Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer Explore
Rahmaddeni
Universitas Sains dan Teknologi Indonesia
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analisis Perbandingan Efektivitas Metode Fuzzy C-Means dan K-Means dalam Mengelompokkan Buku Berdasarkan Frekuensi Peminjaman di Perpustakaan SMKN 1 Mandau Juliandri Saputra; Muhammad Iqbal Al Aksha; Lily Maryani; Gilang; Rahmaddeni
Explore Vol 14 No 2 (2024): Juli 2024
Publisher : Universitas Teknologi Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35200/ex.v14i2.121

Abstract

This research investigates and compares the effectiveness of two data grouping methods, namely Fuzzy C-Means (FCM) and K-Means, in grouping books based on borrowing frequency in the SMKN 1 Mandau Library. The data used is a track record of book borrowing during a certain period. This analysis aims to evaluate the most suitable method for grouping books based on their borrowing patterns. The FCM method is used to consider uncertainty in grouping, while K-Means prioritizes certainty in group division. The results of the analysis can provide deeper insight into reading preferences in libraries, as well as help library managers in designing book placement strategies that are more effective and responsive to different borrowing patterns. The results of the comparison between K-Means and Fuzzy C-Means in grouping subjects based on borrowing frequency at the SMKN 1 Mandau Library show that K-Means has an SSE of 162,083, indicating good centralization of data in its clusters by grouping subjects into two clusters separated. On the other hand, Fuzzy C-Means shows a centroid with a value of [116.03, 136.52], indicating a more flexible approach with varying degrees of membership for each cluster, and a cluster pattern similar to K-Means. Although K-Means is slightly faster in execution with 0.0031 seconds compared to Fuzzy C-Means which requires 0.0032 seconds, both show almost the same time efficiency. Overall, Fuzzy C-Means is proven to be more effective based on centroid value evaluation in handling data with different degrees of membership, while both K-Means and Fuzzy C-Means provide consistent clustering results and can be considered according to the needs of book lending data analysis in the library of SMKN 1 Mandau.
Prediksi Pelanggan VIP Internet Service Provider Menggunakan Regresi Linear Vivi Triani Malya; Ahmadi; Ahmad Tara Pratama; Rahmaddeni
Explore Vol 14 No 2 (2024): Juli 2024
Publisher : Universitas Teknologi Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35200/ex.v14i2.122

Abstract

In the internet service industry, identifying and predicting VIP customers is crucial for enhancing retention and profitability. This study aims to predict VIP customers using the linear regression method. The data used includes various customer attributes such as monthly data usage, subscription duration, payment history, and bandwidth used. By applying linear regression, a model was developed to identify the factors that most influence the VIP status of customers. The results of the study show that monthly data usage and subscription duration are significant predictors for classifying VIP customers. The resulting linear regression model has an adequate level of accuracy in predicting VIP customers. These findings can help internet service providers design more effective marketing strategies and service personalization to enhance customer satisfaction and loyalty. The application of linear regression in VIP customer prediction provides valuable insights into customer behavior and enables companies to be proactive in managing customer relationships. This research also opens opportunities for further exploration using more complex analytical methods such as logistic regression and machine learning to improve prediction accuracy.
KLASIFIKASI PENJUALAN WALMART MENGGUNAKAN ALGORITMA C4.5 Iftar Ramadhan; Rangga Febrio Waleska; Syarifuddin elmi; Lusiana Efrizoni; Rahmaddeni
BETRIK Vol. 15 No. 02 (2024): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/pjbkse24

Abstract

Penelitian ini bertujuan untuk memprediksi penjualan Walmart dengan menggunakan algoritma C4.5, sebuah metode pohon keputusan yang populer dalam data mining. Prediksi penjualan merupakan aspek krusial bagi strategi bisnis Walmart untuk mengoptimalkan persediaan dan meningkatkan keuntungan. Dataset yang digunakan dalam penelitian ini mencakup data historis penjualan Walmart yang terdiri dari berbagai variabel seperti store, date, weakly sales, holiday flag, temperature, fuel price, uci, unemployment dan faktor-faktor lain yang mempengaruhi penjualan. Dari data variabel tersebut akan melakukan klasifikasi pada data penjualan walmart dari 6.345 record. Hasil pengujian metode dengan evaluasi modeling menunjukkan bahwa metode C4.5 mendapatkan hasil acuracy 0.94, precision 0.43, dan recall 0.75.
PERBANDINGAN ALGORITMA RANDOM FOREST DAN XGBOOST UNTUK KLASIFIKASI PENYAKIT PARU-PARU BERDASARKAN DATA DEMOGRAFI PASIEN Risky Harahap; M. Irpan; M. Azzuhri Dinata; Lusiana Efrizoni; Rahmaddeni
BETRIK Vol. 15 No. 02 (2024): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/3v3xwn06

Abstract

Dalam penelitian ini, algoritma Random Forest dan XGBoost dibandingkan dalam klasifikasi penyakit paru-paru menggunakan data demografi pasien. Dataset yang digunakan terdiri dari 30.000 data pasien dengan 9 atribut dan 1 label yang diambil dari Kaggle. Tahapan penelitian termasuk pengumpulan data, Preprocessing, pembagian data, dan klasifikasi data menggunakan kedua algoritma. Hasil menunjukkan bahwa algoritma XGBoost memiliki akurasi 94% dan AUC 0.98, sedangkan algoritma Random Forest memiliki akurasi 91% dan AUC 0.97. Meskipun Random Forest lebih cepat dan lebih mudah diinterpretasikan, XGBoost bekerja lebih baik dengan data yang kompleks dengan hasil yang lebih konsisten. Melalui penggunaan teknik regularisasi dan penanganan outliers yang lebih baik, XGBoost juga dapat mengatasi masalah overfitting dengan lebih baik. Studi ini memberikan panduan untuk peneliti dan praktisi dalam memilih algoritma terbaik untuk tugas klasifikasi medis, terutama yang berkaitan dengan penyakit paru-paru.
Co-Authors Ahmad Tara Pratama Ahmadi Gilang Iftar Ramadhan Juliandri Saputra Lily Maryani Lusiana Efrizoni M. Azzuhri Dinata M. Irpan Muhammad Iqbal Al Aksha Rangga Febrio Waleska Risky Harahap Syarifuddin Elmi Vivi Triani Malya