Abstract:Divorce is a social phenomenon whose rate continues to rise in various regions of Indonesia and has become a shared concern for both the government and society, since it may give rise to social, psychological, and economic…
ic consequences for the individuals and families involved. Divorce is generally caused by several interrelated factors, namely economic problems, continuous domestic disputes, infidelity, and domestic violence (KDRT). This study aims to apply the K-Nearest Neighbor (KNN) algorithm to classify the level of divorce (Low, Medium, and High) based on these four causal factors. The data used are secondary data obtained from the Central Bureau of Statistics (BPS) covering ten provinces on Sumatra Island for the 2023-2025 period. Prior to classification, the data were normalized using the Min-Max Normalization method so that every attribute shared a comparable value range. The dataset was divided into 20 training data (2023-2024) and 10 testing data (2025), with the value of K determined using the formula K = √n, resulting in K = 5. The classification process was carried out by calculating the Euclidean Distance between the testing data and the entire training data, then determining the predicted class through majority voting among the five nearest neighbors. The classification model was implemented in a web-based application built with PHP and MySQL that supports dataset import, data normalization, KNN computation, and classification result display. The test results on the ten testing data for 2025 show that the system achieved an overall accuracy of 70%, with the best performance obtained for the Low class (recall of 100%), while the Medium and High classes still experienced misclassification due to the limited amount of training data in those classes. These results indicate that the KNN algorithm is capable of recognizing divorce patterns based on their causal factors and can be used as a decision-support tool related to the analysis of divorce rates on Sumatra Island.
Abstract:Managing Tjong A Fie Museum as a historical tourism destination requires human resources who are not only technically competent but also able to internalize and convey local wisdom values to visitors. This study focuses…
on analyzing human resource development strategies based on local wisdom and identifying local values that can serve as a foundation for enhancing museum staff competence. A descriptive qualitative approach was employed. Three tour guides and two tourist were selected as informants through purposive sampling, with data collected through semi-structured interviews, observation, and documentation. Data analysis followed the interactive model of Miles, Huberman, and Saldana, while data validity was examined through source and technique triangulation. The findings reveal that guides' competence development has largely relied on informal peer-to-peer learning, whereas actual training needs include storytelling skills, public speaking, cross-language communication, and field situation management. Local wisdom values embedded in the museum's history religious and ethnic tolerance, the spirit of gotong royong (mutual/communal cooperation), social concern, work ethic, and the blend of Chinese, Malay, and European cultures are considered highly relevant as training content. The museum is advised to develop a documented training system grounded in these values to ensure the authenticity and sustainability of the historical tourism services offered
Abstract:Weather observation data produced by the Meteorology, Climatology and Geophysics Agency (BMKG) has multivariate characteristics, so it requires an analysis method that is able to identify patterns based on similarities in…
n data characteristics. This research aims to analyze and visualize daily and monthly weather parameter patterns in the East Jakarta area using the K-Means Clustering algorithm. The dataset used is daily observation data from the Halim Perdanakusuma Meteorological Station for the period January–December 2025, totaling 365 observations with six meteorological parameters, namely TN, TX, TAVG, RH_AVG, RR, and FF_AVG. The research stages include merging data, handling missing values using median imputation, data normalization using StandardScaler, data exploration, determining the optimal number of clusters using the Elbow Method and Silhouette Score, followed by the clustering process using K-Means. The evaluation results show that there are three optimal clusters (K=3), which represent variations in the daily weather characteristics of East Jakarta. The clustering results identified different characteristics, namely Cluster 0 (Hot Dry Weather), Cluster 1 (Cool Cloudy Weather), and Cluster 2 (Heavy Rainy Weather). Visualization in the form of correlation heatmaps, time series graphs, scatter plots, box plots and bar charts provide informative representations of weather parameter distribution patterns, making it easier to interpret analysis results. This research proves that K-Means Clustering is used as an effective exploratory method for identifying weather parameter patterns and visualization of meteorological analysis.
Abstract:Inventory management is a major challenge in the clothing retail business. Toko Saing as a clothing retail business still performs manual stock recording, causing risks of overstock and stockout. This study aims to apply…
the Random Forest algorithm to predict stock availability and optimize marketing of clothing products. Historical sales data for 6 months (October 2024 - March 2025) was used as the training dataset. The prediction system was built web-based using PHP and MySQL. The test results show that the Random Forest algorithm is able to predict stock needs with an average accuracy of 77.3% (R²) and Mean Absolute Error (MAE) of 0.6 pcs. The developed system has successfully helped Toko Saing in managing stock more efficiently and providing data-based marketing recommendations. This study proves that Random Forest is effectively applied to stock prediction problems in retail goods
Abstract:Abstract: The Rejang Penuntun dance training, involving students and the local community in the area of Pura Luhuran Bingin Banjar Kedaton, Sumerta Kelod Village, is part of the dance transmission process linked to the Purnama…
urnama Kapat. This study aims to describe the application of the drill method in the Rejang Penuntun dance training and the changes in participants' abilities following the training process. A qualitative descriptive method was employed, utilizing data collection techniques such as observation, interviews, and documentation. Data analysis involved data reduction, data presentation, and conclusion drawing. The results indicate that the drill method was implemented through training sessions that were gradual, repetitive, and focused, tailored to the material and the participants' capabilities. The process encompassed demonstrations, practice, repetition, correction, and reinforcement, conducted both individually and in groups. The repetitive practice led to observable improvements in participants' abilities, including faster responses to instructions, increased fluency during training, greater consistency in performance, and growing self-confidence in participating in collective activities. The involvement of the Banjar Kedaton community (Sumerta Kelod Village) supported the training process by providing a learning environment closely integrated with community life and by involving participants in preparations for the Rejang Penuntun dance performance at Pura Luhuran Bingin. The findings demonstrate that the drill method effectively supports Rejang Penuntun dance training by fostering a habit of continuous practice aligned with participants' needs and the requirements of the dance performance within the supporting community.
Keyword: dance training; Rejang Penuntun; drill method; Pura Luhuran Bingin.
Abstrak: Pelatihan Tari Rejang Penuntun yang melibatkan peserta didik dan masyarakat di kawasan Pura Luhuran Bingin, Banjar Kedaton, Desa Sumerta Kelod merupakan bagian dari proses pewarisan tari yang berkaitan dengan pelaksanaan piodalan Purnama Kapat. Penelitian ini bertujuan untuk mendeskripsikan penerapan metode drill dalam pelatihan Tari Rejang Penuntun serta perubahan kemampuan peserta setelah mengikuti proses pelatihan. Penelitian ini menggunakan metode deskriptif kualitatif dengan teknik pengumpulan data berupa observasi, wawancara, dan dokumentasi. Data dianalisis melalui reduksi data, penyajian data, dan penarikan kesimpulan. Hasil penelitian menunjukkan bahwa penerapan metode drill dalam pelatihan Tari Rejang Penuntun berlangsung melalui latihan yang dilakukan secara bertahap, berulang, dan terarah dengan menyesuaikan materi serta kemampuan peserta. Proses tersebut mencakup pemberian contoh, praktik, pengulangan, koreksi, dan pemantapan yang dilaksanakan secara perorangan maupun kelompok. Penerapan latihan secara berulang diikuti perubahan kemampuan peserta yang terlihat dari semakin cepatnya respons terhadap arahan, meningkatnya kelancaran dalam mengikuti pelatihan, semakin stabilnya hasil latihan, serta berkembangnya kepercayaan diri peserta dalam mengikuti kegiatan bersama. Keterlibatan masyarakat Banjar Kedaton, Desa Sumerta Kelod turut memberikan dukungan terhadap proses pelatihan melalui lingkungan belajar yang dekat dengan kehidupan masyarakat dan keterlibatan peserta dalam persiapan pelaksanaan Tari Rejang Penuntun di Pura Luhuran Bingin. Hasil penelitian memperlihatkan bahwa metode drill dapat mendukung proses pelatihan Tari Rejang Penuntun melalui pembiasaan latihan yang dilakukan secara berkelanjutan sesuai dengan kebutuhan peserta dan pelaksanaan tari di lingkungan masyarakat pendukungnya.
Kata kunci: pelatihan tari; Rejang Penuntun; metode drill.
Abstract:Abstract: This study forecasts monthly solid-waste retribution revenue at the Solok Regional Landfill using Holt's Double Exponential Smoothing. The database contained 72,000 transactions from two landfills. After selecting…
ing the location and study period, checking transaction status, and removing nonpositive values, 44,864 valid transactions were aggregated into 44 monthly observations from January 2023 to August 2026. January 2023-December 2025 served as training data and January-August 2026 as a temporal holdout. Parameters were selected from 9,801 alpha-beta pairs by minimizing training MAPE. The selected model used alpha=0.73 and beta=0.24. On the holdout, it achieved a MAPE of 9.82%, an MAE of IDR 4.29 million, and an RMSE of IDR 4.74 million, outperforming the 11.77% MAPE of a naive benchmark. After refitting all observations, the September 2026-August 2027 forecasts totaled IDR 695.75 million. The model provides a quantitative baseline for revenue planning, although its linear trend extrapolation requires cautious interpretation.
Keyword: double exponential smoothing; Holt; revenue forecasting; solid-waste retribution; landfill
Abstrak: Penelitian ini bertujuan meramalkan pendapatan retribusi bulanan TPA Regional Solok menggunakan Holt Double Exponential Smoothing. Basis data memuat 72.000 transaksi dari dua TPA. Setelah seleksi lokasi dan periode, pemeriksaan status transaksi, serta penghapusan nilai nonpositif, diperoleh 44.864 transaksi valid yang diagregasi menjadi 44 observasi bulanan Januari 2023-Agustus 2026. Data Januari 2023-Desember 2025 digunakan untuk pelatihan dan Januari-Agustus 2026 sebagai holdout temporal. Parameter dipilih dari 9.801 pasangan alpha-beta dengan meminimalkan MAPE pelatihan. Model terpilih menggunakan alpha=0,73 dan beta=0,24. Pada holdout, model menghasilkan MAPE 9,82%, MAE Rp4,29 juta, dan RMSE Rp4,74 juta, lebih baik daripada baseline naif dengan MAPE 11,77%. Setelah estimasi ulang menggunakan seluruh observasi, total prakiraan September 2026-Agustus 2027 mencapai Rp695,75 juta. Model dapat menjadi baseline kuantitatif untuk perencanaan penerimaan, tetapi ekstrapolasi tren linearnya perlu ditafsirkan secara hati-hati.
Kata kunci: double exponential smoothing; Holt; peramalan pendapatan; retribusi persampahan; tempat pemrosesan akhir
Abstract:Abstract: This study aims to analyze and optimize heart disease risk prediction using Random Forest and XGBoost algorithms combined with feature selection. The dataset used is the Cleveland Heart Disease Dataset, comprising…
ing 303 patient records, 13 predictor features, and a target variable converted into a binary classification. The research stages include preprocessing, data splitting using a stratified train-test split, feature selection, hyperparameter tuning, and evaluation based on accuracy, precision, recall, F1-score, and ROC-AUC. Feature selection yielded eight selected features—thal, cp, thalach, ca, oldpeak, exang, chol, and slope—resulting in a 38.46% reduction in the total number of features. Test results indicate that the Optimized Random Forest model combined with feature selection achieved the best performance, with an accuracy of 91.80%, precision of 89.66%, recall of 92.86%, F1-score of 91.23%, and ROC-AUC of 95.67%.
Keywords: Heart Disease, Random Forest, XGBoost, Feature Selection, Hyperparameter Tuning.
Abstrak: Penelitian ini bertujuan menganalisis dan mengoptimalkan prediksi risiko penyakit jantung menggunakan algoritma Random Forest dan XGBoost berbasis feature selection. Dataset yang digunakan adalah Cleveland Heart Disease Dataset yang terdiri atas 303 data pasien, 13 fitur prediktor, dan satu target yang dikonversi menjadi klasifikasi biner. Tahapan penelitian meliputi preprocessing, pembagian data menggunakan stratified train-test split, feature selection, hyperparameter tuning, serta evaluasi menggunakan accuracy, precision, recall, F1-score, dan ROC-AUC. Feature selection menghasilkan 8 fitur terpilih, yaitu thal, cp, thalach, ca, oldpeak, exang, chol, dan slope, sehingga jumlah fitur berkurang sebesar 38,46%. Hasil pengujian menunjukkan bahwa Optimized Random Forest + Feature Selection memberikan performa terbaik dengan accuracy 91,80%, precision 89,66%, recall 92,86%, F1-score 91,23%, dan ROC-AUC 95,67%.
Kata Kunci: Penyakit Jantung, Random Forest, XGBoost, Feature Selection, Hyperparameter Tuning.
Abstract:Abstract: Digital fraud through short messages has become a national problem in Indonesia; the Indonesia Anti-Scam Centre recorded 637,055 reports with losses of IDR 9.1 trillion up to July 2026. Scam messages are hard to…
o filter with keywords because perpetrators keep changing wording and phone numbers, while official promotional messages share similar linguistic patterns. This study aims to optimize a three-class classifier (normal, fraud, promotion) for Indonesian messages by combining XGBoost, SMOTE, and Bayesian Optimization based on the Tree-structured Parzen Estimator (TPE), and to compare TPE with Grid Search and Random Search under an equal budget of 25 trials. Messages were normalized (URLs, phone numbers, amounts, and slang) and represented with combined word and character n-gram TF-IDF features. On 2,320 messages, XGBoost + SMOTE + TPE achieved a macro F1 of 0.9555, an accuracy of 96.34%, and a fraud-class recall of 0.9507, slightly higher than default XGBoost (F1 0.9531) and Grid Search (F1 0.9529), with a much lighter model that trained 3.2 times faster. Grid Search showed overfitting to the validation folds. The ablation study showed that SMOTE did not help under moderate class imbalance (F1 without SMOTE 0.9581), and Multinomial Naïve Bayes remained the best model (F1 0.9693). Most errors occurred between fraud and promotional messages.
Keywords: Digital Fraud, Text Classification, XGBoost, Bayesian Optimization, SMOTE
Abstrak: Penipuan digital melalui pesan singkat telah menjadi masalah nasional; Indonesia Anti-Scam Centre mencatat 637.055 laporan dengan kerugian Rp9,1 triliun hingga Juli 2026. Pesan penipuan sulit disaring dengan kata kunci karena pelaku terus mengubah variasi kata dan nomor telepon, sementara pesan promosi resmi memiliki pola bahasa yang mirip. Penelitian ini bertujuan mengoptimasi model klasifikasi tiga kelas (normal, penipuan, promo) untuk pesan berbahasa Indonesia dengan menggabungkan XGBoost, SMOTE, dan Bayesian Optimization berbasis Tree-structured Parzen Estimator (TPE), serta membandingkan TPE dengan Grid Search dan Random Search pada anggaran yang sama, yaitu 25 percobaan. Pesan dinormalisasi (tautan, nomor telepon, nominal, dan kata tidak baku) lalu direpresentasikan dengan fitur TF-IDF gabungan n-gram kata dan karakter. Pada 2.320 pesan, XGBoost + SMOTE + TPE mencapai F1-macro 0,9555, akurasi 96,34%, dan recall kelas penipuan 0,9507, sedikit lebih tinggi daripada XGBoost default (F1 0,9531) dan Grid Search (F1 0,9529), dengan model yang jauh lebih ringan dan waktu pelatihan 3,2 kali lebih cepat. Grid Search menunjukkan gejala overfitting terhadap fold validasi. Uji ablasi menunjukkan SMOTE tidak membantu pada ketidakseimbangan kelas moderat (F1 tanpa SMOTE 0,9581), dan Multinomial Naïve Bayes tetap menjadi model terbaik (F1 0,9693). Sebagian besar kesalahan terjadi antara pesan penipuan dan promo.
Kata Kunci: Penipuan Digital, Klasifikasi Teks, XGBoost, Bayesian Optimization, SMOTE.
Abstract:This study aims to analyze the role of digital sustainability accounting and environmental, social, and governance (ESG) practices in supporting the achievement of the Sustainable Development Goals (SDGs) through enhanced…
d transparency, accountability, and financial inclusion in the era of digital transformation. This study employs a qualitative method using a literature review approach based on relevant scientific publications, sustainability reports, and regulatory documents. The findings indicate that digital transformation in sustainability accounting practices can improve the collection, processing, and reporting of ESG information in a more transparent and accountable manner. The use of digital technology also supports broader access to financial services, thereby contributing to financial inclusion and the achievement of the SDGs. The study concludes that the integration of digital sustainability accounting and ESG practices is an important strategy for strengthening transparency, accountability, and financial inclusion. However, successful implementation requires supportive regulations, technological readiness, competent human resources, and strong commitment from relevant stakeholders
Abstract:Abstract: This study aims to analyze human resource management at the Tambelang District Community Health Center (Puskesmas) in the context of delivering public health services. A qualitative approach with a case study design…
esign was employed. Data were collected through interviews, observations, and document analysis, involving nine informants: seven from the health center and two from the community/patient group. The analysis utilized Hasibuan’s (2016) Human Resource Management theory, covering planning, organizing, directing, controlling, and human resource development. The results indicate that HR management at the Tambelang District Health Center has been implemented through workforce planning based on workload, population size, service coverage area, and the specific needs of each unit. Organizing is carried out through task allocation and staff placement based on competence and areas of expertise, accompanied by inter-unit coordination during service delivery. Direction is provided routinely through morning assemblies, briefings, coordination meetings, guidance, and staff motivation. Control is exercised through monitoring task execution and discipline, as well as evaluating service quality. Meanwhile, HR development is conducted through training and guidance activities organized by both the health center and the Health Office. Although various HR management functions are operational, several challenges persist—particularly the limited number and types of specific health personnel, as well as increased workloads during surges in patient numbers or when staff conduct outreach activities outside the facility. These conditions can affect service efficiency, specifically patient waiting times. Therefore, strengthening workforce provision and workload management remains necessary to ensure that HR management can more optimally support public health service delivery.
Keywords: Human Resource Management, Community Health Center (Puskesmas), Public Service, Health Service.
Abstrak: Penelitian ini bertujuan untuk menganalisis manajemen sumber daya manusia di Puskesmas Kecamatan Tambelang dalam memenuhi pelayanan publik di bidang kesehatan. Penelitian menggunakan pendekatan kualitatif dengan desain studi kasus. Data diperoleh melalui wawancara, observasi, dan dokumentasi dengan melibatkan sembilan informan yang terdiri atas tujuh informan dari pihak Puskesmas dan dua informan dari masyarakat/pasien. Analisis dilakukan menggunakan teori Manajemen Sumber Daya Manusia menurut Hasibuan (2016) yang meliputi perencanaan, pengorganisasian, pengarahan, pengawasan, dan pengembangan sumber daya manusia. Hasil penelitian menunjukkan bahwa manajemen SDM di Puskesmas Kecamatan Tambelang telah dilaksanakan melalui perencanaan kebutuhan tenaga berdasarkan beban kerja, jumlah penduduk, cakupan wilayah pelayanan, serta kebutuhan masing-masing unit. Pengorganisasian dilakukan melalui pembagian tugas dan penempatan pegawai berdasarkan kompetensi dan bidang keahlian, disertai koordinasi antarunit dalam pelaksanaan pelayanan. Pengarahan dilakukan secara rutin melalui apel pagi, briefing, rapat koordinasi, pembinaan, dan pemberian motivasi kepada pegawai. Pengawasan dilakukan melalui pemantauan terhadap pelaksanaan tugas, kedisiplinan, serta evaluasi pelayanan. Sementara itu, pengembangan SDM dilakukan melalui kegiatan pelatihan dan pembinaan yang diselenggarakan oleh Puskesmas maupun Dinas Kesehatan. Meskipun berbagai fungsi manajemen SDM telah berjalan, masih terdapat beberapa kendala, terutama keterbatasan jumlah dan jenis tenaga kesehatan tertentu serta beban kerja yang meningkat ketika jumlah pasien bertambah atau tenaga kesehatan melaksanakan kegiatan di luar gedung. Kondisi tersebut dapat memengaruhi kelancaran pelayanan, khususnya waktu tunggu pasien. Dengan demikian, penguatan pemenuhan kebutuhan tenaga dan pengelolaan beban kerja masih diperlukan agar manajemen SDM dapat mendukung pelayanan publik di bidang kesehatan secara lebih optimal.
Kata kunci: Manajemen Sumber Daya Manusia, Puskesmas, Pelayanan Publik, Pelayanan Kesehatan.