MétaCan
Menu
Back to cohort

A Novel Approach to Responding to Key Data Anomalies Using Unsupervised Learning: Work In Progress

2025· article· W4417510432 on OpenAlexaff
Feri Hari Utami, Deris Stiawan, Dian Palupi Rini, Anto Satriyo Nugroho, Lukman Lukman

Bibliographic record

Venuenot available
Typearticle
Language
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsKey (lock)Data pre-processingPreprocessorConfusionData qualityAnomaly detectionHyperparameterData modeling

Abstract

fetched live from OpenAlex

The Student Information System (SIS) plays a crucial role in managing educational data, supporting policy-making, planning, and budget allocation, including the School Operational Assistance (BOS) program. However, data anomalies such as duplicate identities, entry errors, and administrative inconsistencies undermine data validity. Manual anomaly handling is inefficient, particularly at a national scale. This study proposes an unsupervised machine learning approach using the One-Class Support Vector Machine (OC-SVM) to automatically and continuously detect anomalies in educational datasets. A total of 25,204 records from Bengkulu Province were used, with preprocessing involving cleaning, encoding, scaling, and data splitting. Model training includes hyperparameter tuning for optimal performance. Evaluation is conducted using accuracy, precision, recall, F1-score, and confusion matrix. Experimental results show that the OC-SVM model successfully detected 14,424 anomalies with an accuracy of 95%. These findings highlight the potential of automated approaches to improve the quality of national educational data and support future integration into SIS dashboards and further development through ensemble methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.018
metaresearch head score (Gemma)0.007
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Bibliometrics, Scholarly communication, Open science
Consensus categoriesOpen science
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.756
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0180.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0050.023
Science and technology studies0.0010.000
Scholarly communication0.0030.002
Open science0.0070.015
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.368
GPT teacher head0.458
Teacher spread0.091 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicData Quality and ManagementFrench-language works237,207