapkan untuk meramalkan permintaan produk pada PT Anugerah Karya Abiwara Kisaran guna mencegah terjadinya kekurangan stok. Sistem dikembangkan menggunakan Visual Studio 2010 dan Microsoft Access, serta terbukti efektif dalam mendukung perencanaan perawatan dan pengendalian persediaan. Dengan akurasi dan efisiensi yang tinggi, hasil penelitian ini memberikan kontribusi nyata dalam pengambilan keputusan terkait pemeliharaan aki dan manajemen inventori.
Kata kunci: baterai; DMA; prediksi; sepeda motor.
Abstract:Abstract: Information Technology has impacted various sectors, including education. Learning Management Systems (LMS) are designed to facilitate lecturers and students in accessing academic activities such as online learning.…
ning. This study aims to analyze the effectiveness of Learning Management Systems (LMS) among higher education institutions in Indonesia. This analysis is crucial for assessing the effectiveness of LMS use by universities in Indonesia, enabling investments in LMS to yield optimal results. The study employed the D&M IS Success Model and PLS-SEM to evaluate the relationships between various variables, including system, information, service quality, user satisfaction, and benefits. Simple random sampling was used to collect data from 170 universities in Indonesia. This study employed PLS-SEM to investigate the observed variables, including validity and reliability testing, which involves assessing reliability, convergent validity, and discriminant validity. This current study found that all the hypotheses were accepted with p-values below 0,05. These findings contribute to universities paying attention to aspects of system, information, and service quality in Learning Management Systems (LMS) to improve user satisfaction and create a positive perception of benefits. Therefore, this research yields significant results that contribute to higher education in Indonesia, as well as the advancement of knowledge in management information systems.
Keywords: delone and mclean; information system success; LMS; SEM-PLS.
Abstrak: Teknologi Informasi telah memengaruhi berbagai sektor, termasuk pendidikan. Learning Management System (LMS) dirancang untuk memfasilitasi dosen dan mahasiswa dalam mengakses kegiatan akademik seperti pembelajaran daring. Penelitian ini bertujuan untuk menganalisis efektivitas penggunaan Learning Management System (LMS) di perguruan tinggi di Indonesia. Analisis ini penting untuk menilai sejauh mana efektivitas penggunaan LMS oleh universitas-universitas di Indonesia, sehingga investasi dalam LMS dapat mem-berika n hasil yang optimal.Penelitian ini menggunakan model D&M IS Success Model dan metode PLS-SEM untuk mengevaluasi hubungan antara berbagai variabel, termasuk kuali-tas sistem, informasi, layanan, kepuasan pengguna, dan manfaat. Teknik simple random sampling digunakan untuk mengumpulkan data dari 170 perguruan tinggi di Indonesia. Penelitian ini menggunakan PLS-SEM untuk mengkaji variabel-variabel yang diamati, ter-masuk pengujian validitas dan reliabilitas, yang mencakup penilaian reliabilitas, validitas konvergen, dan validitas diskriminan. Hasil dari penelitian ini menunjukkan bahwa semua hipotesis diterima dengan nilai p di bawah 0,05. Temuan ini mendorong universitas untuk memberikan perhatian pada aspek kualitas sistem, informasi, dan layanan dalam penggunaan LMS guna meningkatkan kepuasan pengguna dan menciptakan persepsi posi-tif terhadap manfaatnya. Oleh karena itu, penelitian ini memberikan hasil yang signifikan bagi perguruan tinggi di Indonesia serta turut berkontribusi dalam pengembangan ilmu di bidang sistem informasi manajemen.
Kata kunci: delone and mclean; kesuksesan sistem informasi; LMS; SEM-PLS
Abstract:Abstract: The online exam system is used to evaluate student learning, but it has some limitations. Therefore, it is necessary to research the user satisfaction of the system. This study aims to assess user satisfaction…
using the End User Computing Satisfaction (EUCS), Importance Performance Analysis (IPA), and Customer Satisfaction Index (CSI) methods. The results showed that three dimensions, namely, accuracy, ease of use, and timeliness significantly affected user satisfaction, while content and format did not have a significant effect. IPA analysis shows the majority of attributes (12 attributes) are in quadrant II, which indicates moderate satisfaction, 11 attributes in quadrant III, one attribute in quadrant I, and three attributes in quadrant IV. CSI concluded that the online exam system provides satisfactory service with a score of 77.54%.
Keywords: csi; eucs; ipa; online exam system; user satisfaction
Abstrak: Sistem ujian online digunakan untuk mengevaluasi pembelajaran mahasiswa, tetapi sistem ini memiliki beberapa keterbatasan. Karena itulah perlu penelitian kepuasan pengguna sistem tersebut. Penelitian ini bertujuan menilai kepuasan pengguna dengan menggunakan metode End User Computing Satisfaction (EUCS), Importance Performance Analisys (IPA), dan Customer Satisfaction Index (CSI). Hasil riset menunjukkan tiga dimensi yaitu, akurasi, kemudahan penggunaan, dan ketepatan waktu signifikan mempengaruhi kepuasan pengguna, sementara konten dan format tidak berpengaruh signifikan. Analisis IPA menunjukkan mayoritas atribut (12 atribut) berada di kuadran II, yang mengindikasikan kepuasan sedang, 11 atribut di kuadran III, satu atribut di kuadran I, dan tiga atribut di kuadran IV. CSI menyimpulkan sistem ujian online memberikan layanan yang memuaskan dengan skor 77,54%.
Kata kunci: csi; eucs; ipa; kepuasan pengguna; sistem ujian online
Abstract:Abstract: The utilization of Information Technology (IT) in higher education institutions is crucial for supporting academic and administrative activities. The Data and Information Center (PUSDATIN) of UBP Karawang manages…
es various IT services, such as Sistem Informasi Perguruan Tinggi (SIPT), e-learning Buana Online Course (BOC), and others. This study aims to evaluate the maturity level of IT governance at UBP Karawang to ensure alignment with the university's strategic goals and identify areas requiring improvement. The research employs a quantitative descriptive method based on COBIT 2019, with data collected from 92 respondents, analyzed through goals cascade mapping and maturity level measurement. The evaluation results across 14 COBIT 2019 domains indicate that the IT governance maturity level at UBP Karawang is at Level 4 (Quantitatively Managed) with a score of 3.86 and an average gap of 1.13 from the expected level. The findings suggest that while IT governance at UBP Karawang is well-managed, there is still room for improvement. Therefore, several recommendations are proposed to optimize IT governance effectiveness, ensure regulatory compliance, and support the achievement of the university's strategic objectives.
Keywords: COBIT 2019; IT evaluation; IT governance; maturity level.
Abstrak: Pemanfaatan Teknologi Informasi (TI) di perguruan tinggi sangat krusial untuk mendukung aktivitas akademik dan administratif. Pusat Data dan Informasi (PUSDATIN) UBP Karawang mengelola berbagai layanan TI, seperti Sistem Informasi Perguruan Tinggi (SIPT), e-learning Buana Online Course (BOC) dan lain-lain. Penelitian ini bertujuan untuk mengevaluasi tingkat kematangan tata kelola TI di UBP Karawang guna memastikan keselarasan dengan tujuan universitas serta mengidentifikasi area yang memerlukan perbaikan. Penelitian ini menerapkan metode deskriptif kuantitatif berbasis COBIT 2019, dengan data diperoleh dari 92 responden, dianalisis melalui pemetaan goals cascade dan pengukuran maturity level. Hasil evaluasi pada 14 domain COBIT 2019 menunjukkan tingkat kematangan TI UBP Karawang berada di Level 4 (Terkelola secara Kuantitatif) dengan skor 3.86, serta rata-rata gap 1.13 dari tingkat yang diharapkan. Kesimpulan dari penelitian ini mengindikasikan bahwa meskipun tata kelola TI di UBP Karawang telah terkelola dengan baik, masih terdapat ruang untuk perbaikan. Oleh karena itu, beberapa rekomendasi diajukan guna mengoptimalkan efektivitas tata kelola TI, menjamin kepatuhan terhadap regulasi, serta mendukung pencapaian tujuan strategis universitas.
Kata kunci: COBIT 2019; evaluasi TI; maturity level; tata kelola TI.
Abstract:Abstract: Hypertension is one of the chronic diseases that can increase the risk of cardiovascular disease. A healthy diet is an important factor in managing hypertension, but many patients struggle to choose foods that…
are suitable for their condition. Therefore, a decision support system is needed to help patients determine healthy food choices objectively and systematically. This research aims to apply the ELECTRE (Elimination Et Choix Traduisant La Réalité) method in determining healthy foods for hypertension patients. This method is used because it can handle various criteria simultaneously and provide recommendations based on a mathematical approach. Data were obtained from Serozha Clinic through interviews, observations, and literature reviews on the nutritional content of food. The research results show that the ELECTRE method is capable of providing healthy food recommendations with an accuracy level of 90%, higher than the manual technique which only reaches 70%. In addition, the time required in the decision-making process has significantly decreased. Patients also showed a higher level of satisfaction with the proposed system. In conclusion, the ELECTRE method has proven effective in helping hypertension patients choose foods that meet their nutritional needs, and can thus be used as a reference in the development of decision support systems in the health sector.
Keywords: electre method; healthy food; health management; hypertension.
Abstrak: Hipertensi merupakan salah satu penyakit kronis yang dapat meningkatkan risiko penyakit kardiovaskular. Pola makan yang sehat menjadi faktor penting dalam pengelolaan hipertensi, namun banyak pasien kesulitan dalam memilih makanan yang sesuai dengan kondisi mereka. Oleh karena itu, diperlukan sistem pendukung keputusan yang dapat membantu pasien dalam menentukan pilihan makanan sehat secara objektif dan sistematis. Penelitian ini bertujuan untuk menerapkan metode ELECTRE (Elimination Et Choix Traduisant La Realite) dalam menentukan makanan sehat bagi penderita hipertensi. Metode ini digunakan karena mampu menangani berbagai kriteria secara simultan dan memberikan rekomendasi berdasarkan pendekatan matematis. Data diperoleh dari Klinik Serozha melalui wawancara, observasi, serta tinjauan literatur mengenai kandungan gizi makanan.Hasil penelitian menunjukkan bahwa metode ELECTRE mampu memberikan rekomendasi makanan sehat dengan tingkat akurasi 90%, lebih tinggi dibandingkan teknik manual yang hanya mencapai 70%. Selain itu, waktu yang dibutuhkan dalam proses pengambilan keputusan berkurang secara signifikan. Pasien juga menunjukkan tingkat kepuasan yang lebih tinggi terhadap sistem yang diusulkan.Kesimpulannya, metode ELECTRE terbukti efektif dalam membantu penderita hipertensi memilih makanan yang sesuai dengan kebutuhan gizi mereka, sehingga dapat digunakan sebagai referensi dalam pengembangan sistem pendukung keputusan di bidang kesehatan.
Kata kunci: hipertensi; makanan sehat; metode electre; pengelolaan kesehatan.