Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Teknik Industri : Jurnal Hasil Penelitian dan Karya Ilmiah dalam Bidang Teknik Industri ALMUISY: Journal of Al Muslim Information System
Gunawan Raharjo
Universitas Pancasakti Tegal
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Environmental Science Industrial & Manufacturing Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Financial Instrument Prediction Using Information Retrieval Algorithm Approach on the Comparison of Tf-IDF, Bm25, and Cosine Similarity Methods Diajeng Tyas; Gunawan; Gunawan Raharjo; Didiek Trisatya; Nur Tulus Ujianto
ALMUISY: Journal of Al Muslim Information System Vol. 5 No. 1 (2026): ALMUISY: Journal of Al Muslim Information System
Publisher : STMIK Al Muslim

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini bertujuan untuk mengembangkan sistem prediksi instrumen finansial yang inovatif menggunakan pendekatan algoritma Information Retrieval. Dalam era digitalisasi pasar keuangan yang semakin kompleks, investor membutuhkan alat bantu pengambilan keputusan yang akurat dan berbasis data. Tiga metode yang dibandingkan adalah Term Frequency-Inverse Document Frequency (TF-IDF), Best Matching 25 (BM25), dan Cosine Similarity. Data dikumpulkan dari Yahoo Finance mencakup 18 instrumen finansial dari berbagai kelas aset termasuk saham teknologi Amerika Serikat, saham blue chip Indonesia, Exchange Traded Funds, dan mata uang kripto. Metodologi penelitian merepresentasikan setiap instrumen sebagai dokumen tekstual berdasarkan indikator teknikal. Hasil penelitian menunjukkan ketiga metode memiliki korelasi peringkat tinggi dengan Spearman Correlation di atas 0.94. Metode BM25 memberikan performa terbaik dengan NDCG sebesar 0.8756 dan MAP sebesar 0.8124. Instrumen yang diprediksi mengalami kenaikan meliputi NVIDIA, AMD, Bitcoin, Amazon, dan Microsoft.
Prediksi Customer Churn Berbasis Attention Gated Residual Deep Neural Network dengan Optimasi Optuna pada Tiga Dataset Transformasi Digita Diajeng Tyas; Gunawan; Nur Tulus Ujianto; Gunawan Raharjo; Didiek Trisatya
ALMUISY: Journal of Al Muslim Information System Vol. 5 No. 2 (2026): ALMUISY: Journal of Al Muslim Information System
Publisher : STMIK Al Muslim

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Transformasi digital pada sektor jasa seperti telekomunikasi, perbankan, dan perdagangan elektronik menuntut sistem informasi yang mampu mengidentifikasi pelanggan berisiko churn secara akurat dan tepat waktu. Penelitian ini mengusulkan model deep learning Attention-Gated Residual Deep Neural Network (AGR-DNN) untuk prediksi customer churn, dengan hyperparameter yang dioptimasi menggunakan Optuna berbasis Tree-structured Parzen Estimator. Model diuji pada tiga dataset sekunder publik dari domain berbeda, yaitu Telco Customer Churn, Bank Customer Churn, dan E-Commerce Customer Churn, untuk memperkuat generalisasi temuan dan memperkaya kajian state of the art. Studi ablasi dilakukan dengan menghilangkan komponen attention gate, koneksi residual, teknik SMOTE, dan optimasi Optuna secara bergantian pada ketiga dataset. Hasil pengujian menunjukkan model AGR-DNN penuh mencapai rata-rata F1-score 0,717, AUC 0,900, dan recall 0,824, mengungguli baseline Random Forest dan Logistic Regression terutama pada recall yang krusial bagi strategi retensi pelanggan. SMOTE terbukti sebagai komponen dengan kontribusi konsisten terbesar terhadap kenaikan recall pada ketiga dataset (4,9-30,6 poin persentase), sementara optimasi Optuna meningkatkan F1-score hingga 3,7 poin persentase dibandingkan hyperparameter default. Penelitian ini berkontribusi pada pengembangan sistem informasi prediktif berbasis data yang mendukung transformasi digital pada organisasi jasa..
Quantifying Threshold Sensitivity in Vision-Based Ergonomic Assessment: Decision Stability of RULA and REBA in a Batik Workshop Siswiyanti; Olivia Suci Fajriati; Diajeng Tyas Purwa Hapsari; Gunawan Raharjo
JTI: Jurnal Teknik Industri Vol 12 No 2 (2026): December 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/jti.v12i2.40558

Abstract

Automated pose-estimation pipelines usually report one RULA or REBA score per frame, without indicating whether that decision would survive small errors in the estimated joint angles. Both instruments convert continuous angles into ordinal categories through fixed thresholds and non-additive lookup tables, so the same angular error may leave one decision unchanged while reversing another. Earlier vision-based studies report aggregate agreement with reference systems or experts; none attaches a robustness statement to the individual decision. This study proposes a reproducible protocol that does so. It combines an observability audit, conditional lower and upper bounds for decisions whose inputs cannot all be seen, controlled angle-level perturbation at magnitudes anchored to published single-camera angle errors (σ = 2, 5, 8, and 12°), and a set of metrics in which baseline decision retention (BDR) measures whether the reported decision survives and the Ergonomic Decision Stability Index (EDSI) measures the probability of the most frequent category after perturbation. The protocol was instantiated on one batik worker (four photographs, four videos). At the level of the RULA action level, the four photographed postures retained their lower-bound decision in at least 93% of replications at σ = 5°, although two of them lay only 0.1° and 0.2° from a component threshold, where distance-based predictors anticipated retention of only 21–52%. The same posture that was stable under RULA retained its REBA risk level in only 49% of replications. Unobserved inputs left the final action level undetermined between its bounds for every posture. Across 534 video frames, component-level stability fell from 0.88 at 2° to 0.40 at 12°. The results demonstrate the method on one case; they do not support population inference or a validated triage rule.
Co-Authors Diajeng Tyas Diajeng Tyas Purwa Hapsari Didiek Trisatya Gunawan Nur Tulus Ujianto Olivia Suci Fajriati Siswiyanti