Articles
Comparative Study of Imbalanced Data Oversampling Techniques for Peer-to-Peer Landing Loan Prediction
Muzayanah, Rini;
Lestari, Apri Dwi;
Jumanto, Jumanto;
Prasetiyo, Budi;
Pertiwi, Dwika Ananda Agustina;
Muslim, Much Aziz
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/sji.v11i1.50274
Purpose: Data imbalances that often occur in the classification of loan data on the Peer-to-Peer Lending platform cancause algorithm performance to be less than optimal, causing the resulting accuracy to decrease. To overcome thisproblem, appropriate resampling techniques are needed so that the classification algorithm can work optimally andprovide results with optimal accuracy. This research aims to find the right resampling technique to overcome theproblem of data imbalance in data lending on peer-to-peer landing platforms.Methods: This study uses the XGBoost classification algorithm to evaluate and compare the resampling techniquesused. The resampling techniques that will be compared in this research include SMOTE, ADACYN, Border Line, andRandom Oversampling.Results: The highest training accuracy was achieved by the combination of the XGBoost model with the Boerder Lineresampling technique with a training accuracy of 0.99988 and the combination of the XGBoost model with the SMOTEresampling technique. In accuracy testing, the combination with the highest accuracy score was achieved by acombination of the XGBoost model with the SMOTE resampling technique.Novelty: It is hoped that from this research we can find the most suitable resampling technique combined with theXGBoost sorting algorithm to overcome the problem of unbalanced data in uploading data on peer-to-peer lendingplatforms so that the sorting algorithm can work optimally and produce optimal accuracy.
Penguatan Prestasi Mahasiswa Melalui Pendampingan dan Pembinaan Lembaga Kemahasiswaan di Jurusan Ilmu Komputer UNNES
Subhan, Subhan;
Jumanto;
Hakim, M Faris Al;
Ifriza, Yahya Nur;
Prasetiyo, Budi
Jurnal Abdi Negeri Vol 1 No 1 (2023): Januari 2023
Publisher : Informa Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.63350/jan.v1i1.2
Prestasi mahasiswa menjadi bagian penting dari perguruan tinggi yang perlu dikuatkan. Pada kegiatan ini, penulis melakukan penguatan prestasi mahasiswa melalui pendampingan dan pembinaan lembaga kemahasiswaan. Permasalahan prioritas utama yang dihadapi lembaga kemahasiswaan adalah kurangnya pemanduan bakat mahasiswa dan kurangnya pembinaan bahasa inggris untuk presentasi dalam kompetisi. Sehingga solusi yang ditawarkan adalah peningkatan sikap sadar prestasi mahasiswa, pendampingan bakat mahasiswa, serta peningkatan kapasitas presentasi dan bahasa inggris. Solusi tersebut diwujudkan menggunakan model pembinaan sekolah prestasi yang terdiri dari 4 bentuk kegiatan. Metode pelaksanaan dengan pendekatan permasalahan yang melibatkan partisipasi aktif mitra. Bentuk kegiatan terdiri dari: (1) Pembentukan sekolah prestasi; 2) Workshop motivasi berprestasi; (3) Bimtek pembuatan media presentasi untuk kompetisi (4) Pelatihan presentasi bahasa inggris untuk kompetisi. Hasil kegiatan ini, lembaga kemahasiswaan sangat terbantu dengan penataan kegiatan kemahasiswaan. Mahasiswa lebih terarah dalam menargetkan prestasi yang ditargetkan.
Peningkatan Manajemen Ujian Online Bagi Guru di SMK Negeri 1 Karimunjawa
Prasetiyo, Budi;
Hakim, M. Faris Al;
Purwinarko, Aji;
Putra, Anggyi Trisnawan;
Subhan, Subhan
Jurnal Abdi Negeri Vol 1 No 1 (2023): Januari 2023
Publisher : Informa Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.63350/jan.v1i1.3
Program Pembelajaran dan Penilaian online di era pandemi COVID-19 saat ini telah berlangsung selama satu tahun di SMK Negeri 1 Karimunjawa. Penerapan e-learning di sekolah ini berdampak pada bertambahnya tuntutan peningkatan kompetensi guru dalam melakukan penilaian secara online. Bagi siswa, tentu akan berdampak terhadap cara mereka mengikuti ujian di sekolah. Siswa harus membiasakan diri untuk menggunakan fitur-fitur yang terdapat pada aplikasi e-learning. Berdasarkan hasil komunikasi dan observasi dengan Kepala SMK Negeri 1 Karimunjawa, dibutuhkan aplikasi yang efektif untuk digunakan dalam penyelenggaraan penilaian atau ujian online untuk siswa. Aplikasi Ujian online juga diharapkan dapat digunakan untuk simulasi Asesmen Kompetensi Minimal (AKM) pada tahun pelajaran 2021/2022. Oleh karena itu, Jurusan Ilmu Komputer, FMIPA, UNNES menawarkan solusi berupa penerapan aplikasi e-ujian yang merupakan produk penelitian yang telah memiliki hak cipta. Metode yang digunakan dalam kegiatan pengabdian ini terdiri dari 3 tahap yaitu Analisis Kebutuhan, Perancangan Aplikasi, Pengembangan Aplikasi, Pelaksanaan, dan Evaluasi. Hasil dari kegiatan pengabdian masyarakat yang telah dilaksanakan adalah pengurus sekolah dan guru memahami potensi dari manajemen ujian berbasis daring untuk pembelajaran di masa pandemi sebagai upaya untuk menjaga standar proses pembelajaran.
Perancangan Mesin Pengolah Limbah Sabut Kelapa Bernilai Ekonomis
Prasetiyo, Budi;
Baroroh, Niswah;
Roziqin, Ahmad
Jurnal Abdi Negeri Vol 1 No 2 (2023): September 2023
Publisher : Informa Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.63350/jan.v1i2.7
Limbah sabut kelapa yang selama ini tidak dimanfaatkan dan hanya dibakar dapat diolah menjadi produk bernilai ekonomis. Pengolahan limbah sabut kelapa perlu dilakukan dengan bantuan suatu mesin. Pada pengabdian ini di rancang suatu mesin pengolah limbah sabut kelapa menjadi produk berupa serat sabut bernilai ekonomis. Metode yang digunakan yaitu mulai dari analisis kebutuhan, kemudian perancangan desain alat, pengembangan alat, pengujian dan implementasi. Pada analisis kebutuhan dilakukan observasi untuk penggalian informasi mengenai spesifikasi alat yang dibutuhkan. Selanjutnya dilakukan desain model secara 3 dimensi. Pengembangan alat dilakukan di workshop. Selanjutnya dilakukan pengujian dan di implementasikan. Hasil yang diperoleh yaitu berupa desain konsep alat serta pengembangan mesin pengolah sabut yang baru.
Pengaruh Sales Growth, Inventory dan Operating Capacity Terhadap Cash Holding
Prasetiyo, Budi;
Fitria, Yunita
Jurnal Akuntansi dan Governance Andalas Vol. 4 No. 1 (2021): JURNAL AKUNTANSI DAN GOVERNANCE ANDALAS
Publisher : Unand Press
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.25077/jaga.v4i1.64
This study aims to determine the effect of sales growth, inventory, and operating capacity on cash holding in mining companies listed on the Indonesia Stock Exchange. The sample was determined based on the purposive sampling method of 31 companies during 2015-2019. The data source used is in the form of financial reports for 2015-2019 and 2014 financial reports are needed to help calculate the sales growth variable so that 155 data are obtained. Data is obtained from Indonesian Stoke Exchange (IDX). Data analysis techniques used Multiple Linear Regression. The results of this study indicated that the sales growth and inventory variables had a negative and insignificant effect on cash holding and operating capacity had a significant positive effect on cash holding
Enhancing Sleep Disorder Prediction Through Feature Engineering and Stacking Ensemble Learning on Imbalanced Lifestyle Data
Julianto, Richy;
Prasetiyo, Budi
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35314/mzd3t096
Undiagnosed sleep disorders pose significant cardiovascular risks, necessitating accessible screening tools beyond invasive clinical procedures. This study aims to develop a robust diagnostic framework using the Sleep Health and Lifestyle Dataset. To address class imbalance and enhance predictive sensitivity, a Stacking Ensemble architecture integrating Random Forest, Gradient Boosting, CatBoost, and XGBoost is implemented, augmented by Pulse Pressure feature engineering and the Synthetic Minority Over-sampling Technique (SMOTE). The proposed model achieved a superior accuracy of 98.61% and a recall of 99.24%, significantly outperforming single classifiers. Feature analysis further identified heart rate and sleep duration as critical physiological determinants. These findings conclude that combining feature engineering with optimized ensemble learning offers a highly accurate diagnostic approach with rapid training convergence, providing a scalable pathway for early sleep disorder detection.
Pengaruh Promosi Dan Harga Terhadap Keputusan Pembelian Melalui Citra Merek Sebagai Variabel Mediasi Pada Smartphone Xiaomi Di Indonesia
Ulhaq, Moch Daffa Dhiya;
Wardhana, Aditya;
Prasetiyo, Budi
eProceedings of Management Vol. 12 No. 6 (2025): Desember 2025
Publisher : eProceedings of Management
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Penelitian ini dilaksanakan melalui tujuan agar dapat mengetahui seberapa jauh pengaruh promosi beserta harganyakepada keputusan pembelian smartphone Xiaomi di Indonesia, dengan citra merek sebagai variabel yang memediasihubungan tersebut. Latar belakang penelitian ini berangkat dari tingginya tingkat persaingan di industri smartphone,khususnya di pasar Indonesia, serta pentingnya strategi pemasaran dalam memengaruhi perilaku konsumen.Metodeyang digunakan pada melaksanakan penelitian ini yaitu melalui pendekatan kuantitatif yang memakai metodeanalisis dengan penggunaan PLS ataupun kepanjangannya “Partial Least Square”. Data dikumpulkan melaluipenyebaran kuesioner terhadap seluruh 100 respondennya dengan berupa pengguna maupun yang pernah membelismartphone Xiaomi. Hasil penelitian menampilkan bahwasanya promosi beserta harga memengaruhi dengan positifkepada adanya keputusan pembelian, bisa dengan ataupun tidak langsung melalui citra mereknya. Pada citra mereksendiri dimiliki juga pengaruh yang positif terhadap adanya keputusan pembelian serta terbukti mampu menjadivariabel mediasi dalam hubungan antara promosi beserta harga kepada adanya keputusan pembelian. Berdasarkantemuan ini, dapat disimpulkan bahwasanya promosi yang menarik, harga yang kompetitif, dan citra merek denganterbilang kuat merupakan suatu faktor penting yang dapat memberikan dorongan kepada konsumen agar melakukanpembelian.Kata kunci: Promotion, Price, Brand Image, Purchase Decision, Xiaomi.
Optimalisasi Podcast BISIK dalam Memperkuat Citra dan Preferensi Masyarakat Jawa Barat terhadap RSUD Welas Asih
Marshanda, Ghea;
Prasetiyo, Budi
Jurnal Relevansi : Ekonomi, Manajemen dan Bisnis Vol 9 No 2 (2025): Jurnal Relevansi : Ekonomi, Manajemen dan Bisnis
Publisher : LPPM STIE KRAKATAU
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.61401/relevansi.v9i2.361
The transformation of digital media has driven a shift in communication strategies within the healthcare service sector, including public hospitals that continue to face challenges in shaping public preferences. RSUD Welas Asih, as one of the public hospitals in West Java, has adopted digital promotion through the live streaming podcast program BISIK (Bincang Sehat Asik) as a medium for health education and the dissemination of health-related information to the public. This study aims to examine the effect of digital promotion through the BISIK program on public preferences toward RSUD Welas Asih, as well as to examine the role of brand image as an intervening variable. This research employs a quantitative approach with a causal research design. Data were collected through the distribution of questionnaires to members of the public who had been exposed to the BISIK program. Data analysis was conducted using the Partial Least Squares–Structural Equation Modeling (PLS-SEM) method to test both direct and indirect relationships among the research variables. The results indicate that digital promotion through the BISIK live streaming podcast has a positive and significant effect on public preferences toward RSUD Welas Asih. Furthermore, brand image is proven to function as a mediating variable that strengthens the influence of digital promotion on public preferences. These findings suggest that digital promotion not only exerts a direct impact but also contributes to the formation of a positive image of public hospitals. This study concludes that well-planned and consistently managed digital promotion can serve as an effective strategy for enhancing public preferences and trust in public healthcare services.
PENGARUH KUALITAS PELAYANAN ROOM SERVICE DAN FASILITAS HOTEL TERHADAP KEPUASAN PELANGGAN DI V HOTEL & RESIDENCE BANDUNG
Prasetiyo, Budi;
Ristiawati, Monika
TRANSEKONOMIKA: AKUNTANSI, BISNIS DAN KEUANGAN Vol. 2 No. 5 (2022): September 2022
Publisher : Transpublika Publisher
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.55047/transekonomika.v2i5.233
Hospitality is an aspect of a very large field of business and includes many access fields of work. Therefore, the hotel does not only function to provide services, but also emphasizes the service aspect. Aspects of supporting hotel services and facilities are important points in creating customer satisfaction in a hotel business, for example the completeness of hotel facilities and the friendliness of room service will be of added value in the eyes of customers. This study aims to determine the effect of the quality of room service and hotel facilities on customer satisfaction at V Hotel & Residence Bandung. This study uses a descriptive research method with a quantitative approach. In this study, the variables used are Room Service Quality (X1), Hotel Facilities (X2) and Customer Satisfaction (Y). This research carried out in V Hotel & Residence Bandung, with a total of 100 respondents. Based on the results of the research above, it can be concluded that, the quality of room service (X1) and hotel facilities (X2) partially has a significant effect on customer satisfaction (Y). This indicates that the quality of room service and hotel facilities can affect customer satisfaction V Hotel & Residence Bandung.
PENGARUH KUALITAS PRODUK DAN PERSEPSI HARGA TERHADAP KEPUTUSAN PEMBELIAN SEPEDA MOTOR HONDA BEAT PADA DEALER CV. SUPRA JAYA MOTOR CIANJUR
Nardo, Leo;
Prasetiyo, Budi
TRANSEKONOMIKA: AKUNTANSI, BISNIS DAN KEUANGAN Vol. 2 No. 5 (2022): September 2022
Publisher : Transpublika Publisher
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.55047/transekonomika.v2i5.234
Motorcycles are a favorite means of transportation that are chosen by the community, especially because the current level of congestion is very high, so that one alternative is to make it easier and smoother to reach destinations in the city. The growth of motorcycle consumers that continues to fluctuate resulting in many new entrants in various categories. This study aims to obtain data and information regarding product quality and price perceptions, and to determine the extent of their influence on purchasing decisions for Honda BEAT Motorcycles in Cianjur. This study uses quantitative methods and uses the Non-Probability Sampling technique with an incidental sampling technique approach of 72 people. The research findings found that the variable quality of the product on the Honda BEAT motorcycle can be seen that the score is 305.8. Variable price perception on the Honda BEAT motorcycle can be seen that the results are very good because it reaches a score of 304.25. Variable purchasing decisions for Honda BEAT motorcycles at CV. Supra Jaya Motor Cianjur Dealers can be seen the results are good because they reach a score of 296.4.