Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Coreid Journal Jurnal Accounting Information System (AIMS)
Yogi Saputra
UIN Sunan Gunung Djati Bandung
Computer Science & IT Economics, Econometrics & Finance Education Other

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

Found 3 Documents
Search

 1 
Natural Language Processing and Random Forest for Mental Health Symptom Identification Using Social Media Data Sigit Sugara; Popon Dauni; Novianti Indah Putri; Yogi Saputra; Nana Suryana
CoreID Journal Vol. 3 No. 3 (2025): November 2025
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v3i3.145

Abstract

This study explores the implementation of machine learning models, specifically Natural Language Processing (NLP) and Random Forest, for detecting mental health symptoms based on text analysis of web-sourced data. The research addresses the challenges of analyzing highly subjective and dynamic text in social media content to identify patterns associated with anxiety, depression, and stress. The methodology involves several preprocessing steps including case folding, cleansing, language normalization, negation conversion, stopword removal, and tokenization, followed by TF-IDF weighting and Random Forest classification. The model evaluation revealed a high accuracy rate of approximately 80%, although achieving a confidence level of 75% proved challenging. This research demonstrates that despite the inherent difficulties in predicting subjectively variable text, the machine learning approaches employed show satisfactory performance in identifying mental health symptoms, offering potential for early detection and intervention systems.
Optimizing Subscription Package Selection Using a Business Intelligence-Based Decision Support System on Customer Payment Data Moch Mukhsin Nauval; Kamaludin Kamaludin; Yogi Saputra
CoreID Journal Vol. 4 No. 2 (2026): July 2026
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v4i2.164

Abstract

Subscription-based business models generate large amounts of customer payment data that has the potential to be used to support strategic decision-making. However, in many companies, the use of this data is still limited to presenting descriptive information through Business Intelligence dashboards, thus failing to produce objective decision recommendations. This condition often results in the selection of superior subscription packages being based on subjective assessments. This study aims to design a Decision Support System (DSS) integrated with Business Intelligence to determine the optimal subscription package. The Analytic Hierarchy Process method is used to determine the criteria weights, Simple Additive Weighting is used to rank alternatives, and the Technique for Order Preference by Similarity to Ideal Solution is used to validate the ranking results. The research data comes from customer payment data including the number of customers, number of transactions, total revenue, and average transaction value. The results show that the New Hit package consistently ranks highest in the SAW and TOPSIS methods. These findings demonstrate that the integration of Business Intelligence and Decision Support System (DSS) can produce objective, stable and reliable data-driven recommendations to support a company's strategic decisions.
Distributed Cloud Performance Benchmarking on Google Cloud Platform Using MobileNetV2 Inference Workloads Yogi Saputra; Muhammad Saifurridwani Ijazi; Wisnu Uriawan
Jurnal Accounting Information System (AIMS) Vol. 9 No. 2 (2026)
Publisher : Ma'soem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/aims.v9i2.2241

Abstract

This study benchmarked MobileNetV2 inference on Google Kubernetes Engine to examine how cluster configuration and concurrent-user load affected service performance. A 3×3 factorial design compared static two-node, static four-node, and autoscaling two-to-four-node deployments at 10, 50, and 100 concurrent users. Five 15-minute runs per treatment yielded 45 experimental units. Client-side throughput, average latency, and error rate were interpreted alongside CPU and pod telemetry. At 100 users, the two-node configuration recorded 14.40 requests/s, 7,121.81 ms latency, and 70.67% errors. Four static nodes recorded 19.62 requests/s, 4,636.13 ms latency, and 50.53% errors. The 36.25% throughput increase was less than proportional to the doubled node count at that load. Autoscaling recorded 19.82 requests/s and 69.79% errors at 100 users, while its 50-user treatment coincided with pod thrashing. The reported two-way analysis of variance indicated significant configuration, load, and interaction effects at the 0.05 level; exact assumption-test outputs and sums of squares were unavailable for independent verification. The results showed that the tested configurations did not ensure reliable service under high concurrency. Resource limits, timeouts, and autoscaling settings remained plausible contributors requiring controlled follow-up experiments.
Co-Authors Kamaludin Kamaludin Moch Mukhsin Nauval Muhammad Saifurridwani Ijazi Nana Suryana Novianti Indah Putri Popon Dauni Sigit Sugara Wisnu Uriawan, Wisnu