July 30, 2025Information Technology International Journal

Optimization of the SRIKANDI E-Government System Using XGBoost-Based Classification and One-Class SVM Anomaly DetectionType

View Full Paper

Ask AI

Bookmark

Authors

FDFitri Damaryanti ASAji SupriyantoUniversitas Stikubank

Discussion

Member takes

Implication

This analysis demonstrates improved classification and anomaly detection in archival metadata, indicating enhanced data governance in e-government systems.

Key Points

The XGBoost model achieved a classification accuracy of 77% in identifying 'Destructible' archives, enhancing archival efficiency.
Out of 175 archives, the One-Class SVM model successfully detected 16 anomalies, supporting improved metadata integrity.
Data preprocessing and feature selection were key components of implementing machine learning models for archival data optimization.
This integration of AI into e-government systems may enhance transparency and accountability in public sector data management.

Cite This Study

Damaryanti et al. (2025) studied this question.

synapsesocial.com/papers/68af4088cf1dd9ea359ebfcd https://doi.org/10.33005/itij.v3i1.50

View Full Paper

Ask AI

Bookmark

Implication

This analysis demonstrates improved classification and anomaly detection in archival metadata, indicating enhanced data governance in e-government systems.

Optimization of the SRIKANDI E-Government System Using XGBoost-Based Classification and One-Class SVM Anomaly DetectionType

Discussion

Member takes

Implication

Key Points

Cite This Study

Optimization of the SRIKANDI E-Government System Using XGBoost-Based Classification and One-Class SVM Anomaly DetectionType

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider