Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika RABIT: Jurnal Teknologi dan Sistem Informasi Univrab Jurnal Sistem Komputer dan Informatika (JSON) SKANIKA: Sistem Komputer dan Teknik Informatika Community: Jurnal Pengabdian Pada Masyarakat
Fikri Budiman
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Health Professions Languange, Linguistic, Communication & Media

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Optimalisasi Layanan Administrasi Melalui Pemanfaatan Teknologi Informasi untuk Tenaga Pendidik pada Fakultas Ekonomi dan Bisnis Islam UIN Gus Dur Pekalongan Nur Rokhman; Sindhu Rakasiwi; Edi Sugiarto; Fikri Budiman
Community : Jurnal Pengabdian Pada Masyarakat Vol. 3 No. 3 (2023): November : Jurnal Pengabdian Pada Masyarakat
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/community.v3i3.421

Abstract

Administrasi mengambil peran yang sangat penting dalam sebuah organisasi, lembaga ataupun negara sebagai tolok ukur kemajuannya. Buruknya pengelolaan administrasi dan layanannya dapat mengakibatkan kehancuran, tanpa perlu adanya musibah bencana alam ataupun perang. Pesatnya perkembangan teknologi informasi saat ini dapat dimanfaatkan dalam mengoptimalkan layanan administrasi, terutama di sektor pendidikan, karena sektor pendidikan memegang peran penting dalam modal membangun kemajuan bangsa. Tenaga pendidik sesuai undang-undang juga bertugas dalam administrasi dan pelayanan teknis, maka dari itu kali ini diadakan kegiatan pengabdian kepada masyarakat berupa pelatihan dengan tujuan optimalisasi layanan administrasi yang ditujukan untuk tenaga pendidik pada Fakultas Ekonomi dan Bisnis Islam UIN Gus Dur Pekalongan. Hasilnya, pekerjaan menjadi lebih mudah dan lebih cepat untuk bertukar informasi antar bagian, dan kepala bagian TU dapat dengan mudah memantau pekerjaan terkait dengan administrasi dan layanannya, karena data dapat diakses secara online.
Analisis Perbandingan Algoritma K-Nearest Neighbor dan Decision Tree dalam Klasifikasi Tingkat Obesitas Rizki Wahyu Yulianti; Fikri Budiman; Defri Kurniawan
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 2 (2025): Desember 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i2.9227

Abstract

Kasus obesitas yang terus bertambah di era digital dipengaruhi oleh perubahan gaya hidup, pola makan, aktivitas fisik, serta faktor demografis. Untuk mendukung upaya deteksi dini, penelitian ini menerapkan metode machine learning guna mengklasifikasikan tingkat obesitas berdasarkan Obesity Levels Dataset yang memuat 2.111 data individu dengan 17 variabel terkait perilaku dan kondisi fisik. Penelitian berfokus pada analisis perbandingan dua algoritma klasifikasi, yaitu K-Nearest Neighbor (KNN) dan Decision Tree, dengan tujuan menilai akurasi, presisi, recall, serta stabilitas performa kedua model setelah melalui proses optimasi. Tahapan penelitian dimulai dengan pembersihan data, imputasi nilai hilang menggunakan median, penghapusan outlier melalui metode IQR, encoding variabel kategori, serta standardisasi fitur numerik. Untuk menangani ketidakseimbangan kelas, digunakan teknik SMOTE sehingga setiap kategori kelas target memiliki distribusi yang seimbang. Model kemudian dilatih menggunakan data latih sebesar 80% dan dievaluasi pada 20% data uji. Optimasi parameter dilakukan menggunakan GridSearchCV. Pada model K-Nearest Neighbor, nilai k terbaik diperoleh pada k = 3 dengan akurasi 86,59%. Sementara itu, Decision Tree mencapai performa optimal pada konfigurasi max_depth = 10, min_samples_split = 5, dan min_samples_leaf = 1. Hasil evaluasi menunjukkan bahwa kedua algoritma mampu melakukan klasifikasi tingkat obesitas dengan baik setelah proses tuning dan penyeimbangan data. Decision Tree memberikan performa yang lebih stabil dalam mengenali pola kompleks antarvariabel, sedangkan K-Nearest Neighbor menunjukkan performa optimal pada nilai k kecil ketika data telah distandarisasi dan diseimbangkan. Penelitian ini memberikan gambaran empiris mengenai efektivitas kedua algoritma dalam pemodelan klasifikasi obesitas serta dapat menjadi dasar pengembangan sistem prediksi kesehatan berbasis machine learning yang lebih akurat dan efisien.
ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI GOJEK MENGGUNAKAN METODE RANDOM FOREST, SVM, DAN LOGISTIC REGRESSION Anugrah Ramadhani; Fikri Budiman
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8141

Abstract

The development of digital applications such as Gojek has generated a wide range of user reviews that can be used to assess service quality and user satisfaction. However, the large volume and unstructured nature of these reviews make manual sentiment identification inefficient, which encourages the use of sentiment analysis techniques to automatically process user opinions. This study compares the performance of Random Forest, Support Vector Machine (SVM), and Logistic Regression in analyzing opinions from Gojek user reviews. The dataset consists of 8,091 Indonesian-language reviews obtained from Kaggle. The research process includes data preprocessing such as cleaning, removing irrelevant words, and stemming using the Sastrawi library. The reviews are then converted into numerical features using the TF-IDF method. The dataset is split into 80% training data and 20% testing data before classification using the three algorithms. Model performance is evaluated using accuracy, precision, recall, and F1-score. The results show that Logistic Regression achieves the highest accuracy of 91.84%, followed by SVM with 89.99% and Random Forest with 86.09%. In addition, Logistic Regression shows more balanced performance across positive, negative, and neutral sentiment classes based on precision, recall, and F1-score. Based on the results, Logistic Regression is identified as the most effective method for sentiment analysis of Gojek user reviews in this study.  
KLASIFIKASI KELAYAKAN KREDIT MENGGUNAKAN RANDOM FOREST DENGAN OPTIMISASI SMOTENC DAN GRIDSEARCHCV Nandito Diaz Vannesa; Fikri Budiman
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 9 No 2 (2026): Jurnal SKANIKA Juli 2026
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v9i2.3829

Abstract

Creditworthiness is critical to financial system stability, yet conventional methods struggle with imbalanced data and mixed numeric-categorical features. This study develops the CreditRF-OptSHAP pipeline, integrating Random Forest, SMOTENC, GridSearchCV, and SHAP to improve credit classification performance and interpretability. The dataset used, Statlog German Credit Data (UCI), comprises 1,000 instances, 20 mixed features, and a 70:30 imbalance ratio. The pipeline comprises five phases: data exploration; preprocessing via label encoding and StandardScaler; SMOTENC-based training-set balancing; hyperparameter optimization via GridSearchCV with Stratified 10-Fold Cross Validation; and model interpretation via SHAP TreeExplainer so that each feature's contribution to prediction is explained, making the model no longer a black box. The significance of this recall gain over RF Default was validated using McNemar's Test to rule out statistical coincidence. The main model (RF+SMOTENC+GridSearchCV) achieved a recall of 0.5833 for the bad credit class and an AUC-ROC of 0.7638, up from 0.5000 for RF Default. SHAP analysis identified checking account status as the most dominant feature (importance 0.1239). The McNemar test confirmed a statistically significant difference (p=0.041), confirming its validity. The CreditRF-OptSHAP pipeline yields a model that is more sensitive to non-performing loans, transparent, and statistically validated, thus supporting accountable credit decisions in financial institutions.
Comparison of Classification Methods for Email Spam Detection Rifqi Arya Saputra; Fikri Budiman
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 4 (2026): Research Articles October 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i4.16789

Abstract

Email spam remains a persistent cybersecurity problem, since unsolicited messages waste user time and often deliver phishing or malicious content. Prior comparative studies of conventional spam classifiers rarely state clearly whether their preprocessing avoids leakage between training and test data, or whether reported metrics come from a held-out test set or from cross-validation. This study addresses that gap by comparing five conventional classifiers — Naïve Bayes, Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) — under a pipeline in which the 80:20 train-test split is performed first, TF-IDF is fit only on the training partition, and SMOTE oversampling is applied only to the training data, so the test set stays unseen during model development. A public Kaggle email dataset of 5,157 messages (4,516 legitimate, 641 spam) was used, with spam explicitly defined as the positive class. On the untouched test set, SVM achieved the best overall performance (98.55% accuracy, 98.40% precision, 90.44% recall, 94.25% F1-score), followed by Random Forest (98.16% accuracy, 97.56% precision), while Logistic Regression obtained the highest recall (95.59%). Comparing these results with five-fold cross-validation on the already-oversampled training data revealed a large optimistic gap — up to about 30 points in precision for Naïve Bayes — demonstrating why resampling must be repeated inside each fold rather than applied once beforehand. The findings show that reported performance depends strongly on how resampling interacts with data splitting, and provide a transparent, leakage-aware baseline for future spam-detection research.
Co-Authors Anugrah Ramadhani Defri Kurniawan Edi Sugiarto Nandito Diaz Vannesa Nur Rokhman Rifqi Arya Saputra Rizki Wahyu Yulianti Sindhu Rakasiwi