Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Darma Diksani: Jurnal Pengabdian Ilmu Pendidikan, Sosial, dan Humaniora Jurnal Computer and Technology
Wenti Ayu Wahyuni
Universitas Teknologi Mataram
Computer Science & IT Languange, Linguistic, Communication & Media Social Sciences Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Meraih Keunggulan Kompetitif dalam Lomba Desa Wisata melalui Pelatihan IT bagi Aparat Desa Batu Kumbung: Achieving Competitive Advantage in the Tourism Village Competition through IT Training for Village Officials of Batu Kumbung Juhartini Juhartini; Wenti Ayu Wahyuni; Dwinita Arwidiyarti
DARMADIKSANI Vol 6 No 2 (2026): Edisi Juni
Publisher : Jurusan Pendidikan Bahasa dan Seni, FKIP, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/darmadiksani.v6i2.9949

Abstract

Desa Batu Kumbung terletak di kecamatan Lingsar, kabupaten Lombok Barat yang berada di daerah yang subur dengan sumber air yang melimpah. Aplikasi Jaringan Desa Wisata (Jadesta) merupakan platform pengumpulan dan analisis data profil untuk menentukan klasifikasi desa wisata. Aplikasi ini diharapkan dapat menjadi platform pendukung pengembangan data pariwisata nasional sebagai kontribusi data untuk mendukung kegiatan pengembangan desa wisata. Keberhasilan pelatihan ini didasarkan pada dua indikator yang terukur dan nyata antara lain: Keterukuran pertama dilihat pada saat tim PkM melakukan kegiatan pelatihan, keterukuran reaksi peserta ketika mengikuti kegiatan tersebut sangat tinggi dan memberikan hasil praktis yang sangat baik dengan cepat. Keterukuran yang kedua, yakni meningkatnya keterampilan para aparat desa dari pelatihan yang diberikan. Tahapan program dilaksanakan melalui tahap sosialisasi, pelatihan, dan pengenalan perkembangan teknologi informasi dan metode operasional pengolahan data komputer. Pelatihan bertujuan untuk membantu staf desa mitra memahami teknologi informasi, jenis-jenisnya, dan cara mengoperasikan aplikasi Jadesta. Pemahaman yang baik diharapkan akan meningkatkan kemampuan aparat desa dalam memanfaatkan teknologi informasi dalam aktivitas sehari-hari untuk melaksanakan tugas administrasi desa dan memberikan pelayanan kepada masyarakat. Sesuai dengan saran kepala desa Batu Kumbung, program PkM selanjutnya diharapkan mencakup pembahasan lebih mendalam mengenai penerapan aplikasi Jadesta dan pelatihan berbasis teknologi informasi lainnya.
A Leakage-Aware Ensemble Framework for Imbalanced Tabular Data: Mitigating SMOTE Contamination in Hotel Cancellation Prediction Gibran Maulana Syamroni; Bahtiar Imran; Surni Erniwati; Zaeniah; Wenti Ayu Wahyuni
Journal Computer and Technology Vol. 4 No. 1 (2026): July 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/comtechno.v4i1.514

Abstract

Predictive modeling on large-scale, imbalanced tabular data is frequently compromised by target leakage and improper resampling, leading to inflated performance metrics. While tree-based ensemble methods like Random Forest (RF) and XGBoost are widely deployed, their architectural divergence in handling complex behavioral anomalies under strict class imbalance remains underexplored. This study proposes a leakage-aware ensemble framework to mitigate SMOTE contamination and target leakage in hotel cancellation prediction. Using a rigorous CRISP-DM pipeline on 119,390 records, we applied SMOTE exclusively to the training set and engineered six behavioral features to capture non-linear contradictions, such as the counter-intuitive 99.36% cancellation rate in non-refund deposits. We systematically benchmarked RF (bagging) against XGBoost (boosting) using stratified 5-fold cross-validation, hyperparameter optimization, and loss curve monitoring. Results demonstrate that XGBoost structurally outperforms RF in minority-class detection, achieving superior Recall (0.6659), F1-Score (0.6607), and AUC-ROC (0.8657), with significantly lower variance (0.0035). Conversely, RF exhibited higher Precision (0.6588) and better cross-validation stability during hyperparameter search. Crucially, feature importance analysis revealed a structural divergence: RF prioritized temporal variables (lead_time), while XGBoost emphasized behavioral commitment signals (parking, special requests). These findings confirm that gradient boosting’s sequential residual-correction mechanism is inherently more robust than variance-reduction bagging for imbalanced tabular data containing complex, non-linear anomalies. The proposed leakage-free framework not only resolves methodological flaws in prior studies but also provides a reliable, proactive risk-scoring foundation for integrating real-time decision support systems in production environments.
Co-Authors Arwidiyarti, Dwinita erniwati, surni Gibran Maulana Syamroni Imran, Bahtiar Zaeniah