Article Per Year (5 Year)
p-Index From 2021 - 2026
1.048
P-Index
This Author published in this journals
All Journal International Journal of Social Science and Business JATI (Jurnal Mahasiswa Teknik Informatika) Journal of Information Systems and Technology Research Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Journal of Computer Science and Information Technology
Andri Fauzan Adziima
Data Science Department, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya, Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Social Sciences

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Pengembangan Algoritma Sharpe Ratio dengan Integrasi Filter Tren SMA dalam Strategi Portofolio Aset Kripto Andri Fauzan Adziima; Shindi Shella May Wara; Muhammad Nasrudin; Alfan Rizaldy Pratama
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 1 (2025): Juni 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i1.383

Abstract

Penelitian ini mengusulkan sebuah strategi alokasi aset kripto yang bersifat dinamis, dengan menggabungkan pembobotan berdasarkan Sharpe Ratio dan penyaringan tren menggunakan indikator Simple Moving Average (SMA) dari Bitcoin (BTC). Model ini melakukan alokasi ulang modal setiap tiga hari pada tujuh aset kripto utama (BTC, ETH, BNB, SOL, TON, TRX, XRP), dengan ketentuan bahwa harga BTC berada di atas ambang SMA tertentu (50 hari, 100 hari, atau 200 hari). Apabila BTC berada di bawah nilai SMA tersebut, seluruh portofolio secara otomatis dialihkan ke USDT untuk menekan risiko penurunan nilai. Studi ini menggunakan data historis dari 1 Januari 2024 hingga 1 Januari 2025 dan menguji performa model dalam tiga konfigurasi SMA, lalu dibandingkan dengan strategi dasar buy-and-hold. Hasil menunjukkan bahwa strategi dengan parameter SMA 50 hari menghasilkan return kumulatif tertinggi (+231,51%) serta rasio Sharpe terbaik (2,51), jauh melampaui model dengan SMA yang lebih panjang maupun rata-rata return dari strategi dasar (+132,14%). Analisis risiko mengindikasikan bahwa jendela SMA yang lebih pendek memberikan respons yang lebih cepat terhadap tren naik pasar, meskipun disertai dengan peningkatan volatilitas jangka pendek. Secara keseluruhan, temuan ini menguatkan efektivitas strategi hibrida yang mengombinasikan penyaringan tren dengan alokasi berbasis risiko dalam pengelolaan portofolio kripto di tengah kondisi pasar yang fluktuatif.
Optimasi Sistem Antrian Pada Medical Center ITS Dengan Simulasi Discrete Event Dan Response Surface Methodology Shindi Shella May Wara; Muhammad Nasrudin; Andri Fauzan Adziima; Alfan Rizaldy Pratama
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 1 (2025): Juni 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i1.411

Abstract

Medical Center ITS berfungsi sebagai unit rawat jalan yang melayani pemeriksaan, tindakan medis, penunjang medis, dan rujukan bagi civitas academica ITS serta masyarakat umum dengan biaya yang terjangkau. Penelitian ini bertujuan untuk mengoptimalkan sistem antrean di Medical Center ITS, yang sering menghadapi antrean panjang dan berdampak pada waktu tunggu pasien serta efisiensi pelayanan, menggunakan pendekatan simulasi diskrit. Data primer, meliputi waktu antar kedatangan dan waktu pelayanan (resepsionis, poli umum, poli gigi, resep, dan pengambilan obat), dikumpulkan secara empiris untuk memodelkan sistem antrean berbasis kejadian. Model simulasi yang dikembangkan secara akurat merepresentasikan seluruh alur pelayanan. Hasil simulasi menunjukkan bahwa sistem pelayanan saat ini belum optimal dengan hanya satu server di poli umum dan satu di poli gigi. Berdasarkan temuan, skenario penambahan server pada poli gigi menjadi empat dan tetap satu server di poli umum diusulkan sebagai konfigurasi optimum. Implementasi skenario ini terbukti secara signifikan mengurangi waktu tunggu rata-rata pasien dan meningkatkan tingkat utilitas sumber daya. Penelitian ini menegaskan bahwa simulasi diskrit adalah alat pengambilan keputusan yang efektif untuk meningkatkan kualitas dan efisiensi pelayanan di fasilitas kesehatan.
Prediksi Kebutuhan Rawat Inap Pasien Berdasarkan Data Hematologi Menggunakan Random Forest dengan Hyperparameter Optimization dan SHAP Explainability Milla Akbarany Baktiar Putri Putri; Hana Titania Sastrian; Muhammad Erlangga Kurniawan; Andri Fauzan Adziima; Kartika Maulida Hindrayani; Muhammad Zulhaj Aliansyah
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.650

Abstract

Determining whether a patient requires inpatient or outpatient care is one of the most critical clinical decisions in healthcare facility management. Complete blood count (CBC) parameters provide routine and rapidly available physiological indicators, making them strong candidates for machine learning-based clinical decision support systems. This study aims to develop a prediction model for patient hospitalization needs using the Random Forest algorithm optimized through RandomizedSearchCV, combined with SHAP (SHapley Additive exPlanations) for model interpretability. The dataset consists of 4,412 patient records from an Indonesian private hospital available on Kaggle, containing nine hematological parameters and two demographic attributes. Feature engineering was applied by constructing three derived variables: leucocyte-thrombocyte ratio (leu_throm_ratio), hemoglobin-hematocrit ratio (hb_hct_ratio), and thrombocyte-age interaction (platelet_age). Two models were compared: a baseline Random Forest with manually configured hyperparameters and an optimized model using RandomizedSearchCV with Stratified 5-Fold Cross Validation. The baseline model achieved accuracy of .7633 and ROC AUC of .8097, while the optimized model yielded accuracy of .7644 and ROC AUC of .8131 on the test set. Feature importance analysis identified thrombocyte (.1655) and leu_throm_ratio (.1525) as the dominant predictors, together contributing over 31% of the model's predictive information. SHAP analysis confirmed that low thrombocyte values and high leucocyte values were the primary drivers of inpatient predictions, consistent with clinical indicators of infection and systemic inflammation. These findings demonstrate that Random Forest with clinically grounded feature engineering and SHAP interpretability provides a transparent and reasonably accurate approach for supporting hospital admission triage decisions.
Multidimensional Analysis of Hashtag-Driven Conversations: Detecting Hybrid Discourse Patterns in the #KaburAjaDulu Twitter Campaign Andri Fauzan Adziima; Wahyu SJ Saputra; Windri Saifudin; Meisya Vira Amelia; Alumdadini Bilqis Lanisari
International Journal of Social Science and Business Vol. 10 No. 1 (2026): February
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/ijssb.v10i1.105807

Abstract

This study investigated the multidimensional dynamics of the Indonesian hashtag #KaburAjaDulu on Twitter (X) between April and July 2025. By integrating sentiment analysis, social network analysis (SNA), and topic modeling, the research developed a framework to distinguish organic grassroots discourse from coordinated non-organic amplification, often associated with "buzzer" activity. Findings revealed that conversation volume peaked in May and July 2025, largely dominated by positive sentiment. The SNA identified a complex network structure that was simultaneously decentralized and characterized by dense clusters indicative of coordinated behavior. Key actors with high centrality scores functioned as both popular figures and essential information bridges. Topic modeling indicated that positive discourse centered on humor, personal success, and lighthearted narratives, while negative sentiment consistently aligned with themes of national skepticism and career frustration. The integration of these methodologies demonstrated that the #KaburAjaDulu phenomenon was shaped by a multifaceted interplay of trending narratives and influential actors. The study concluded by providing a practical analytical framework for social media and policy research, enabling stakeholders to monitor public discourse and map influential actors to inform evidence-based responses to emerging societal issues.
Implementation of Multi-Level Association Rule Mining Based on Concept Hierarchy in Drug Transaction Analysis to Support Inventory Management Nurul Kamalia Zahra; Mohammad Idhom; Andri Fauzan Adziima
Journal of Information Systems and Technology Research Vol. 5 No. 2 (2026): May 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i2.1606

Abstract

Drug inventory planning is a crucial aspect in logistics management in first-level health care facilities, as the availability of the right type and quantity of drugs greatly affects the quality of service and patient safety. However, in practice, there are still various problems, such as the mismatch between the amount of stock and the real need for limitations in the use of historical data on drug transactions, and the lack of optimal systems in identifying drug use patterns in a structured and data-based manner. This condition has the potential to cause stockouts and overstock, which has an impact on delays in the delivery of therapy, wasted budgets, and increased risk of expired drugs. In addition, the lack of analysis of drug use combinations also hinders more accurate decision-making in inventory planning and control. Based on these problems, this study aims to apply the Multi-Level Association Rule Mining (MLARM) method in identifying combinations of drug use based on transaction data at health facilities. The results of the study showed that the MLARM method  was effective in identifying patterns of drug use associations at various levels of the hierarchy. At the drug class level, it was found that there was a relationship between hard drugs, over-the-counter drugs, and limited over-the-counter drugs which reflected the use of combinations between drug classes in health services. At the group level of therapy, the association involves analgesics, antibiotics, antihistamines, corticosteroids, and decongestants. Meanwhile, at the level of drug names, specific combinations were found, such as Mms with Kalk, Fe with Paracetamol, Ctm with Paracetamol, and Mefenamic Acid with Amoxicillin. This information can be used to support more optimal management of drug supplies and reduce the risk of stockout and overstock.
ANALISIS EMOSI AUDIENS PADA KOMENTAR INSTAGRAM @JTV_REK BERBASIS LATENT SEMANTIC ANALYSIS DENGAN PENDEKATAN ENSEMBLE STACKING UNTUK KLASIFIKASI EMOSI Jasmine Aulia; Amri Muhaimin; Andri Fauzan Adziima
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 10 No. 3 (2026): JATI Vol. 10 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v10i3.18305

Abstract

Perkembangan media sosial telah mengubah pola interaksi masyarakat dalam menyampaikan opini dan ekspresi emosional terhadap berbagai konten digital, khususnya melalui komentar pada platform Instagram. Namun, analisis emosi pada komentar media sosial menghadapi tantangan seperti ketidakseimbangan data, teks yang pendek, dan penggunaan bahasa informal. Penelitian ini bertujuan untuk mengklasifikasikan emosi audiens pada komentar Instagram akun @JTV_rek menggunakan metode Stacking Ensemble dengan dukungan Latent Semantic Analysis (LSA) untuk analisis topik. Dataset yang digunakan terdiri dari 3.701 komentar yang dikumpulkan pada periode Januari 2024 hingga Agustus 2025 dan dilabeli secara manual ke dalam tiga kelas emosi, yaitu joy, netral, dan negative. Representasi fitur menggunakan TF-IDF, sedangkan LSA digunakan untuk mengekstraksi pola semantik. Proses klasifikasi dilakukan dengan menggabungkan Random Forest, Support Vector Machine, dan XGBoost dalam skema Stacking Ensemble dengan Logistic Regression sebagai meta-learner. Hasil penelitian menunjukkan bahwa model terbaik diperoleh pada skenario Stacking tanpa SMOTE dengan nilai accuracy sebesar 74% dan F1-score sebesar 73%. Hasil ini menunjukkan bahwa pendekatan ensemble mampu meningkatkan performa klasifikasi emosi pada data komentar media sosial.
Co-Authors Alfan Rizaldy Pratama Alumdadini Bilqis Lanisari Amri Muhaimin Hana Titania Sastrian Jasmine Aulia Kartika Maulida Hindrayani Meisya Vira Amelia Milla Akbarany Baktiar Putri Putri Mohammad Idhom Muhammad Erlangga Kurniawan Muhammad Nasrudin Muhammad Zulhaj Aliansyah Nurul Kamalia Zahra Shindi Shella May Wara Wahyu SJ Saputra Windri Saifudin