Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bulletin of Intelligent Machines and Algorithms
Angela Nisrina Zhafir
Universitas Informatika dan Bisnis Indonesia
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : bulletin of intelligent machines and algorithms

 1 
Classification of Pension Program Service Workload Levels Across Payment Cities at PT ASABRI (Persero) Bandung Branch Office Using Machine Learning Models Angela Nisrina Zhafir; Nur Alamsyah
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 6 (2026): BIMA issue September 2026
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i6.44

Abstract

This study classifies service workload levels across 13 cities served by the PT ASABRI (Persero) Bandung Branch Office to mitigate evaluation bias by implementing the CRISP-DM methodology on transaction data from 2023 to 2024. The target variable was constructed by combining multiple operational variables into a composite score index, using percentile cutoffs to define High, Medium, and Low workload categories. Under an Out-of-Time Validation (OOTV) framework, data from 2023 served as training data and data from 2024 as testing data, followed by the application of the Synthetic Minority Oversampling Technique (SMOTE) exclusively to the training data to neutralize class imbalance. Comparative evaluation identified a Random Forest model optimized via RandomizedSearchCV as the top-performing model, achieving an accuracy of 83.33%, a macro F1-score of 81.17%, and minimal performance discrepancy between training and test sets. Architecture stability was demonstrated through 5-fold cross-validation, yielding an average accuracy of 72.42% with a minimal standard deviation of 5.69%. Global Feature Importance analysis identified the total number of family dependents (TOTAL_JIWA_DILAYANI) as the dominant operational factor, with an importance score of 0.4145. This comprehensive modeling provides a measurable Early Warning System that enables management to prioritize evaluation areas more systematically while minimizing subjective assumptions.
Co-Authors Nur Alamsyah