Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Abadi: Jurnal Ahmad Dahlan Mengabdi Scripta Technica: Journal of Engineering and Applied Technology Technema: Journal of Intelligent Engineering and Computing
Masrur Anwar
Institut Teknologi dan Bisnis Ahmad Dahlan Lamongan
Religion Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

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

Found 3 Documents
Search

 1 
Pendampingan Dan Digitalisasi Pada Usaha Mikro Keripik Singkong Untuk Meningkatkan Daya Saing M adhitya Nugraha Pratama; Masrur Anwar; Ika Purwanti; Imtinan widhah kumala; Irma Indira
Ahmad Dahlan Mengabdi Vol 3 No 2 (2024): ABADI : Jurnal Ahmad Dahlan Mengabdi Edisi September 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Institut Teknologi dan Bisnis Ahmad Dahlan Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58906/abadi.v3i2.199

Abstract

Program pengabdian masyarakat ini bertujuan untuk meningkatkan daya saing usaha mikro keripik singkong di Desa Deket Agung melalui transformasi digital. Pelatihan yang diberikan meliputi pemasaran digital, pembukuan digital, dan manajemen usaha berbasis aplikasi. Hasil dari pelatihan menunjukkan bahwa peserta mengalami peningkatan penjualan hingga 30% dengan memanfaatkan media sosial dan platform e-commerce. Selain itu, penggunaan aplikasi pembukuan digital membantu pengelolaan keuangan yang lebih efisien. Meskipun demikian, tantangan utama yang dihadapi adalah kesulitan dalam penggunaan teknologi bagi beberapa peserta, yang menunjukkan perlunya pendampingan berkelanjutan. Program ini berhasil meningkatkan kapasitas pelaku usaha dan dapat diteruskan dengan pelatihan lanjutan untuk memperluas dampaknya di desa.
Explainable AI (XAI) Analysis Using SHAP for Credit Card Fraud Yanuangga Galahartlambang; Titik Khotiah; Ilham Basri K; Masrur Anwar
Journal of Engineering and Applied Technology Vol 1 No 2 (2025): December: Scripta Technica: Journal of Engineering and Applied Technology
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/scxk4755

Abstract

The increased use of credit cards in digital payment systems has also increased the risk of transaction fraud, which has led to financial losses and a decline in user confidence. Various machine learning approaches have been developed to automatically detect fraud, but most high-performance models are black-box in nature, making them difficult to explain and unsupportive of auditing and decision-making processes. This study aims to analyze the application of Explainable Artificial Intelligence (XAI) using the SHAP (SHapley Additive exPlanations) method in credit card fraud detection systems. An imbalanced credit card transaction dataset was used as experimental data, with two classification models, namely Logistic Regression as a baseline and Random Forest as an ensemble model. Performance evaluation was conducted using Precision, Recall, F1-score, and Average Precision (PR-AUC) metrics, which are more suitable for imbalanced data cases. The experimental results show that the Random Forest model performs better than Logistic Regression, especially in terms of Precision, F1-Score, and PR-AUC metrics. Explainability analysis using SHAP was performed to obtain global and local explanations for the model's decisions. Global explanations successfully identified the dominant features that influence fraud predictions, while local explanations provided an overview of the contribution of individual features to specific fraud transactions. The results of this study show that the application of SHAP can improve the transparency and clarity of fraud detection model decisions without sacrificing prediction performance, thereby potentially supporting the development of a more reliable and easily audited fraud detection system.  
Implementation of SHAP in Ensemble Learning for Interpreting Audit Risk Classification: A Preliminary Study Using a Public Audit Dataset Yanuangga Galahartlambang; Titik Khotiah; Ilham Basri K; Masrur Anwar; Mohamad Akhsan Rofiqi
Technema: Journal of Intelligent Engineering and Computing Vol. 1 No. 2 (2026): : June: Technema: Journal of Intelligent Engineering and Computing
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

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

Abstract

Ensemble learning models can achieve strong predictive performance on structured audit-risk data, yet their complex decision logic can limit transparency and technical accountability. This study develops a proof-of-concept Explainable Artificial Intelligence pipeline using SHapley Additive exPlanations (SHAP) to interpret Random Forest and XGBoost classifiers on the public UCI Audit Data. The experiment processed 776 observations and 27 columns, with one missing value in Money_Value imputed using the median of 0.09 and the non-numeric LOCATION_ID removed, resulting in 25 predictors and one binary target. A stratified 80:20 split with random_state = 42 produced 620 training observations and 156 test observations, with Random Forest achieving 1.0000 across accuracy, precision, recall, F1-score, and ROC-AUC, while XGBoost achieved 0.9936 accuracy, 1.0000 precision, 0.9836 recall, 0.9917 F1-score, and 1.0000 ROC-AUC. SHAP analysis identified Audit_Risk as the dominant global predictor, while its contribution to a representative at-risk prediction reached +5.82, shifting the raw model margin from −0.506 to 5.107 and yielding an estimated probability of approximately 0.994. However, because the dataset's target construction is closely associated with the Audit Risk Score, retaining Audit_Risk as a predictor introduces potential structural target leakage. The findings position the near-perfect performance as evidence of successful pipeline implementation and model interpretability rather than external generalization, supporting future leakage-controlled ablation, cross-validation, and external-data validation.
Co-Authors Ilham Basri K Imtinan Widhah Kumala Irma Indira M Adhitya Nugraha Pratama Mohamad Akhsan Rofiqi Purwanti, Ika Titik Khotiah Yanuangga Galahartlambang